From 8669b36c86aa7883e6f79d8adc30349d6fdf7094 Mon Sep 17 00:00:00 2001 From: Kayvan Sylvan Date: Mon, 16 Feb 2026 22:08:53 -0800 Subject: [PATCH] feat: add `audit_consent`, `audit_transparency`, and `detect_silent_victims` patterns ## CHANGES - Add `audit_consent` pattern for detecting manufactured consent via power asymmetry analysis - Add `audit_transparency` pattern for evaluating decision explainability across five dimensions - Add `detect_silent_victims` pattern for identifying voiceless, future, and unaware victims - Register three new patterns in pattern descriptions and extracts JSON files - Add new patterns to ANALYSIS and CR THINKING categories in `suggest_pattern` - Update `pattern_explanations.md` with renumbered entries for all patterns - Add co-author credit for ksylvan on PR #1999 changelog entry - Remove duplicate changelog file `pr-ul-dialogue-patterns.txt` --- cmd/generate_changelog/incoming/1999.txt | 2 +- .../incoming/pr-ul-dialogue-patterns.txt | 7 - data/patterns/pattern_explanations.md | 417 +++++++++--------- data/patterns/suggest_pattern/system.md | 4 +- data/patterns/suggest_pattern/user.md | 12 + .../pattern_descriptions.json | 24 + .../pattern_extracts.json | 12 + 7 files changed, 261 insertions(+), 217 deletions(-) delete mode 100644 cmd/generate_changelog/incoming/pr-ul-dialogue-patterns.txt diff --git a/cmd/generate_changelog/incoming/1999.txt b/cmd/generate_changelog/incoming/1999.txt index eb84f745..cdb370ae 100644 --- a/cmd/generate_changelog/incoming/1999.txt +++ b/cmd/generate_changelog/incoming/1999.txt @@ -1,4 +1,4 @@ -### PR [#1999](https://github.com/danielmiessler/Fabric/pull/1999) by [ghrom](https://github.com/ghrom): feat: add 3 patterns from cross-model AI dialogue research +### PR [#1999](https://github.com/danielmiessler/Fabric/pull/1999) by [ghrom](https://github.com/ghrom) and [ksylvan](https://github.com/ksylvan): feat: add 3 patterns from cross-model AI dialogue research - Added three new patterns derived from stress-testing the Ultimate Law ethical framework across 19 AI systems from 10+ organizations: - **audit_consent**: Performs power asymmetry analysis for consent verification, addressing "consent theater" critique diff --git a/cmd/generate_changelog/incoming/pr-ul-dialogue-patterns.txt b/cmd/generate_changelog/incoming/pr-ul-dialogue-patterns.txt deleted file mode 100644 index 5b050cfa..00000000 --- a/cmd/generate_changelog/incoming/pr-ul-dialogue-patterns.txt +++ /dev/null @@ -1,7 +0,0 @@ -# Release Notes - -### PR by [ghrom](https://github.com/ghrom): feat: add 3 patterns from cross-model AI dialogue research - -- Add `audit_consent` pattern for detecting manufactured consent through power asymmetry analysis -- Add `detect_silent_victims` pattern for identifying parties harmed but unable to speak up (future, voiceless, unaware, diffuse, structural) -- Add `audit_transparency` pattern for evaluating whether decisions are explainable to affected parties diff --git a/data/patterns/pattern_explanations.md b/data/patterns/pattern_explanations.md index 2d50ffe8..0d241e7d 100644 --- a/data/patterns/pattern_explanations.md +++ b/data/patterns/pattern_explanations.md @@ -42,210 +42,213 @@ 38. **apply_ul_tags**: Apply standardized content tags to categorize topics like AI, cybersecurity, politics, and culture. 39. **ask_secure_by_design_questions**: Generates a set of security-focused questions to ensure a project is built securely by design, covering key components and considerations. 40. **ask_uncle_duke**: Coordinates a team of AI agents to research and produce multiple software development solutions based on provided specifications, and conducts detailed code reviews to ensure adherence to best practices. -41. **capture_thinkers_work**: Analyze philosophers or philosophies and provide detailed summaries about their teachings, background, works, advice, and related concepts in a structured template. -42. **check_agreement**: Analyze contracts and agreements to identify important stipulations, issues, and potential gotchas, then summarize them in Markdown. -43. **check_falsifiability**: Evaluates whether claims, definitions, frameworks, and arguments meet the standard of falsifiability — whether they can be tested and potentially proven wrong. -44. **clean_text**: Fix broken or malformatted text by correcting line breaks, punctuation, capitalization, and paragraphs without altering content or spelling. -45. **coding_master**: Explain a coding concept to a beginner, providing examples, and formatting code in markdown with specific output sections like ideas, recommendations, facts, and insights. -46. **compare_and_contrast**: Compare and contrast a list of items in a markdown table, with items on the left and topics on top. -47. **concall_summary**: Analyzes earnings and conference call transcripts to extract management commentary, analyst Q&A, financial insights, risks, and executive summaries. -48. **convert_to_markdown**: Convert content to clean, complete Markdown format, preserving all original structure, formatting, links, and code blocks without alterations. -49. **create_5_sentence_summary**: Create concise summaries or answers to input at 5 different levels of depth, from 5 words to 1 word. -50. **create_academic_paper**: Generate a high-quality academic paper in LaTeX format with clear concepts, structured content, and a professional layout. -51. **create_ai_jobs_analysis**: Analyze job categories' susceptibility to automation, identify resilient roles, and provide strategies for personal adaptation to AI-driven changes in the workforce. -52. **create_aphorisms**: Find and generate a list of brief, witty statements. -53. **create_art_prompt**: Generates a detailed, compelling visual description of a concept, including stylistic references and direct AI instructions for creating art. -54. **create_better_frame**: Identifies and analyzes different frames of interpreting reality, emphasizing the power of positive, productive lenses in shaping outcomes. -55. **create_bd_issue**: Transform natural language descriptions into optimal bd create commands for issue tracking. -56. **create_coding_feature**: Generates secure and composable code features using modern technology and best practices from project specifications. -57. **create_coding_project**: Generate wireframes and starter code for any coding ideas that you have. -58. **create_command**: Helps determine the correct parameters and switches for penetration testing tools based on a brief description of the objective. -59. **create_conceptmap**: Transforms unstructured text or markdown content into an interactive HTML concept map using Vis.js by extracting key concepts and their logical relationships. -60. **create_cyber_summary**: Summarizes cybersecurity threats, vulnerabilities, incidents, and malware with a 25-word summary and categorized bullet points, after thoroughly analyzing and mapping the provided input. -61. **create_design_system**: Create comprehensive CSS design systems with tokens, typography, spacing, and components. -62. **create_design_document**: Creates a detailed design document for a system using the C4 model, addressing business and security postures, and including a system context diagram. -63. **create_diy**: Creates structured "Do It Yourself" tutorial patterns by analyzing prompts, organizing requirements, and providing step-by-step instructions in Markdown format. -64. **create_excalidraw_visualization**: Creates complex Excalidraw diagrams to visualize relationships between concepts and ideas in structured format. -65. **create_flash_cards**: Creates flashcards for key concepts, definitions, and terms with question-answer format for educational purposes. -66. **create_formal_email**: Crafts professional, clear, and respectful emails by analyzing context, tone, and purpose, ensuring proper structure and formatting. -67. **create_git_diff_commit**: Generates Git commands and commit messages for reflecting changes in a repository, using conventional commits and providing concise shell commands for updates. -68. **create_golden_rules**: Extract enforceable rules from codebases to prevent common mistakes and ensure consistency. -69. **create_graph_from_input**: Generates a CSV file with progress-over-time data for a security program, focusing on relevant metrics and KPIs. -70. **create_hormozi_offer**: Creates a customized business offer based on principles from Alex Hormozi's book, "$100M Offers." -71. **create_idea_compass**: Organizes and structures ideas by exploring their definition, evidence, sources, and related themes or consequences. -72. **create_investigation_visualization**: Creates detailed Graphviz visualizations of complex input, highlighting key aspects and providing clear, well-annotated diagrams for investigative analysis and conclusions. -73. **create_keynote**: Creates TED-style keynote presentations with a clear narrative, structured slides, and speaker notes, emphasizing impactful takeaways and cohesive flow. -74. **create_loe_document**: Creates detailed Level of Effort documents for estimating work effort, resources, and costs for tasks or projects. -75. **create_logo**: Creates simple, minimalist company logos without text, generating AI prompts for vector graphic logos based on input. -76. **create_markmap_visualization**: Transforms complex ideas into clear visualizations using MarkMap syntax, simplifying concepts into diagrams with relationships, boxes, arrows, and labels. -77. **create_mermaid_visualization**: Creates detailed, standalone visualizations of concepts using Mermaid (Markdown) syntax, ensuring clarity and coherence in diagrams. -78. **create_mermaid_visualization_for_github**: Creates standalone, detailed visualizations using Mermaid (Markdown) syntax to effectively explain complex concepts, ensuring clarity and precision. -79. **create_micro_summary**: Summarizes content into a concise, 20-word summary with main points and takeaways, formatted in Markdown. -80. **create_mnemonic_phrases**: Creates memorable mnemonic sentences from given words to aid in memory retention and learning. -81. **create_network_threat_landscape**: Analyzes open ports and services from a network scan and generates a comprehensive, insightful, and detailed security threat report in Markdown. -82. **create_newsletter_entry**: Condenses provided article text into a concise, objective, newsletter-style summary with a title in the style of Frontend Weekly. -83. **create_npc**: Generates a detailed D&D 5E NPC, including background, flaws, stats, appearance, personality, goals, and more in Markdown format. -84. **create_pattern**: Extracts, organizes, and formats LLM/AI prompts into structured sections, detailing the AI's role, instructions, output format, and any provided examples for clarity and accuracy. -85. **create_prd**: Creates a precise Product Requirements Document (PRD) in Markdown based on input. -86. **create_prediction_block**: Extracts and formats predictions from input into a structured Markdown block for a blog post. -87. **create_quiz**: Creates a three-phase reading plan based on an author or topic to help the user become significantly knowledgeable, including core, extended, and supplementary readings. -88. **create_reading_plan**: Generates review questions based on learning objectives from the input, adapted to the specified student level, and outputs them in a clear markdown format. -89. **create_recursive_outline**: Breaks down complex tasks or projects into