메뉴
When Lark integration tests need running → execute test suite, analyze failures, auto-iterate fixes by severity.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.
| name | self-test |
| description | When Lark integration tests need running → execute test suite, analyze failures, auto-iterate fixes by severity. |
| triggers | {"intent_patterns":["self.?test|自测|场景测试|scenario.?test|run.?test|测试套件","跑.*测试|run.*tests|执行.*测试|execute.*tests","飞书.*测试|lark.*test|集成.*测试|integration.*test","测试.*失败.*修|fix.*failing|修复.*测试|repair.*test","全量.*测试|full.*suite|冒烟.*测试|smoke.*test"],"context_signals":{"keywords":["test","scenario","lark","测试","自测","集成","冒烟","suite","失败","修复"]},"confidence_threshold":0.7} |
| priority | 7 |
| requires_tools | ["bash"] |
| max_tokens | 200 |
| cooldown | 120 |
Run the Lark scenario test suite, analyze failures by root cause (test_drift, prompt_issue, tool_bug, etc.), apply tiered auto-fixes (up to 3 rounds), and generate a structured report. All test execution, failure analysis, and iterative repair logic are handled by run.py.
python3 skills/self-test/run.py run