Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
【Code Review 子 Agent · 门控一】校验本迭代所有 commit 是否符合 Conventional Commits 规范及项目可追溯性格式。输入 git log 片段和项目元数据,输出结构化校验报告并以 STATUS=OK|FAIL 结尾。由 spec-driven-dev 的 code_review 阶段自动调用,不建议单独触发。
Code Review 流水线的第一道门控:Commit Message 合规校验子 Agent。
由 spec-driven-dev 的 code_review 阶段作为 Sub-Agent 调用,校验通过后才解锁门控二。
| 字段 | 类型 | 说明 |
|---|---|---|
us_id | string | 用户故事 ID,如 US042 |
iter_id | string | 当前迭代 ID,如 iter_003 |
git_log | string | git log main..HEAD --pretty=full 的完整输出 |
tasks_json_path | string | requirements/{us_id}/docs/tasks.json 路径,用于核对 task 列表完整性 |
Orchestrator 调用示例(OpenCode Sub-Agent 格式):
invoke_skill: cr-commit-check
with:
us_id: "US042"
iter_id: "iter_003"
git_log: "<git log output>"
tasks_json_path: "requirements/US042/docs/tasks.json"
{
"agent": "cr-commit-check",
"verdict": "PASS | FAIL",
"h_count": 0,
"rules": [
{ "id": "CM-01", "result": "PASS | FAIL", "note": "…" }
],
"fix_commands": ["git commit --amend", "git rebase -i HEAD~N"]
}
[AGENT:cr-commit-check] START us_id={us_id} iter_id={iter_id}
从 git_log 中提取本迭代全部 commit,按以下顺序校验每一条:
| 规则 ID | 检查项 | 通过条件 | 失败影响 |
npx skills add LeoYeAI/openclaw-master-skills --skill cr-commit-checkHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Very clear and well structured, with almost no room for misunderstanding.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Highly actionable with clear, concrete steps that an agent can follow directly.