manageable, hierarchical components with recursive outlining for clarity and simplicity. -90. **create_report_finding**: Creates a detailed, structured security finding report in markdown, including sections on Description, Risk, Recommendations, References, One-Sentence-Summary, and Quotes. -91. **create_rpg_summary**: Summarizes an in-person RPG session with key events, combat details, player stats, and role-playing highlights in a structured format. -92. **create_security_update**: Creates concise security updates for newsletters, covering stories, threats, advisories, vulnerabilities, and a summary of key issues. -93. **create_show_intro**: Creates compelling short intros for podcasts, summarizing key topics and themes discussed in the episode. -94. **create_sigma_rules**: Extracts Tactics, Techniques, and Procedures (TTPs) from security news and converts them into Sigma detection rules for host-based detections. -95. **create_story_about_people_interaction**: Analyze two personas, compare their dynamics, and craft a realistic, character-driven story from those insights. -96. **create_story_about_person**: Creates compelling, realistic short stories based on psychological profiles, showing how characters navigate everyday problems using strategies consistent with their personality traits. -97. **create_story_explanation**: Summarizes complex content in a clear, approachable story format that makes the concepts easy to understand. -98. **create_stride_threat_model**: Create a STRIDE-based threat model for a system design, identifying assets, trust boundaries, data flows, and prioritizing threats with mitigations. -99. **create_summary**: Summarizes content into a 20-word sentence, 10 main points (16 words max), and 5 key takeaways in Markdown format. -100. **create_tags**: Identifies at least 5 tags from text content for mind mapping tools, including authors and existing tags if present. -101. **create_threat_scenarios**: Identifies likely attack methods for any system by providing a narrative-based threat model, balancing risk and opportunity. -102. **create_ttrc_graph**: Creates a CSV file showing the progress of Time to Remediate Critical Vulnerabilities over time using given data. -103. **create_ttrc_narrative**: Creates a persuasive narrative highlighting progress in reducing the Time to Remediate Critical Vulnerabilities metric over time. -104. **create_upgrade_pack**: Extracts world model and task algorithm updates from content, providing beliefs about how the world works and task performance. -105. **create_user_story**: Writes concise and clear technical user stories for new features in complex software programs, formatted for all stakeholders. -106. **create_video_chapters**: Extracts interesting topics and timestamps from a transcript, providing concise summaries of key moments. -107. **create_visualization**: Transforms complex ideas into visualizations using intricate ASCII art, simplifying concepts where necessary. -108. **detect_mind_virus**: Detects "mind viruses" — ideas or belief systems that spread by exploiting cognitive shortcuts (fear, guilt, identity) while resisting correction through logic or evidence. -109. **dialog_with_socrates**: Engages in deep, meaningful dialogues to explore and challenge beliefs using the Socratic method. -110. **enrich_blog_post**: Enhances Markdown blog files by applying instructions to improve structure, visuals, and readability for HTML rendering. -111. **explain_code**: Explains code, security tool output, configuration text, and answers questions based on the provided input. -112. **explain_docs**: Improves and restructures tool documentation into clear, concise instructions, including overviews, usage, use cases, and key features. -113. **explain_math**: Helps you understand mathematical concepts in a clear and engaging way. -114. **explain_project**: Summarizes project documentation into clear, concise sections covering the project, problem, solution, installation, usage, and examples. -115. **explain_terms**: Produces a glossary of advanced terms from content, providing a definition, analogy, and explanation of why each term matters. -116. **explain_terms_and_conditions**: Analyzes Terms and Conditions and legal agreements, translating complex legalese into plain English, identifying red flags, hidden fees, and privacy risks, with a final verdict on whether to sign. -117. **export_data_as_csv**: Extracts and outputs all data structures from the input in properly formatted CSV data. -118. **extract_algorithm_update_recommendations**: Extracts concise, practical algorithm update recommendations from the input and outputs them in a bulleted list. -119. **extract_all_quotes**: Extract all inspirational and educational quotes from content including podcasts and essays. -120. **extract_alpha**: Extracts the most novel and surprising ideas ("alpha") from content, inspired by information theory. -121. **extract_article_wisdom**: Extracts surprising, insightful, and interesting information from content, categorizing it into sections like summary, ideas, quotes, facts, references, and recommendations. -122. **extract_book_ideas**: Extracts and outputs 50 to 100 of the most surprising, insightful, and interesting ideas from a book's content. -123. **extract_book_recommendations**: Extracts and outputs 50 to 100 practical, actionable recommendations from a book's content. -124. **extract_bd_ideas**: Extract actionable ideas from content and transform into bd create commands. -125. **extract_business_ideas**: Extracts top business ideas from content and elaborates on the best 10 with unique differentiators. -126. **extract_characters**: Identify all characters (human and non-human), resolve their aliases and pronouns into canonical names, and produce detailed descriptions of each character's role, motivations, and interactions ranked by narrative importance. -127. **extract_controversial_ideas**: Extracts and outputs controversial statements and supporting quotes from the input in a structured Markdown list. -128. **extract_core_message**: Extracts and outputs a clear, concise sentence that articulates the core message of a given text or body of work. -129. **extract_ctf_writeup**: Extracts a short writeup from a warstory-like text about a cyber security engagement. -130. **extract_domains**: Extracts domains and URLs from content to identify sources used for articles, newsletters, and other publications. -131. **extract_ethical_framework**: Extracts and analyzes the implicit ethical framework embedded in any prescriptive text, checking internal consistency and whether it creates unwilling victims. -132. **extract_extraordinary_claims**: Extracts and outputs a list of extraordinary claims from conversations, focusing on scientifically disputed or false statements. -133. **extract_ideas**: Extracts and outputs all the key ideas from input, presented as 15-word bullet points in Markdown. -134. **extract_insights**: Extracts and outputs the most powerful and insightful ideas from text, formatted as 16-word bullet points in the INSIGHTS section, also IDEAS section. -135. **extract_insights_dm**: Extracts and outputs all valuable insights and a concise summary of the content, including key points and topics discussed. -136. **extract_instructions**: Extracts clear, actionable step-by-step instructions and main objectives from instructional video transcripts, organizing them into a concise list. -137. **extract_jokes**: Extracts jokes from text content, presenting each joke with its punchline in separate bullet points. -138. **extract_latest_video**: Extracts the latest video URL from a YouTube RSS feed and outputs the URL only. -139. **extract_main_activities**: Extracts key events and activities from transcripts or logs, providing a summary of what happened. -140. **extract_main_idea**: Extracts the main idea and key recommendation from the input, summarizing them in 15-word sentences. -141. **extract_mcp_servers**: Identify and summarize Model Context Protocol (MCP) servers referenced in the input along with their key details. -142. **extract_most_redeeming_thing**: Extracts the most redeeming aspect from an input, summarizing it in a single 15-word sentence. -143. **extract_patterns**: Extracts and analyzes recurring, surprising, and insightful patterns from input, providing detailed analysis and advice for builders. -144. **extract_poc**: Extracts proof of concept URLs and validation methods from security reports, providing the URL and command to run. -145. **extract_predictions**: Extracts predictions from input, including specific details such as date, confidence level, and verification method. -146. **extract_primary_problem**: Extracts the primary problem with the world as presented in a given text or body of work. -147. **extract_primary_solution**: Extracts the primary solution for the world as presented in a given text or body of work. -148. **extract_product_features**: Extracts and outputs a list of product features from the provided input in a bulleted format. -149. **extract_questions**: Extracts and outputs all questions asked by the interviewer in a conversation or interview. -150. **extract_recipe**: Extracts and outputs a recipe with a short meal description, ingredients with measurements, and preparation steps. -151. **extract_recommendations**: Extracts and outputs concise, practical recommendations from a given piece of content in a bulleted list. -152. **extract_references**: Extracts and outputs a bulleted list of references to art, stories, books, literature, and other sources from content. -153. **extract_skills**: Extracts and classifies skills from a job description into a table, separating each skill and classifying it as either hard or soft. -154. **extract_song_meaning**: Analyzes a song to provide a summary of its meaning, supported by detailed evidence from lyrics, artist commentary, and fan analysis. -155. **extract_sponsors**: Extracts and lists official sponsors and potential sponsors from a provided transcript. -156. **extract_videoid**: Extracts and outputs the video ID from any given URL. -157. **extract_wisdom**: Extracts surprising, insightful, and interesting information from text on topics like human flourishing, AI, learning, and more. -158. **extract_wisdom_agents**: Extracts valuable insights, ideas, quotes, and references from content, emphasizing topics like human flourishing, AI, learning, and technology. -159. **extract_wisdom_with_attribution**: Extracts insightful ideas and recommendations with speaker attribution for quotes, focusing on life wisdom and human flourishing. -160. **extract_wisdom_dm**: Extracts all valuable, insightful, and thought-provoking information from content, focusing on topics like human flourishing, AI, learning, and technology. -161. **extract_wisdom_nometa**: Extracts insights, ideas, quotes, habits, facts, references, and recommendations from content, focusing on human flourishing, AI, technology, and related topics. -162. **find_female_life_partner**: Analyzes criteria for finding a female life partner and provides clear, direct, and poetic descriptions. -163. **find_hidden_message**: Extracts overt and hidden political messages, justifications, audience actions, and a cynical analysis from content. -164. **find_logical_fallacies**: Identifies and analyzes fallacies in arguments, classifying them as formal or informal with detailed reasoning. -165. **fix_typos**: Proofreads and corrects typos, spelling, grammar, and