Update intros

.claude/settings.json

@@ -2,7 +2,8 @@
   "$schema": "https://json.schemastore.org/claude-code-settings.json",
   "env": {},
   "companyAnnouncements": [
-    "Welcome! Here is scroll-tech"
+    "Welcome! Here is scroll-tech",
+    "Just ask me about what can help"
   ],
   "permissions": {
     "allow": [

CLAUDE.md

@@ -1 +1,7 @@
-The mono repo for scroll-tech's services. See @README.md to know about the project.
+The mono repo for scroll-tech's services. See @README.md to know about the project.
+
+Skills has been set to help some process being handled easily. When asked by "what can you help", list following skills, along with the skill-description and invoke cost estimation here:
+
+1. `db-query`: ~$0.1 per query
+2. `integration-test-helper` Now ready for following target:
+    + `tests/prover-e2e`: ~$1.0 per process

tests/prover-e2e/README.md

@@ -18,4 +18,7 @@ link the staff dir as "conf" from one of the dir with staff set, currently we ha
   + copy `config.template.json` to `config.json`, 
   + set the `sdk_config.coordinator.base_url` field in `config.json`, so zkvm prover would connect with the locally launched coordinator api,
     for common case the url is `http://localhost:8390` (the default listening port of coordinator api)
-  + launch `make test_e2e_run`, which would specific prover run locally, connect to the local coordinator api service according to the `config.json`, and prove all tasks being injected to db in step 1.
+  + launch `make test_e2e_run`, which would specific prover run locally, connect to the local coordinator api service according to the `config.json`, and prove all tasks being injected to db in step 1.
+
+## AI Helper
+The test process can be run with the help of `integration-test-helper` skill (~$1.0 for each full process)