github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-04-30 03:00:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(docs): Add block documentation auto-generation system (#11707)

Browse Source 
- Add generate_block_docs.py script that introspects block code to
generate markdown
- Support manual content preservation via <!-- MANUAL: --> markers
- Add migrate_block_docs.py to preserve existing manual content from git
HEAD
- Add CI workflow (docs-block-sync.yml) to fail if docs drift from code
- Add Claude PR review workflow (docs-claude-review.yml) for doc changes
- Add manual LLM enhancement workflow (docs-enhance.yml)
- Add GitBook configuration (.gitbook.yaml, SUMMARY.md)
- Fix non-deterministic category ordering (categories is a set)
- Add comprehensive test suite (32 tests)
- Generate docs for 444 blocks with 66 preserved manual sections

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

<!-- Clearly explain the need for these changes: -->

### Changes 🏗️

<!-- Concisely describe all of the changes made in this pull request:
-->

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  <!-- Put your test plan here: -->
  - [x] Extensively test code generation for the docs pages



<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Introduces an automated documentation pipeline for blocks and
integrates it into CI.
> 
> - Adds `scripts/generate_block_docs.py` (+ tests) to introspect blocks
and generate `docs/integrations/**`, preserving `<!-- MANUAL: -->`
sections
> - New CI workflows: **docs-block-sync** (fails if docs drift),
**docs-claude-review** (AI review for block/docs PRs), and
**docs-enhance** (optional LLM improvements)
> - Updates existing Claude workflows to use `CLAUDE_CODE_OAUTH_TOKEN`
instead of `ANTHROPIC_API_KEY`
> - Improves numerous block descriptions/typos and links across backend
blocks to standardize docs output
> - Commits initial generated docs including
`docs/integrations/README.md` and many provider/category pages
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
631e53e0f6. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Nicholas Tindle
2026-01-19 01:03:19 -06:00
committed by GitHub
parent 1b56ff13d9
commit c1a1767034
177 changed files with 21068 additions and 1718 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
docs/integrations/dataforseo/keyword_suggestions.md Normal file
View File

@@ -0,0 +1,91 @@
# Dataforseo Keyword Suggestions
<!-- MANUAL: file_description -->
Blocks for getting keyword suggestions with search volume and competition metrics from DataForSEO.
<!-- END MANUAL -->
## Data For Seo Keyword Suggestions
### What it is
Get keyword suggestions from DataForSEO Labs Google API
### How it works
<!-- MANUAL: how_it_works -->
This block calls the DataForSEO Labs Google Keyword Suggestions API to generate keyword ideas based on a seed keyword. It provides search volume, competition metrics, CPC data, and keyword difficulty scores for each suggestion.
Configure location and language targeting to get region-specific results. Optional SERP and clickstream data provide additional insights into search behavior and click patterns.
<!-- END MANUAL -->
### Inputs
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| keyword | Seed keyword to get suggestions for | str | Yes |
| location_code | Location code for targeting (e.g., 2840 for USA) | int | No |
| language_code | Language code (e.g., 'en' for English) | str | No |
| include_seed_keyword | Include the seed keyword in results | bool | No |
| include_serp_info | Include SERP information | bool | No |
| include_clickstream_data | Include clickstream metrics | bool | No |
| limit | Maximum number of results (up to 3000) | int | No |
### Outputs
| Output | Description | Type |
|--------|-------------|------|
| error | Error message if the operation failed | str |
| suggestions | List of keyword suggestions with metrics | List[KeywordSuggestion] |
| suggestion | A single keyword suggestion with metrics | KeywordSuggestion |
| total_count | Total number of suggestions returned | int |
| seed_keyword | The seed keyword used for the query | str |
### Possible use case
<!-- MANUAL: use_case -->
**Content Planning**: Generate blog post and article ideas based on keyword suggestions with high search volume.
**SEO Strategy**: Discover new keyword opportunities to target based on competition and difficulty metrics.
**PPC Campaigns**: Find keywords for advertising campaigns using CPC and competition data.
<!-- END MANUAL -->
---
## Keyword Suggestion Extractor
### What it is
Extract individual fields from a KeywordSuggestion object
### How it works
<!-- MANUAL: how_it_works -->
This block extracts individual fields from a KeywordSuggestion object returned by the Keyword Suggestions block. It decomposes the suggestion into separate outputs for easier use in workflows.
Each field including keyword text, search volume, competition level, CPC, difficulty score, and optional SERP/clickstream data becomes available as individual outputs for downstream processing.
<!-- END MANUAL -->
### Inputs
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| suggestion | The keyword suggestion object to extract fields from | KeywordSuggestion | Yes |
### Outputs
| Output | Description | Type |
|--------|-------------|------|
| error | Error message if the operation failed | str |
| keyword | The keyword suggestion | str |
| search_volume | Monthly search volume | int |
| competition | Competition level (0-1) | float |
| cpc | Cost per click in USD | float |
| keyword_difficulty | Keyword difficulty score | int |
| serp_info | data from SERP for each keyword | Dict[str, Any] |
| clickstream_data | Clickstream data metrics | Dict[str, Any] |
### Possible use case
<!-- MANUAL: use_case -->
**Keyword Filtering**: Extract search volume and difficulty to filter keywords meeting specific thresholds.
**Data Analysis**: Access individual metrics for comparison, sorting, or custom scoring algorithms.
**Report Generation**: Pull specific fields like CPC and competition for SEO or PPC reports.
<!-- END MANUAL -->
---