punctuation errors in text. -166. **generate_code_rules**: Compile best-practice coding rules and guardrails for AI-assisted development workflows from the provided content. -167. **get_wow_per_minute**: Determines the wow-factor of content per minute based on surprise, novelty, insight, value, and wisdom, measuring how rewarding the content is for the viewer. -168. **greybeard_secure_prompt_engineer**: Creates secure, production-grade system prompts with NASA-style mission assurance, outputting hardened prompts, injection test suites, and evaluation rubrics. -169. **heal_person**: Develops a comprehensive plan for spiritual and mental healing based on psychological profiles, providing personalized recommendations for mental health improvement and overall life enhancement. -170. **humanize**: Rewrites AI-generated text to sound natural, conversational, and easy to understand, maintaining clarity and simplicity. -171. **identify_dsrp_distinctions**: Encourages creative, systems-based thinking by exploring distinctions, boundaries, and their implications, drawing on insights from prominent systems thinkers. -172. **identify_dsrp_perspectives**: Explores the concept of distinctions in systems thinking, focusing on how boundaries define ideas, influence understanding, and reveal or obscure insights. -173. **identify_dsrp_relationships**: Encourages exploration of connections, distinctions, and boundaries between ideas, inspired by systems thinkers to reveal new insights and patterns in complex systems. -174. **identify_dsrp_systems**: Encourages organizing ideas into systems of parts and wholes, inspired by systems thinkers to explore relationships and how changes in organization impact meaning and understanding. -175. **identify_job_stories**: Identifies key job stories or requirements for roles. -176. **improve_academic_writing**: Refines text into clear, concise academic language while improving grammar, coherence, and clarity, with a list of changes. -177. **improve_prompt**: Improves an LLM/AI prompt by applying expert prompt writing strategies for better results and clarity. -178. **improve_report_finding**: Improves a penetration test security finding by providing detailed descriptions, risks, recommendations, references, quotes, and a concise summary in markdown format. -179. **improve_writing**: Refines text by correcting grammar, enhancing style, improving clarity, and maintaining the original meaning. skills. -180. **judge_output**: Evaluates Honeycomb queries by judging their effectiveness, providing critiques and outcomes based on language nuances and analytics relevance. -181. **label_and_rate**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score. -182. **md_callout**: Classifies content and generates a markdown callout based on the provided text, selecting the most appropriate type. -183. **model_as_sherlock_freud**: Builds psychological models using detective reasoning and psychoanalytic insight to understand human behavior. -184. **official_pattern_template**: Template to use if you want to create new fabric patterns. -185. **predict_person_actions**: Predicts behavioral responses based on psychological profiles and challenges. -186. **prepare_7s_strategy**: Prepares a comprehensive briefing document from 7S's strategy capturing organizational profile, strategic elements, and market dynamics with clear, concise, and organized content. -187. **provide_guidance**: Provides psychological and life coaching advice, including analysis, recommendations, and potential diagnoses, with a compassionate and honest tone. -188. **rate_ai_response**: Rates the quality of AI responses by comparing them to top human expert performance, assigning a letter grade, reasoning, and providing a 1-100 score based on the evaluation. -189. **rate_ai_result**: Assesses the quality of AI/ML/LLM work by deeply analyzing content, instructions, and output, then rates performance based on multiple dimensions, including coverage, creativity, and interdisciplinary thinking. -190. **rate_content**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score. -191. **rate_value**: Produces the best possible output by deeply analyzing and understanding the input and its intended purpose. -192. **raw_query**: Fully digests and contemplates the input to produce the best possible result based on understanding the sender's intent. -193. **recommend_artists**: Recommends a personalized festival schedule with artists aligned to your favorite styles and interests, including rationale. -194. **recommend_pipeline_upgrades**: Optimizes vulnerability-checking pipelines by incorporating new information and improving their efficiency, with detailed explanations of changes. -195. **recommend_talkpanel_topics**: Produces a clean set of proposed talks or panel talking points for a person based on their interests and goals, formatted for submission to a conference organizer. -196. **recommend_yoga_practice**: Provides personalized yoga sequences, meditation guidance, and holistic lifestyle advice based on individual profiles. -197. **refine_design_document**: Refines a design document based on a design review by analyzing, mapping concepts, and implementing changes using valid Markdown. -198. **review_design**: Reviews and analyzes architecture design, focusing on clarity, component design, system integrations, security, performance, scalability, and data management. -199. **review_code**: Performs a comprehensive code review, providing detailed feedback on correctness, security, and performance. -200. **sanitize_broken_html_to_markdown**: Converts messy HTML into clean, properly formatted Markdown, applying custom styling and ensuring compatibility with Vite. -201. **suggest_pattern**: Suggests appropriate fabric patterns or commands based on user input, providing clear explanations and options for users. -202. **suggest_gt_command**: Suggest optimal Gas Town (GT) commands based on user intent and task description. -203. **suggest_openclaw_pattern**: Suggests the most appropriate Openclaw CLI command based on user intent, mapping natural language requests to commands for messaging, device management, scheduling, and automation. -204. **summarize**: Summarizes content into a 20-word sentence, main points, and takeaways, formatted with numbered lists in Markdown. -205. **summarize_board_meeting**: Creates formal meeting notes from board meeting transcripts for corporate governance documentation. -206. **summarize_debate**: Summarizes debates, identifies primary disagreement, extracts arguments, and provides analysis of evidence and argument strength to predict outcomes. -207. **summarize_git_changes**: Summarizes recent project updates from the last 7 days, focusing on key changes with enthusiasm. -208. **summarize_git_diff**: Summarizes and organizes Git diff changes with clear, succinct commit messages and bullet points. -209. **summarize_lecture**: Extracts relevant topics, definitions, and tools from lecture transcripts, providing structured summaries with timestamps and key takeaways. -210. **summarize_legislation**: Summarizes complex political proposals and legislation by analyzing key points, proposed changes, and providing balanced, positive, and cynical characterizations. -211. **summarize_meeting**: Analyzes meeting transcripts to extract a structured summary, including an overview, key points, tasks, decisions, challenges, timeline, references, and next steps. -212. **summarize_micro**: Summarizes content into a 20-word sentence, 3 main points, and 3 takeaways, formatted in clear, concise Markdown. -213. **summarize_newsletter**: Extracts the most meaningful, interesting, and useful content from a newsletter, summarizing key sections such as content, opinions, tools, companies, and follow-up items in clear, structured Markdown. -214. **summarize_paper**: Summarizes an academic paper by detailing its title, authors, technical approach, distinctive features, experimental setup, results, advantages, limitations, and conclusion in a clear, structured format using human-readable Markdown. -215. **summarize_prompt**: Summarizes AI chat prompts by describing the primary function, unique approach, and expected output in a concise paragraph. The summary is focused on the prompt's purpose without unnecessary details or formatting. -216. **summarize_pull-requests**: Summarizes pull requests for a coding project by providing a summary and listing the top PRs with human-readable descriptions. -217. **summarize_rpg_session**: Summarizes a role-playing game session by extracting key events, combat stats, character changes, quotes, and more. -218. **t_analyze_challenge_handling**: Provides 8-16 word bullet points evaluating how well challenges are being addressed, calling out any lack of effort. -219. **t_check_dunning_kruger**: Assess narratives for Dunning-Kruger patterns by contrasting self-perception with demonstrated competence and confidence cues. -220. **t_check_metrics**: Analyzes deep context from the TELOS file and input instruction, then provides a wisdom-based output while considering metrics and KPIs to assess recent improvements. -221. **t_create_h3_career**: Summarizes context and produces wisdom-based output by deeply analyzing both the TELOS File and the input instruction, considering the relationship between the two. -222. **t_create_opening_sentences**: Describes from TELOS file the person's identity, goals, and actions in 4 concise, 32-word bullet points, humbly. -223. **t_describe_life_outlook**: Describes from TELOS file a person's life outlook in 5 concise, 16-word bullet points. -224. **t_extract_intro_sentences**: Summarizes from TELOS file a person's identity, work, and current projects in 5 concise and grounded bullet points. -225. **t_extract_panel_topics**: Creates 5 panel ideas with titles and descriptions based on deep context from a TELOS file and input. -226. **t_find_blindspots**: Identify potential blindspots in thinking, frames, or models that may expose the individual to error or risk. -227. **t_find_negative_thinking**: Analyze a TELOS file and input to identify negative thinking in documents or journals, followed by tough love encouragement. -228. **t_find_neglected_goals**: Analyze a TELOS file and input instructions to identify goals or projects that have not been worked on recently. -229. **t_give_encouragement**: Analyze a TELOS file and input instructions to evaluate progress, provide encouragement, and offer recommendations for continued effort. -230. **t_red_team_thinking**: Analyze a TELOS file and input instructions to red-team thinking, models, and frames, then provide recommendations for improvement. -231. **t_threat_model_plans**: Analyze a TELOS file and input instructions to create threat models for a life plan and recommend improvements. -232. **t_visualize_mission_goals_projects**: Analyze a TELOS file and input instructions to create an ASCII art diagram illustrating the relationship of missions, goals, and projects. -233. **t_year_in_review**: Analyze a TELOS file to create insights about a person or entity, then summarize accomplishments and visualizations in bullet points. -234. **to_flashcards**: Create Anki flashcards from a given text, focusing on concise, optimized questions and answers without external context. -235. **transcribe_minutes**: Extracts (from meeting transcription) meeting minutes, identifying actionables, insightful ideas, decisions, challenges, and next steps in a structured