{{NAME=null}=null}
Briefly describe what this skill does AND when to use it. Use imperative phrasing ("Use this skill when..."). Aim for 80-500 chars. Include keywords the model can pattern-match against the user's prompt.
- License 许可
- MIT
- 最近更新
- 2026-04-30
- Stars
- ★ 1
- Forks
- 2
01 前言 Front Matter
- name
- { "{NAME=null}": null }
- license
- MIT
- metadata
- { "harness-author": "human", "harness-status": "draft" }
- description
- Briefly describe what this skill does AND when to use it. Use imperative phrasing ("Use this skill when..."). Aim for 80-500 chars. Include keywords the model can pattern-match against the user's prompt.
02 资源文件 2
- 参考文档references/REFERENCE.md323 B
- 脚本scripts/run.sh906 B
03 SKILL.md 正文
{{NAME}}
When to use
Describe the trigger context. Example: "Use when the user asks to..."
Available scripts
scripts/run.sh— Brief description of what the script does and when to invoke it
Workflow
- Step 1: Run
scripts/run.sh <args>and read the JSON result - Step 2: ...
Gotchas
Non-obvious facts the agent would otherwise get wrong. Example: "The API
returns 200 even on auth failure — check the error field in the body, not
the HTTP status."
Failure modes
Known errors and recovery paths. Each entry includes the error.code the
script returns and what the agent should do next.
04 同仓库更多 Skills
research
Conduct research.
working-in-a-git-repo
Operating manual for dev work: worktree discipline, build/test/lint commands, file ownership zones, commit style, and a verification checklist before reporting done. Use when starting any feature/fix work in this repo.
test-runner
Runs the project's test suite (or a targeted subset), parses the output, and reports pass/fail with failing-test details. Use when you need to know test status; call with the test command to run, or leave blank for the project default.
reviewer
Reviews a diff or change set for bugs, security issues, test gaps, and style. Use when evaluating a code change, reviewing a pull request, or running a structured review pass before merge.
fix-failing-tests
Seven-step flow for diagnosing and fixing failing tests. Use when the user asks to fix failing tests, green the suite, or says 'tests are red' — works through reproduce → read → root-cause → propose → apply → verify → commit.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code