92
docs/integrations/dataforseo/related_keywords.md Normal file
View File

@@ -0,0 +1,92 @@
# Dataforseo Related Keywords
<!-- MANUAL: file_description -->
Blocks for finding semantically related keywords using the DataForSEO Labs API.
<!-- END MANUAL -->
## Data For Seo Related Keywords
### What it is
Get related keywords from DataForSEO Labs Google API
### How it works
<!-- MANUAL: how_it_works -->
This block uses the DataForSEO Labs Google Related Keywords API to find semantically related keywords based on a seed keyword. It returns keywords that share similar search intent or topic relevance.
The depth parameter controls the breadth of the search, with higher values returning exponentially more related keywords. Results include search metrics, competition data, and optional SERP/clickstream information.
<!-- END MANUAL -->
### Inputs
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| keyword | Seed keyword to find related keywords for | str | Yes |
| location_code | Location code for targeting (e.g., 2840 for USA) | int | No |
| language_code | Language code (e.g., 'en' for English) | str | No |
| include_seed_keyword | Include the seed keyword in results | bool | No |
| include_serp_info | Include SERP information | bool | No |
| include_clickstream_data | Include clickstream metrics | bool | No |
| limit | Maximum number of results (up to 3000) | int | No |
| depth | Keyword search depth (0-4). Controls the number of returned keywords: 0=1 keyword, 1=~8 keywords, 2=~72 keywords, 3=~584 keywords, 4=~4680 keywords | int | No |
### Outputs
| Output | Description | Type |
|--------|-------------|------|
| error | Error message if the operation failed | str |
| related_keywords | List of related keywords with metrics | List[RelatedKeyword] |
| related_keyword | A related keyword with metrics | RelatedKeyword |
| total_count | Total number of related keywords returned | int |
| seed_keyword | The seed keyword used for the query | str |
### Possible use case
<!-- MANUAL: use_case -->
**Topic Clustering**: Group related keywords to build comprehensive content clusters around a topic.
**Semantic SEO**: Discover LSI (latent semantic indexing) keywords to improve content relevance.
**Keyword Expansion**: Expand targeting beyond exact match to capture related search traffic.
<!-- END MANUAL -->
---
## Related Keyword Extractor
### What it is
Extract individual fields from a RelatedKeyword object
### How it works
<!-- MANUAL: how_it_works -->
This block extracts individual fields from a RelatedKeyword object returned by the Related Keywords block. It separates the compound object into distinct outputs for workflow integration.
Outputs include the keyword text, search volume, competition score, CPC, keyword difficulty, and any SERP or clickstream data that was requested in the original search.
<!-- END MANUAL -->
### Inputs
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| related_keyword | The related keyword object to extract fields from | RelatedKeyword | Yes |
### Outputs
| Output | Description | Type |
|--------|-------------|------|
| error | Error message if the operation failed | str |
| keyword | The related keyword | str |
| search_volume | Monthly search volume | int |
| competition | Competition level (0-1) | float |
| cpc | Cost per click in USD | float |
| keyword_difficulty | Keyword difficulty score | int |
| serp_info | SERP data for the keyword | Dict[str, Any] |
| clickstream_data | Clickstream data metrics | Dict[str, Any] |
### Possible use case
<!-- MANUAL: use_case -->
**Keyword Prioritization**: Extract metrics to rank related keywords by opportunity score.
**Content Optimization**: Access keyword difficulty and search volume for content planning decisions.
**Competitive Analysis**: Pull competition and CPC data to assess keyword viability.
<!-- END MANUAL -->
---