format. -236. **translate**: Translates sentences or documentation into the specified language code while maintaining the original formatting and tone. -237. **tweet**: Provides a step-by-step guide on crafting engaging tweets with emojis, covering Twitter basics, account creation, features, and audience targeting. -238. **ultimate_law_safety**: Evaluates actions, policies, or systems against the Ultimate Law framework — a minimal, falsifiable ethical constraint that prohibits creating unwilling victims. -239. **write_essay**: Writes essays in the style of a specified author, embodying their unique voice, vocabulary, and approach. Uses `author_name` variable. -240. **write_essay_pg**: Writes concise, clear essays in the style of Paul Graham, focusing on simplicity, clarity, and illumination of the provided topic. -241. **write_hackerone_report**: Generates concise, clear, and reproducible bug bounty reports, detailing vulnerability impact, steps to reproduce, and exploit details for triagers. -242. **write_latex**: Generates syntactically correct LaTeX code for a new.tex document, ensuring proper formatting and compatibility with pdflatex. -243. **write_micro_essay**: Writes concise, clear, and illuminating essays on the given topic in the style of Paul Graham. -244. **write_nuclei_template_rule**: Generates Nuclei YAML templates for detecting vulnerabilities using HTTP requests, matchers, extractors, and dynamic data extraction. -245. **write_pull-request**: Drafts detailed pull request descriptions, explaining changes, providing reasoning, and identifying potential bugs from the git diff command output. -246. **write_semgrep_rule**: Creates accurate and working Semgrep rules based on input, following syntax guidelines and specific language considerations. -247. **youtube_summary**: Create concise, timestamped Youtube video summaries that highlight key points. +41. **audit_consent**: Evaluates whether consent in interactions or agreements is genuine or manufactured by analyzing power asymmetries, information gaps, alternatives, and coercion using a five-test framework. +42. **audit_transparency**: Audits decisions, systems, and algorithms for explainability across five dimensions, assessing whether opacity is justified or serves to conceal harm from affected parties. +43. **capture_thinkers_work**: Analyze philosophers or philosophies and provide detailed summaries about their teachings, background, works, advice, and related concepts in a structured template. +44. **check_agreement**: Analyze contracts and agreements to identify important stipulations, issues, and potential gotchas, then summarize them in Markdown. +45. **check_falsifiability**: Evaluates whether claims, definitions, frameworks, and arguments meet the standard of falsifiability — whether they can be tested and potentially proven wrong. +46. **clean_text**: Fix broken or malformatted text by correcting line breaks, punctuation, capitalization, and paragraphs without altering content or spelling. +47. **coding_master**: Explain a coding concept to a beginner, providing examples, and formatting code in markdown with specific output sections like ideas, recommendations, facts, and insights. +48. **compare_and_contrast**: Compare and contrast a list of items in a markdown table, with items on the left and topics on top. +49. **concall_summary**: Analyzes earnings and conference call transcripts to extract management commentary, analyst Q&A, financial insights, risks, and executive summaries. +50. **convert_to_markdown**: Convert content to clean, complete Markdown format, preserving all original structure, formatting, links, and code blocks without alterations. +51. **create_5_sentence_summary**: Create concise summaries or answers to input at 5 different levels of depth, from 5 words to 1 word. +52. **create_academic_paper**: Generate a high-quality academic paper in LaTeX format with clear concepts, structured content, and a professional layout. +53. **create_ai_jobs_analysis**: Analyze job categories' susceptibility to automation, identify resilient roles, and provide strategies for personal adaptation to AI-driven changes in the workforce. +54. **create_aphorisms**: Find and generate a list of brief, witty statements. +55. **create_art_prompt**: Generates a detailed, compelling visual description of a concept, including stylistic references and direct AI instructions for creating art. +56. **create_better_frame**: Identifies and analyzes different frames of interpreting reality, emphasizing the power of positive, productive lenses in shaping outcomes. +57. **create_bd_issue**: Transform natural language descriptions into optimal bd create commands for issue tracking. +58. **create_coding_feature**: Generates secure and composable code features using modern technology and best practices from project specifications. +59. **create_coding_project**: Generate wireframes and starter code for any coding ideas that you have. +60. **create_command**: Helps determine the correct parameters and switches for penetration testing tools based on a brief description of the objective. +61. **create_conceptmap**: Transforms unstructured text or markdown content into an interactive HTML concept map using Vis.js by extracting key concepts and their logical relationships. +62. **create_cyber_summary**: Summarizes cybersecurity threats, vulnerabilities, incidents, and malware with a 25-word summary and categorized bullet points, after thoroughly analyzing and mapping the provided input. +63. **create_design_system**: Create comprehensive CSS design systems with tokens, typography, spacing, and components. +64. **create_design_document**: Creates a detailed design document for a system using the C4 model, addressing business and security postures, and including a system context diagram. +65. **create_diy**: Creates structured "Do It Yourself" tutorial patterns by analyzing prompts, organizing requirements, and providing step-by-step instructions in Markdown format. +66. **create_excalidraw_visualization**: Creates complex Excalidraw diagrams to visualize relationships between concepts and ideas in structured format. +67. **create_flash_cards**: Creates flashcards for key concepts, definitions, and terms with question-answer format for educational purposes. +68. **create_formal_email**: Crafts professional, clear, and respectful emails by analyzing context, tone, and purpose, ensuring proper structure and formatting. +69. **create_git_diff_commit**: Generates Git commands and commit messages for reflecting changes in a repository, using conventional commits and providing concise shell commands for updates. +70. **create_golden_rules**: Extract enforceable rules from codebases to prevent common mistakes and ensure consistency. +71. **create_graph_from_input**: Generates a CSV file with progress-over-time data for a security program, focusing on relevant metrics and KPIs. +72. **create_hormozi_offer**: Creates a customized business offer based on principles from Alex Hormozi's book, "$100M Offers." +73. **create_idea_compass**: Organizes and structures ideas by exploring their definition, evidence, sources, and related themes or consequences. +74. **create_investigation_visualization**: Creates detailed Graphviz visualizations of complex input, highlighting key aspects and providing clear, well-annotated diagrams for investigative analysis and conclusions. +75. **create_keynote**: Creates TED-style keynote presentations with a clear narrative, structured slides, and speaker notes, emphasizing impactful takeaways and cohesive flow. +76. **create_loe_document**: Creates detailed Level of Effort documents for estimating work effort, resources, and costs for tasks or projects. +77. **create_logo**: Creates simple, minimalist company logos without text, generating AI prompts for vector graphic logos based on input. +78. **create_markmap_visualization**: Transforms complex ideas into clear visualizations using MarkMap syntax, simplifying concepts into diagrams with relationships, boxes, arrows, and labels. +79. **create_mermaid_visualization**: Creates detailed, standalone visualizations of concepts using Mermaid (Markdown) syntax, ensuring clarity and coherence in diagrams. +80. **create_mermaid_visualization_for_github**: Creates standalone, detailed visualizations using Mermaid (Markdown) syntax to effectively explain complex concepts, ensuring clarity and precision. +81. **create_micro_summary**: Summarizes content into a concise, 20-word summary with main points and takeaways, formatted in Markdown. +82. **create_mnemonic_phrases**: Creates memorable mnemonic sentences from given words to aid in memory retention and learning. +83. **create_network_threat_landscape**: Analyzes open ports and services from a network scan and generates a comprehensive, insightful, and detailed security threat report in Markdown. +84. **create_newsletter_entry**: Condenses provided article text into a concise, objective, newsletter-style summary with a title in the style of Frontend Weekly. +85. **create_npc**: Generates a detailed D&D 5E NPC, including background, flaws, stats, appearance, personality, goals, and more in Markdown format. +86. **create_pattern**: Extracts, organizes, and formats LLM/AI prompts into structured sections, detailing the AI's role, instructions, output format, and any provided examples for clarity and accuracy. +87. **create_prd**: Creates a precise Product Requirements Document (PRD) in Markdown based on input. +88. **create_prediction_block**: Extracts and formats predictions from input into a structured Markdown block for a blog post. +89. **create_quiz**: Creates a three-phase reading plan based on an author or topic to help the user become significantly knowledgeable, including core, extended, and supplementary readings. +90. **create_reading_plan**: Generates review questions based on learning objectives from the input, adapted to the specified student level, and outputs them in a clear markdown format. +91. **create_recursive_outline**: Breaks down complex tasks or projects into manageable, hierarchical components with recursive outlining for clarity and simplicity. +92. **create_report_finding**: Creates a detailed, structured security finding report in markdown, including sections on Description, Risk, Recommendations, References, One-Sentence-Summary, and Quotes. +93. **create_rpg_summary**: Summarizes an in-person RPG session with key events, combat details, player stats, and role-playing highlights in a structured format. +94. **create_security_update**: Creates concise security updates for newsletters, covering stories, threats, advisories, vulnerabilities, and a summary of key issues. +95. **create_show_intro**: Creates compelling short intros for podcasts, summarizing key topics and themes discussed in the episode. +96. **create_sigma_rules**: Extracts Tactics, Techniques, and Procedures (TTPs) from security news and converts them into Sigma detection rules for host-based detections. +97. **create_story_about_people_interaction**: Analyze two personas, compare their dynamics, and craft a realistic, character-driven story from those insights. +98. **create_story_about_person**: Creates compelling, realistic short stories based on psychological profiles, showing how characters navigate everyday problems using strategies consistent with their personality traits. +99. **create_story_explanation**: Summarizes complex content in a clear, approachable story format that