# Self Test

> When Lark integration tests need running → execute test suite, analyze failures, auto-iterate fixes by severity.

- Skill: `cklxx/self-test` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add cklxx/self-test`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cklxx/self-test/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: cklxx (https://skillmd.com/u/cklxx)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/cklxx/self-test

---


# self-test

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.

## 调用

```bash
python3 skills/self-test/run.py run
```