The review agent was creating too many low-value skills. Three changes
tighten the funnel:
- review_worker prompt: rewritten in "保守模式". Default decision is
do-nothing. To create, all five AND conditions must hold (>=5 tool
calls with step dependencies, an explicit fail->fix->success episode,
cross-scenario reusability, no >=70% overlap with skill_list, can
produce >=300 chars of substance). Adds 7 explicit NO categories
(single-tool loops, one-off queries, LLM common knowledge, etc.)
and a 4-question self-check before any create. Hard cap of 1 new
skill per review, with patch preferred over create.
- min_tool_calls: 3 -> 5. Matches the prompt's ">=5 steps" hard
condition so trivial turns never reach the LLM reviewer.
- Updated config.yaml, the default-value assertion in
test_skill_review_worker, and the middleware docstring's "(default
3)" annotation to keep all three references in sync.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reuses the full middleware chain (ToolErrorHandlingMiddleware,
LLMErrorHandlingMiddleware, etc.) so tool errors like 'already exists'
and invalid SKILL.md are converted to ToolMessages by the middleware,
not silently swallowed or crashing the review task.