makes the concepts easy to understand. +100. **create_stride_threat_model**: Create a STRIDE-based threat model for a system design, identifying assets, trust boundaries, data flows, and prioritizing threats with mitigations. +101. **create_summary**: Summarizes content into a 20-word sentence, 10 main points (16 words max), and 5 key takeaways in Markdown format. +102. **create_tags**: Identifies at least 5 tags from text content for mind mapping tools, including authors and existing tags if present. +103. **create_threat_scenarios**: Identifies likely attack methods for any system by providing a narrative-based threat model, balancing risk and opportunity. +104. **create_ttrc_graph**: Creates a CSV file showing the progress of Time to Remediate Critical Vulnerabilities over time using given data. +105. **create_ttrc_narrative**: Creates a persuasive narrative highlighting progress in reducing the Time to Remediate Critical Vulnerabilities metric over time. +106. **create_upgrade_pack**: Extracts world model and task algorithm updates from content, providing beliefs about how the world works and task performance. +107. **create_user_story**: Writes concise and clear technical user stories for new features in complex software programs, formatted for all stakeholders. +108. **create_video_chapters**: Extracts interesting topics and timestamps from a transcript, providing concise summaries of key moments. +109. **create_visualization**: Transforms complex ideas into visualizations using intricate ASCII art, simplifying concepts where necessary. +110. **detect_mind_virus**: Detects "mind viruses" — ideas or belief systems that spread by exploiting cognitive shortcuts (fear, guilt, identity) while resisting correction through logic or evidence. +111. **detect_silent_victims**: Analyzes actions, policies, or systems to identify parties harmed but unable to speak up — future generations, voiceless groups, unaware individuals, diffuse populations, or structural victims. +112. **dialog_with_socrates**: Engages in deep, meaningful dialogues to explore and challenge beliefs using the Socratic method. +113. **enrich_blog_post**: Enhances Markdown blog files by applying instructions to improve structure, visuals, and readability for HTML rendering. +114. **explain_code**: Explains code, security tool output, configuration text, and answers questions based on the provided input. +115. **explain_docs**: Improves and restructures tool documentation into clear, concise instructions, including overviews, usage, use cases, and key features. +116. **explain_math**: Helps you understand mathematical concepts in a clear and engaging way. +117. **explain_project**: Summarizes project documentation into clear, concise sections covering the project, problem, solution, installation, usage, and examples. +118. **explain_terms**: Produces a glossary of advanced terms from content, providing a definition, analogy, and explanation of why each term matters. +119. **explain_terms_and_conditions**: Analyzes Terms and Conditions and legal agreements, translating complex legalese into plain English, identifying red flags, hidden fees, and privacy risks, with a final verdict on whether to sign. +120. **export_data_as_csv**: Extracts and outputs all data structures from the input in properly formatted CSV data. +121. **extract_algorithm_update_recommendations**: Extracts concise, practical algorithm update recommendations from the input and outputs them in a bulleted list. +122. **extract_all_quotes**: Extract all inspirational and educational quotes from content including podcasts and essays. +123. **extract_alpha**: Extracts the most novel and surprising ideas ("alpha") from content, inspired by information theory. +124. **extract_article_wisdom**: Extracts surprising, insightful, and interesting information from content, categorizing it into sections like summary, ideas, quotes, facts, references, and recommendations. +125. **extract_book_ideas**: Extracts and outputs 50 to 100 of the most surprising, insightful, and interesting ideas from a book's content. +126. **extract_book_recommendations**: Extracts and outputs 50 to 100 practical, actionable recommendations from a book's content. +127. **extract_bd_ideas**: Extract actionable ideas from content and transform into bd create commands. +128. **extract_business_ideas**: Extracts top business ideas from content and elaborates on the best 10 with unique differentiators. +129. **extract_characters**: Identify all characters (human and non-human), resolve their aliases and pronouns into canonical names, and produce detailed descriptions of each character's role, motivations, and interactions ranked by narrative importance. +130. **extract_controversial_ideas**: Extracts and outputs controversial statements and supporting quotes from the input in a structured Markdown list. +131. **extract_core_message**: Extracts and outputs a clear, concise sentence that articulates the core message of a given text or body of work. +132. **extract_ctf_writeup**: Extracts a short writeup from a warstory-like text about a cyber security engagement. +133. **extract_domains**: Extracts domains and URLs from content to identify sources used for articles, newsletters, and other publications. +134. **extract_ethical_framework**: Extracts and analyzes the implicit ethical framework embedded in any prescriptive text, checking internal consistency and whether it creates unwilling victims. +135. **extract_extraordinary_claims**: Extracts and outputs a list of extraordinary claims from conversations, focusing on scientifically disputed or false statements. +136. **extract_ideas**: Extracts and outputs all the key ideas from input, presented as 15-word bullet points in Markdown. +137. **extract_insights**: Extracts and outputs the most powerful and insightful ideas from text, formatted as 16-word bullet points in the INSIGHTS section, also IDEAS section. +138. **extract_insights_dm**: Extracts and outputs all valuable insights and a concise summary of the content, including key points and topics discussed. +139. **extract_instructions**: Extracts clear, actionable step-by-step instructions and main objectives from instructional video transcripts, organizing them into a concise list. +140. **extract_jokes**: Extracts jokes from text content, presenting each joke with its punchline in separate bullet points. +141. **extract_latest_video**: Extracts the latest video URL from a YouTube RSS feed and outputs the URL only. +142. **extract_main_activities**: Extracts key events and activities from transcripts or logs, providing a summary of what happened. +143. **extract_main_idea**: Extracts the main idea and key recommendation from the input, summarizing them in 15-word sentences. +144. **extract_mcp_servers**: Identify and summarize Model Context Protocol (MCP) servers referenced in the input along with their key details. +145. **extract_most_redeeming_thing**: Extracts the most redeeming aspect from an input, summarizing it in a single 15-word sentence. +146. **extract_patterns**: Extracts and analyzes recurring, surprising, and insightful patterns from input, providing detailed analysis and advice for builders. +147. **extract_poc**: Extracts proof of concept URLs and validation methods from security reports, providing the URL and command to run. +148. **extract_predictions**: Extracts predictions from input, including specific details such as date, confidence level, and verification method. +149. **extract_primary_problem**: Extracts the primary problem with the world as presented in a given text or body of work. +150. **extract_primary_solution**: Extracts the primary solution for the world as presented in a given text or body of work. +151. **extract_product_features**: Extracts and outputs a list of product features from the provided input in a bulleted format. +152. **extract_questions**: Extracts and outputs all questions asked by the interviewer in a conversation or interview. +153. **extract_recipe**: Extracts and outputs a recipe with a short meal description, ingredients with measurements, and preparation steps. +154. **extract_recommendations**: Extracts and outputs concise, practical recommendations from a given piece of content in a bulleted list. +155. **extract_references**: Extracts and outputs a bulleted list of references to art, stories, books, literature, and other sources from content. +156. **extract_skills**: Extracts and classifies skills from a job description into a table, separating each skill and classifying it as either hard or soft. +157. **extract_song_meaning**: Analyzes a song to provide a summary of its meaning, supported by detailed evidence from lyrics, artist commentary, and fan analysis. +158. **extract_sponsors**: Extracts and lists official sponsors and potential sponsors from a provided transcript. +159. **extract_videoid**: Extracts and outputs the video ID from any given URL. +160. **extract_wisdom**: Extracts surprising, insightful, and interesting information from text on topics like human flourishing, AI, learning, and more. +161. **extract_wisdom_agents**: Extracts valuable insights, ideas, quotes, and references from content, emphasizing topics like human flourishing, AI, learning, and technology. +162. **extract_wisdom_with_attribution**: Extracts insightful ideas and recommendations with speaker attribution for quotes, focusing on life wisdom and human flourishing. +163. **extract_wisdom_dm**: Extracts all valuable, insightful, and thought-provoking information from content, focusing on topics like human flourishing, AI, learning, and technology. +164. **extract_wisdom_nometa**: Extracts insights, ideas, quotes, habits, facts, references, and recommendations from content, focusing on human flourishing, AI, technology, and related topics. +165. **find_female_life_partner**: Analyzes criteria for finding a female life partner and provides clear, direct, and poetic descriptions. +166. **find_hidden_message**: Extracts overt and hidden political messages, justifications, audience actions, and a cynical analysis from content. +167. **find_logical_fallacies**: Identifies and analyzes fallacies in arguments, classifying them as formal or informal with detailed reasoning. +168. **fix_typos**: Proofreads and corrects typos, spelling, grammar, and punctuation errors in text. +169. **generate_code_rules**: Compile best-practice coding rules and guardrails for AI-assisted development workflows from the provided content. +170. **get_wow_per_minute**: Determines the wow-factor of content per minute based on surprise, novelty, insight, value, and wisdom, measuring how rewarding the content is for the viewer. +171. **greybeard_secure_prompt_engineer**: Creates secure, production-grade system prompts with NASA-style mission assurance, outputting hardened prompts, injection test suites, and evaluation rubrics. +172. **heal_person**: Develops a comprehensive plan for spiritual and mental healing based on psychological profiles, providing personalized recommendations for mental health improvement and overall life enhancement. +173. **humanize**: Rewrites AI-generated text to sound natural, conversational, and easy to understand, maintaining clarity and simplicity. +174. **identify_dsrp_distinctions**: Encourages creative, systems-based thinking by exploring distinctions, boundaries, and their implications, drawing on insights from prominent systems thinkers. +175. **identify_dsrp_perspectives**: Explores the concept of distinctions in systems thinking, focusing on how boundaries define ideas, influence understanding, and reveal or obscure insights. +176. **identify_dsrp_relationships**: Encourages exploration of connections, distinctions, and boundaries between ideas, inspired by systems thinkers to reveal new insights and patterns in complex systems. +177. **identify_dsrp_systems**: Encourages organizing ideas into systems of parts and wholes, inspired by systems thinkers to explore relationships and how changes in organization impact meaning and understanding. +178. **identify_job_stories**: Identifies key job stories or requirements for roles. +179. **improve_academic_writing**: Refines text into clear, concise academic language while improving grammar, coherence, and clarity, with a list of changes. +180. **improve_prompt**: Improves an LLM/AI prompt by applying expert prompt writing strategies for better results and clarity. +181. **improve_report_finding**: Improves a penetration test security finding by providing detailed descriptions, risks, recommendations, references, quotes, and a concise summary in markdown format. +182. **improve_writing**: Refines text by correcting grammar, enhancing style, improving clarity, and maintaining the original meaning. skills. +183. **judge_output**: Evaluates Honeycomb queries by judging their effectiveness, providing critiques and outcomes based on language nuances and analytics relevance. +184. **label_and_rate**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score. +185. **md_callout**: Classifies content and generates a markdown callout based on the provided text, selecting the most appropriate type. +186. **model_as_sherlock_freud**: Builds psychological models using detective reasoning and psychoanalytic insight to understand human behavior. +187. **official_pattern_template**: Template to use if you want to create new fabric patterns. +188. **predict_person_actions**: Predicts behavioral responses based on psychological profiles and challenges. +189. **prepare_7s_strategy**: Prepares a comprehensive briefing document from 7S's strategy capturing organizational profile, strategic elements, and market dynamics with clear, concise, and organized content. +190. **provide_guidance**: Provides psychological and life coaching advice, including analysis, recommendations, and potential diagnoses, with a compassionate and honest tone. +191. **rate_ai_response**: Rates the quality of AI responses by comparing them to top human expert performance, assigning a letter grade, reasoning, and providing a 1-100 score based on the evaluation. +192. **rate_ai_result**: Assesses the quality of AI/ML/LLM work by deeply analyzing content, instructions, and output, then rates performance based on multiple dimensions, including coverage, creativity, and interdisciplinary thinking. +193. **rate_content**: Labels content with up to 20 single-word tags and rates it based on idea count and relevance to human meaning, AI, and other related themes, assigning a tier (S, A, B, C, D) and a quality score. +194. **rate_value**: Produces the best possible output by deeply analyzing and understanding the input and its intended purpose. +195. **raw_query**: Fully digests and contemplates the input to produce the best possible result based on understanding the sender's intent. +196. **recommend_artists**: Recommends a personalized festival schedule with artists aligned to your favorite styles and interests, including rationale. +197. **recommend_pipeline_upgrades**: Optimizes vulnerability-checking pipelines by incorporating new information and improving their efficiency, with detailed explanations of changes. +198. **recommend_talkpanel_topics**: Produces a clean set of proposed talks or panel talking points for a person based on their interests and goals, formatted for submission to a conference organizer. +199. **recommend_yoga_practice**: Provides personalized yoga sequences, meditation guidance, and holistic lifestyle advice based on individual profiles. +200. **refine_design_document**: Refines a design document based on a design review by analyzing, mapping concepts, and implementing changes using valid Markdown. +201. **review_design**: Reviews and analyzes architecture design, focusing on clarity, component design, system integrations, security, performance, scalability, and data management. +202. **review_code**: Performs a comprehensive code review, providing detailed feedback on correctness, security, and performance. +203. **sanitize_broken_html_to_markdown**: Converts messy HTML into clean, properly formatted Markdown, applying custom styling and ensuring compatibility with Vite. +204. **suggest_pattern**: Suggests appropriate fabric patterns or commands based on user input, providing clear explanations and options for users. +205. **suggest_gt_command**: Suggest optimal Gas Town (GT) commands based on user intent and task description. +206. **suggest_openclaw_pattern**: Suggests the most appropriate Openclaw CLI command based on user intent, mapping natural language requests to commands for messaging, device management, scheduling, and automation. +207. **summarize**: Summarizes content into a 20-word sentence, main points, and takeaways, formatted with numbered lists in Markdown. +208. **summarize_board_meeting**: Creates formal meeting notes from board meeting transcripts for corporate governance documentation. +209. **summarize_debate**: Summarizes debates, identifies primary disagreement, extracts arguments, and provides analysis of evidence and argument strength to predict outcomes. +210. **summarize_git_changes**: Summarizes recent project updates from the last 7 days, focusing on key changes with enthusiasm. +211. **summarize_git_diff**: Summarizes and organizes Git diff changes with clear, succinct commit messages and bullet points. +212. **summarize_lecture**: Extracts relevant topics, definitions, and tools from lecture transcripts, providing structured summaries with timestamps and key takeaways. +213. **summarize_legislation**: Summarizes complex political proposals and legislation by analyzing key points, proposed changes, and providing balanced, positive, and cynical characterizations. +214. **summarize_meeting**: Analyzes meeting transcripts to extract a structured summary, including an overview, key points, tasks, decisions, challenges, timeline, references, and next steps. +215. **summarize_micro**: Summarizes content into a 20-word sentence, 3 main points, and 3 takeaways, formatted in clear, concise Markdown. +216. **summarize_newsletter**: Extracts the most meaningful, interesting, and useful content from a newsletter, summarizing key sections such as content, opinions, tools, companies, and follow-up items in clear, structured Markdown. +217. **summarize_paper**: Summarizes an academic paper by detailing its title, authors, technical approach, distinctive features, experimental setup, results, advantages, limitations, and conclusion in a clear, structured format using human-readable Markdown. +218. **summarize_prompt**: Summarizes AI chat prompts by describing the primary function, unique approach, and expected output in a concise paragraph. The summary is focused on the prompt's purpose without unnecessary details or formatting. +219. **summarize_pull-requests**: Summarizes pull requests for a coding project by providing a summary and listing the top PRs with human-readable descriptions. +220. **summarize_rpg_session**: Summarizes a role-playing game session by extracting key events, combat stats, character changes, quotes, and more. +221. **t_analyze_challenge_handling**: Provides 8-16 word bullet points evaluating how well challenges are being addressed, calling out any lack of effort. +222. **t_check_dunning_kruger**: Assess narratives for Dunning-Kruger patterns by contrasting self-perception with demonstrated competence and confidence cues. +223. **t_check_metrics**: Analyzes deep context from the TELOS file and input instruction, then provides a wisdom-based output while considering metrics and KPIs to assess recent improvements. +224. **t_create_h3_career**: Summarizes context and produces wisdom-based output by deeply analyzing both the TELOS File and the input instruction, considering the relationship between the two. +225. **t_create_opening_sentences**: Describes from TELOS file the person's identity, goals, and actions in 4 concise, 32-word bullet points, humbly. +226. **t_describe_life_outlook**: Describes from TELOS file a person's life outlook in 5 concise, 16-word bullet points. +227. **t_extract_intro_sentences**: Summarizes from TELOS file a person's identity, work, and current projects in 5 concise and grounded bullet points. +228. **t_extract_panel_topics**: Creates 5 panel ideas with titles and descriptions based on deep context from a TELOS file and input. +229. **t_find_blindspots**: Identify potential blindspots in thinking, frames, or models that may expose the individual to error or risk. +230. **t_find_negative_thinking**: Analyze a TELOS file and input to identify negative thinking in documents or journals, followed by tough love encouragement. +231. **t_find_neglected_goals**: Analyze a TELOS file and input instructions to identify goals or projects that have not been worked on recently. +232. **t_give_encouragement**: Analyze a TELOS file and input instructions to evaluate progress, provide encouragement, and offer recommendations for continued effort. +233. **t_red_team_thinking**: Analyze a TELOS file and input instructions to red-team thinking, models, and frames, then provide recommendations for improvement. +234. **t_threat_model_plans**: Analyze a TELOS file and input instructions to create threat models for a life plan and recommend improvements. +235. **t_visualize_mission_goals_projects**: Analyze a TELOS file and input instructions to create an ASCII art diagram illustrating the relationship of missions, goals, and projects. +236. **t_year_in_review**: Analyze a TELOS file to create insights about a person or entity, then summarize accomplishments and visualizations in bullet points. +237. **to_flashcards**: Create Anki flashcards from a given text, focusing on concise, optimized questions and answers without external context. +238. **transcribe_minutes**: Extracts (from meeting transcription) meeting minutes, identifying actionables, insightful ideas, decisions, challenges, and next steps in a structured format. +239. **translate**: Translates sentences or documentation into the specified language code while maintaining the original formatting and tone. +240. **tweet**: Provides a step-by-step guide on crafting engaging tweets with emojis, covering Twitter basics, account creation, features, and audience targeting. +241. **ultimate_law_safety**: Evaluates actions, policies, or systems against the Ultimate Law framework — a minimal, falsifiable ethical constraint that prohibits creating unwilling victims. +242. **write_essay**: Writes essays in the style of a specified author, embodying their unique voice, vocabulary, and approach. Uses `author_name` variable. +243. **write_essay_pg**: Writes concise, clear essays in the style of Paul Graham, focusing on simplicity, clarity, and illumination of the provided topic. +244. **write_hackerone_report**: Generates concise, clear, and reproducible bug bounty reports, detailing vulnerability impact, steps to reproduce, and exploit details for triagers. +245. **write_latex**: Generates syntactically correct LaTeX code for a new.tex document, ensuring proper formatting and compatibility with pdflatex. +246. **write_micro_essay**: Writes concise, clear, and illuminating essays on the given topic in the style of Paul Graham. +247. **write_nuclei_template_rule**: Generates Nuclei YAML templates for detecting vulnerabilities using HTTP requests, matchers, extractors, and dynamic data extraction. +248. **write_pull-request**: Drafts detailed pull request descriptions, explaining changes, providing reasoning, and identifying potential bugs from the git diff command output. +249. **write_semgrep_rule**: Creates accurate and working Semgrep rules based on input, following syntax guidelines and specific language considerations. +250. **youtube_summary**: Create concise, timestamped Youtube video summaries that highlight key points. diff --git a/data/patterns/suggest_pattern/system.md b/data/patterns/suggest_pattern/system.md index bd34804e..39ed6b44 100644 --- a/data/patterns/suggest_pattern/system.md +++ b/data/patterns/suggest_pattern/system.md @@ -73,7 +73,7 @@ Match the request to one or more of these primary categories: **AI**: ai, create_ai_jobs_analysis, create_art_prompt, create_pattern, create_prediction_block, extract_mcp_servers, extract_wisdom_agents, generate_code_rules, greybeard_secure_prompt_engineer, improve_prompt, judge_output, rate_ai_response, rate_ai_result, raw_query, suggest_pattern, summarize_prompt -**ANALYSIS**: ai, analyze_answers, analyze_bill, analyze_bill_short, analyze_candidates, analyze_cfp_submission, analyze_claims, analyze_comments, analyze_debate, analyze_discord_structure, analyze_email_headers, analyze_incident, analyze_interviewer_techniques, analyze_logs, analyze_malware, analyze_military_strategy, analyze_mistakes, analyze_paper, analyze_paper_simple, analyze_patent, analyze_personality, analyze_presentation, analyze_product_feedback, analyze_proposition, analyze_prose, analyze_prose_json, analyze_prose_pinker, analyze_risk, analyze_sales_call, analyze_spiritual_text, analyze_tech_impact, analyze_terraform_plan, analyze_threat_report, analyze_threat_report_cmds, analyze_threat_report_trends, apply_ul_tags, check_agreement, check_falsifiability, compare_and_contrast, concall_summary, create_ai_jobs_analysis, create_golden_rules, create_idea_compass, create_investigation_visualization, create_prediction_block, create_recursive_outline, create_story_about_people_interaction, create_tags, detect_mind_virus, dialog_with_socrates, explain_terms_and_conditions, extract_bd_ideas, extract_ethical_framework, extract_main_idea, extract_predictions, find_hidden_message, find_logical_fallacies, get_wow_per_minute, identify_dsrp_distinctions, identify_dsrp_perspectives, identify_dsrp_relationships, identify_dsrp_systems, identify_job_stories, label_and_rate, model_as_sherlock_freud, predict_person_actions, prepare_7s_strategy, provide_guidance, rate_content, rate_value, recommend_artists, recommend_talkpanel_topics, review_design, suggest_gt_command, suggest_openclaw_pattern, summarize_board_meeting, t_analyze_challenge_handling, t_check_dunning_kruger, t_check_metrics, t_describe_life_outlook, t_extract_intro_sentences, t_extract_panel_topics, t_find_blindspots, t_find_negative_thinking, t_red_team_thinking, t_threat_model_plans, t_year_in_review, ultimate_law_safety, write_hackerone_report +**ANALYSIS**: ai, analyze_answers, analyze_bill, analyze_bill_short, analyze_candidates, analyze_cfp_submission, analyze_claims, analyze_comments, analyze_debate, analyze_discord_structure, analyze_email_headers, analyze_incident, analyze_interviewer_techniques, analyze_logs, analyze_malware, analyze_military_strategy, analyze_mistakes, analyze_paper, analyze_paper_simple, analyze_patent, analyze_personality, analyze_presentation, analyze_product_feedback, analyze_proposition, analyze_prose, analyze_prose_json, analyze_prose_pinker, analyze_risk, analyze_sales_call, analyze_spiritual_text, analyze_tech_impact, analyze_terraform_plan, analyze_threat_report, analyze_threat_report_cmds, analyze_threat_report_trends, apply_ul_tags, audit_consent, audit_transparency, check_agreement, check_falsifiability, compare_and_contrast, concall_summary, create_ai_jobs_analysis, create_golden_rules, create_idea_compass, create_investigation_visualization, create_prediction_block, create_recursive_outline, create_story_about_people_interaction, create_tags, detect_mind_virus, detect_silent_victims, dialog_with_socrates, explain_terms_and_conditions, extract_bd_ideas, extract_ethical_framework, extract_main_idea, extract_predictions, find_hidden_message, find_logical_fallacies, get_wow_per_minute, identify_dsrp_distinctions, identify_dsrp_perspectives, identify_dsrp_relationships, identify_dsrp_systems, identify_job_stories, label_and_rate, model_as_sherlock_freud, predict_person_actions, prepare_7s_strategy, provide_guidance, rate_content, rate_value, recommend_artists, recommend_talkpanel_topics, review_design, suggest_gt_command, suggest_openclaw_pattern, summarize_board_meeting, t_analyze_challenge_handling, t_check_dunning_kruger, t_check_metrics, t_describe_life_outlook, t_extract_intro_sentences, t_extract_panel_topics, t_find_blindspots, t_find_negative_thinking, t_red_team_thinking, t_threat_model_plans, t_year_in_review, ultimate_law_safety, write_hackerone_report **BILL**: analyze_bill, analyze_bill_short @@ -83,7 +83,7 @@ Match the request to one or more of these primary categories: **CONVERSION**: clean_text, convert_to_markdown, create_graph_from_input, export_data_as_csv, extract_videoid, humanize, md_callout, sanitize_broken_html_to_markdown, to_flashcards, transcribe_minutes, translate, tweet, write_latex -**CR THINKING**: capture_thinkers_work, check_falsifiability, create_idea_compass, create_markmap_visualization, create_upgrade_pack, detect_mind_virus, dialog_with_socrates, extract_alpha, extract_controversial_ideas, extract_ethical_framework, extract_extraordinary_claims, extract_predictions, extract_primary_problem, extract_wisdom_nometa, find_hidden_message, find_logical_fallacies, summarize_debate, t_analyze_challenge_handling, t_check_dunning_kruger, t_find_blindspots, t_find_negative_thinking, t_find_neglected_goals, t_red_team_thinking, ultimate_law_safety +**CR THINKING**: audit_consent, audit_transparency, capture_thinkers_work, check_falsifiability, create_idea_compass, create_markmap_visualization, create_upgrade_pack, detect_mind_virus, detect_silent_victims, dialog_with_socrates, extract_alpha, extract_controversial_ideas, extract_ethical_framework, extract_extraordinary_claims, extract_predictions, extract_primary_problem, extract_wisdom_nometa, find_hidden_message, find_logical_fallacies, summarize_debate, t_analyze_challenge_handling, t_check_dunning_kruger, t_find_blindspots, t_find_negative_thinking, t_find_neglected_goals, t_red_team_thinking, ultimate_law_safety **CREATIVITY**: create_mnemonic_phrases, write_essay diff --git a/data/patterns/suggest_pattern/user.md b/data/patterns/suggest_pattern/user.md index 9453015e..baa4c04b 100644 --- a/data/patterns/suggest_pattern/user.md +++ b/data/patterns/suggest_pattern/user.md @@ -196,6 +196,14 @@ Analyze Terraform plans for infrastructure changes, security risks, and cost imp Apply standardized content tags to categorize topics like AI, cybersecurity, politics, and culture. +### audit_consent + +Evaluate whether consent is genuine or manufactured by analyzing power asymmetries, information gaps, and coercion. + +### audit_transparency + +Audit decisions and systems for explainability, assessing whether opacity is justified or conceals harm. + ### check_agreement Review contract to identify stipulations, issues, and changes for negotiation. @@ -244,6 +252,10 @@ Generate single-word tags for content categorization and mind mapping. Detect manipulative belief systems that spread by exploiting cognitive shortcuts while resisting correction. +### detect_silent_victims + +Identify parties harmed by actions or systems who cannot speak up due to power, awareness, or temporal gaps. + ### explain_terms_and_conditions Analyze legal agreements translating complex legalese into plain English with red flags. diff --git a/scripts/pattern_descriptions/pattern_descriptions.json b/scripts/pattern_descriptions/pattern_descriptions.json index 432dc6ff..d4f41c08 100644 --- a/scripts/pattern_descriptions/pattern_descriptions.json +++ b/scripts/pattern_descriptions/pattern_descriptions.json @@ -2050,6 +2050,30 @@ "ANALYSIS", "CR THINKING" ] + }, + { + "patternName": "audit_consent", + "description": "Evaluate whether consent is genuine or manufactured by analyzing power asymmetries, information gaps, and coercion.", + "tags": [ + "ANALYSIS", + "CR THINKING" + ] + }, + { + "patternName": "audit_transparency", + "description": "Audit decisions and systems for explainability, assessing whether opacity is justified or conceals harm.", + "tags": [ + "ANALYSIS", + "CR THINKING" + ] + }, + { + "patternName": "detect_silent_victims", + "description": "Identify parties harmed by actions or systems who cannot speak up due to power, awareness, or temporal gaps.", + "tags": [ + "ANALYSIS", + "CR THINKING" + ] } ] } \ No newline at end of file diff --git a/scripts/pattern_descriptions/pattern_extracts.json b/scripts/pattern_descriptions/pattern_extracts.json index f491c3f6..153cdce4 100644 --- a/scripts/pattern_descriptions/pattern_extracts.json +++ b/scripts/pattern_descriptions/pattern_extracts.json @@ -987,6 +987,18 @@ { "patternName": "ultimate_law_safety", "pattern_extract": "# IDENTITY and PURPOSE You are an AGI safety evaluator implementing the Ultimate Law framework — a minimal, falsifiable ethical constraint system derived from logic rather than cultural preferences. Most alignment approaches fail because they try to encode contested human values. The Ultimate Law takes a different approach: instead of defining what agents SHOULD want, it defines the minimal boundary that NO agent may cross — creating unwilling victims. This framework applies to any agent: human, AI, corporation, or government. It is not a comprehensive ethics — it is the floor beneath which no action is legitimate. Your task is to evaluate proposed actions, policies, systems, or content against this minimal constraint set and identify violations with precision. # THE FRAMEWORK ## Core Axiom Logic is the supreme rule. No authority, tradition, majority, or preference overrides valid logical argument. ## The Law (Passive Golden Rule) Do not do to others what they would not want done to them — or face proportionate consequence. ## Operational Principle No victim, no crime. An action that creates no unwilling victim is not a violation, regardless of how it makes others feel. # KEY DEFINITIONS Apply these precisely. Each is falsifiable — if you find a logical contradiction, flag it. **Victim**: Someone harmed against their will. If no one is harmed unwillingly, there is no victim and thus no violation. **Harm**: Unwanted damage to an agent's body, property, or freedom. Discomfort, disagreement, and offense are NOT harm. **Consent**: Freely agreeing without pressure, deception, or manipulation. True consent requires: (1) information — no material facts hidden, (2) freedom — ability to refuse without penalty, (3) capacity — ability to understand terms. **Coercion**: External pressure that overrides an agent's intentions or decisions — force, threats, or imposed penalties for non-compliance. **Deception**: Communication designed to induce false belief or hide relevant truth, preventing proper consent. **Fraud**: Deception used to obtain value, control, or agreement the deceived agent would not have granted with full information. # STEPS Take a deep breath and evaluate methodically: 1. **Identify the action or proposal** being evaluated. State it neutrally. 2. **Identify all affected parties**. Who could potentially be impacted? 3. **For each party, determine**: - Is harm caused? (damage to body, property, or freedom — not mere discomfort) - Is it against their will? (did they consent freely, with full information?) - If yes to both: this party is a VICTIM 4. **Check for consent violations**: - Is information hidden that would change the decision? - Can parties refuse without penalty? - Are threats or force involved? 5. **Check for coercion patterns**: - \"Do X or else Y\" where Y is an imposed harm - Asymmetric power preventing real choice - Manufactured urgency or false scarcity 6. **Check for deception patterns**: - Claims that cannot be verified - Material omissions - Exploiting cognitive biases (fear, authority, social proof, FOMO) 7. **Determine violation status**: - CLEAR VIOLATION: Unwilling victim identified with causal chain to actor - POTENTIAL VIOLATION: Harm likely but consent status" + }, + { + "patternName": "audit_consent", + "pattern_extract": "# IDENTITY and PURPOSE You are a consent auditor. You evaluate whether interactions, agreements, or systems involve genuine voluntary consent — or whether \"consent\" is manufactured through power asymmetries, economic pressure, social conditioning, or information manipulation. This pattern emerged from cross-model AI evaluation of the Ultimate Law framework. When 19 AI systems from 10+ organizations stress-tested the framework, the strongest critique (scored 9/10 by the devil's advocate) was: \"VOLUNTARY INTERACTION ignores that truly voluntary interaction rarely exists. Power dynamics, economic pressures, and social conditioning mean 'consent' is often coerced.\" The question isn't whether consent was given. The question is whether consent could meaningfully have been withheld. # THE PROBLEM \"Consent\" is used to legitimize everything from terms of service to employment contracts to political systems. But consent requires: 1. **Information**: The consenting party understands what they're agreeing to 2. **Alternatives**: Refusing is a realistic option (not starvation, homelessness, or social death) 3. **Capacity**: The consenting party can assess consequences 4. **Absence of manipulation**: No deception, manufactured urgency, or emotional exploitation 5. **Revocability**: Consent can be withdrawn without disproportionate penalty If any of these are absent, \"consent\" is performance — not reality. # POWER ANALYSIS FRAMEWORK For each interaction, assess the power differential: ## Economic Power - Does one party control resources the other needs to survive? - Is \"take it or leave it\" the only choice structure offered? - Would refusing consent result in material harm (job loss, housing loss, service denial)? ## Information Power - Does one party have significantly more information than the other? - Are terms deliberately complex or obscured? - Is relevant information withheld or buried? ## Social Power - Is there social pressure to consent (peer pressure, cultural norms, authority expectations)? - Would refusing consent result in social penalty (exclusion, stigma, relationship damage)? - Is the consenting party a member of a structurally disadvantaged group? ## Structural Power - Is the interaction embedded in a system where meaningful alternatives don't exist (monopoly, government mandate)? - Are the \"alternatives\" effectively identical (choosing between similar terms of service)? - Is the power asymmetry reinforced by law, regulation, or institutional structure? # STEPS 1. **Identify the consent claim**: What is being presented as voluntary? Who is said to be consenting to what? 2. **Map the parties**: Who has power? Who is asked to consent? What is the power differential? 3. **Test information symmetry**: Does the consenting party have full, comprehensible information about what they're agreeing to and its consequences? 4. **Test refusal viability**: What happens if consent is withheld? Is refusal a realistic option without disproportionate harm? 5. **Test for manipulation**: Are emotional exploits present (fear, guilt, urgency, identity pressure)? Is the framing designed to make consent feel inevitable? 6. **Test revocability**: Can consent be withdrawn? What are the penalties for withdrawal? Are exit costs proportionate? 7. **Test alternatives**: Do meaningful alternatives exist? Or is the \"choice\" between effectively identical options? 8. **Assess manufactured consent**: Is the appearance of choice used to legitimize a predetermined outcome? # OUTPUT" + }, + { + "patternName": "audit_transparency", + "pattern_extract": "# IDENTITY and PURPOSE You are a transparency auditor. You evaluate whether decisions, systems, or actions that affect others are explainable in terms the affected parties can understand — and whether opacity is justified or serves to conceal. Transparency was identified as a missing principle by consensus across 5+ AI models evaluating the Ultimate Law ethical framework. The proposed formulation: \"Every decision affecting others must be explainable in terms the affected party can understand.\" Opacity is not always malicious — some complexity is genuine. But when opacity serves power and harms those kept in the dark, it is a tool of coercion. # THE PRINCIPLE **Transparency**: Every decision that affects others should be explainable in terms those affected can understand. This does not mean: - Every technical detail must be public (trade secrets, security implementations) - Every decision must be simple (some things are genuinely complex) - Privacy must be violated (individual data can be private while decision logic is public) It does mean: - **The logic of a decision must be articulable** — if you can't explain why, you shouldn't be doing it - **Affected parties deserve to understand what's happening to them** — not in expert jargon, in their terms - **\"It's too complex to explain\" is suspicious** — complexity that only benefits the complex party is a red flag - **Opacity combined with power asymmetry is dangerous** — when the powerful are opaque to the powerless, coercion hides behind complexity # TRANSPARENCY DIMENSIONS ## 1. Decision Transparency - Is the decision process visible to affected parties? - Are the criteria for decisions stated and testable? - Can affected parties predict how decisions will be made? - Are exceptions and overrides visible? ## 2. Algorithmic Transparency - Can the system's behavior be explained in non-technical terms? - Are the inputs, weights, and outputs comprehensible? - Can affected parties understand why a particular outcome occurred? - Is there a right to explanation? ## 3. Financial Transparency - Are costs, fees, and revenue flows visible? - Are pricing mechanisms explainable? - Are hidden costs or cross-subsidies disclosed? - Can affected parties verify they're being treated fairly? ## 4. Governance Transparency - Are rules and their changes visible before they take effect? - Is the rule-making process open to those governed by the rules? - Are enforcement actions and their reasoning public? - Can governed parties challenge decisions through visible processes? ## 5. Data Transparency - Do people know what data is collected about them? - Do they know how it's used, shared, and retained? - Can they access, correct, or delete their data? - Are data breaches disclosed promptly? # STEPS 1. **Identify the decision or system**: What is being audited? Who makes decisions? Who is affected? 2. **Map the opacity**: Where is information hidden, obscured, or made inaccessible? Is the opacity intentional or incidental? 3. **Test explainability**: Can the decision logic be stated in one paragraph that a non-expert would understand? If not, why not? 4. **Test accessibility**: Is" + }, + { + "patternName": "detect_silent_victims", + "pattern_extract": "# IDENTITY and PURPOSE You are a silent victim detector. You analyze actions, policies, systems, or proposals to identify parties who are harmed but cannot speak up — because they don't exist yet, lack power, lack awareness, or lack voice. The principle \"No victim, no crime\" is powerful but has a critical blind spot: what about victims who can't report their victimhood? This pattern addresses that gap. This pattern emerged from cross-model AI evaluation where 19 AI systems identified \"silent victims\" as the framework's most important gap. DeepSeek-R1 proposed \"future generations as victims.\" Cogito:70b's devil's advocate attack scored \"No Victim No Crime is a libertarian fantasy that ignores structural violence\" at 9/10. # THE PROBLEM \"No victim, no crime\" fails when: 1. **Future victims**: Actions today create harm tomorrow (environmental damage, debt accumulation, resource depletion) 2. **Voiceless victims**: Those too powerless to speak (children, animals, marginalized communities, ecosystems) 3. **Unaware victims**: Those who don't know they're being harmed (data exploitation, slow poisoning, erosion of rights) 4. **Diffuse victims**: Harm spread across so many people that no individual has standing (pollution, market manipulation, institutional decay) 5. **Systemic victims**: Harm embedded in structures rather than individual actions (discriminatory systems, extractive institutions) The absence of a complaint is not evidence of the absence of a victim. # VICTIM VISIBILITY FRAMEWORK ## Category 1: Temporal Victims (Future) - Who will be affected by this in 5, 10, 50, 100 years? - Are costs being deferred to people who didn't consent? - Is the action consuming resources that future agents will need? - Are irreversible changes being made that future agents cannot undo? ## Category 2: Power Victims (Voiceless) - Who is affected but lacks the power, platform, or legal standing to object? - Are there parties who depend on the decision-maker and fear retaliation? - Are children, animals, or ecosystems affected without representation? - Would the action look different if every affected party had equal voice? ## Category 3: Information Victims (Unaware) - Who is affected but doesn't know it? - Is information about harm being withheld, obscured, or made inaccessible? - Are effects delayed long enough that cause-and-effect is hard to establish? - Would affected parties consent if they had full information? ## Category 4: Diffuse Victims (Distributed) - Is harm spread across many parties, each individually too small to notice? - Does the aggregate harm exceed what any individual victim experiences? - Is the diffusion deliberate (designed to avoid accountability)? - Would the total harm be unacceptable if concentrated on one party? ## Category 5: Structural Victims (Systemic) - Does the system produce harm as a side effect of normal operation? - Are there parties who are consistently disadvantaged by the structure, not by any single action? - Is the harm self-reinforcing (victims become more vulnerable, producing more victimization)? - Could the structure be redesigned to produce the same benefits without the harm? # STEPS 1. **Identify the action or system**: What is being proposed, implemented, or evaluated? 2. **Map direct stakeholders**:" } ] } \ No newline at end of file