Agent skill

Cr Commit Check

by LeoYeAI in LeoYeAI/openclaw-master-skills

【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 codereview 阶段自动调用,不建议单独触发。

MITAuto-check passedDevelopment

Install Cr Commit Check

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill cr-commit-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills cr-commit-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spec-driven-dev/sub-skills/cr-commit-check .claude/skills/cr-commit-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cr-commit-check
GitHub stars
2.2k
Token cost
~943 tokens
SKILL.md length
171 words
Files
1
Skills in repo
1,215
Repo updated
First seen
Licence
MIT

At a glance

【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 codereview 阶段自动调用,不建议单独触发。

  • Works in 6 steps: 发出启动检查点 → 解析 commit 列表 → 输出规则结果表 → …
  • Tasks that involve Spec-driven development
  • SKILL.md covers 调用契约, 执行协议, 校验规则 and 裁决规则, plus 1 more section
  • Calls git

What it does

Cr Commit Check is an agent skill from LeoYeAI/openclaw-master-skills. 【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 codereview 阶段自动调用,不建议单独触发。

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Spec-driven development, Commit messages and Code review. It works with Git. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Spec-driven development
  • Tasks that involve Commit messages
  • Tasks that involve Code review

Example prompts

  • “/cr-commit-check”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 发出启动检查点
  2. 解析 commit 列表
  3. 输出规则结果表
  4. 生成修复指引(仅 FAIL 时)
  5. 返回结构化结果
  6. 发出结束检查点

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cr Commit Check loads about 943 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 171 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~943

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 171 words, ~943 tokens.

Download SKILL.mdSave it as .claude/skills/cr-commit-check/SKILL.md (or your agent's skills folder).
name
cr-commit-check
description
【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。
user-invocable
false

cr-commit-check

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。


调用契约

输入(由 Orchestrator 注入上下文)
字段类型说明
us_idstring用户故事 ID,如 US042
iter_idstring当前迭代 ID,如 iter_003
git_logstringgit log main..HEAD --pretty=full 的完整输出
tasks_json_pathstringrequirements/{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"
输出(写回 Orchestrator)
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"]
}

执行协议

Step 0 — 发出启动检查点
[AGENT:cr-commit-check] START  us_id={us_id}  iter_id={iter_id}
Step 1 — 解析 commit 列表

从 git_log 中提取本迭代全部 commit,按以下顺序校验每一条:


校验规则

规则 ID检查项通过条件失败影响
CM-01Conventional Commits 格式满足正则 ^(feat|fix|config|docs|test|refactor|perf|style|chore|build)(\(.+\))?: .+FAIL
CM-02type 在允许列表内type ∈ feat|fix|config|docs|test|refactor|perf|style|chore|buildFAIL
CM-03每迭代仅一次 commitcommit 数量 = 1FAIL
CM-04scope 包含正确的 us_id/iter_idscope 满足 #<us_id>/<iter_id> 格式,如 #US042/iter_003FAIL
CM-05描述中列出全部 task读取 tasks.json,验证每个 task id 都以 task-XX/描述 形式出现在 message 中FAIL
CM-06无 WIP / 临时提交message 不含 wip、temp、fixup!、squash!,且 message 非空FAIL

所有规则均为硬性规则:任意一条失败 → 整体裁决 FAIL。

Step 2 — 输出规则结果表

逐条输出结构化结果:

[cr-commit-check] CM-01  ✅ PASS
[cr-commit-check] CM-02  ✅ PASS
[cr-commit-check] CM-03  ❌ FAIL  — 发现 2 条 commit,迭代只允许 1 条
[cr-commit-check] CM-04  ✅ PASS
[cr-commit-check] CM-05  ❌ FAIL  — task-03 未出现在 commit message 中
[cr-commit-check] CM-06  ✅ PASS
Step 3 — 生成修复指引(仅 FAIL 时)

若裁决为 FAIL,输出可直接执行的修复命令,例如:

bash
# 合并多余 commit 并修正 message
git rebase -i HEAD~2
# 或直接修正最后一条 commit
git commit --amend -m "feat(#US042/iter_003): task-01/login flow, task-02/jwt, task-03/tests"
Step 4 — 返回结构化结果
json
{
  "agent": "cr-commit-check",
  "verdict": "FAIL",
  "h_count": 2,
  "rules": [
    { "id": "CM-01", "result": "PASS", "note": "" },
    { "id": "CM-02", "result": "PASS", "note": "" },
    { "id": "CM-03", "result": "FAIL", "note": "发现 2 条 commit,应为 1 条" },
    { "id": "CM-04", "result": "PASS", "note": "" },
    { "id": "CM-05", "result": "FAIL", "note": "task-03 未在 message 中声明" },
    { "id": "CM-06", "result": "PASS", "note": "" }
  ],
  "fix_commands": [
    "git rebase -i HEAD~2",
    "git commit --amend -m 'feat(#US042/iter_003): task-01/…, task-02/…, task-03/…'"
  ]
}
Step 5 — 发出结束检查点
[AGENT:cr-commit-check] DONE  verdict=PASS|FAIL  h_count=N

裁决规则

裁决条件Orchestrator 行为
PASS全部 6 条规则通过继续调用 cr-code-gate
FAIL任意规则失败终止流水线,返回修复指引,阻塞 release

禁止行为

  • 禁止对不符合规范的 commit 自动修正,只输出修复命令供人工确认执行。
  • 禁止将 m/l 的建议性问题升级为 FAIL。
  • 禁止在 git_log 为空时静默通过,应报告 CM-03 FAIL(未找到任何 commit)。

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/spec-driven-dev/sub-skills/cr-commit-check of LeoYeAI/openclaw-master-skills.

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Cr Commit Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cr Commit Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cr Commit Check this skillLeoYeAI/openclaw-master-skills2.2k—~943Automated safety check: PassMIT
Tbdjlevy/strif131—~3.5kAutomated safety check: PassMIT
GitHub Workflowtransilienceai/communitytools559—~812Automated safety check: NotesMIT
CommitZhangShenao/harness9141—~327Automated safety check: NotesMIT
Speckit Git Commitkunstmusik/blue1545 repos~492Automated safety check: PassGPL-3.0
Ship Thisplanetabhi/riseofmachine111—~2.9kAutomated safety check: PassCustom licence

Similar skills

  • Tbd

    jlevy/strif

    Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

    131 GitHub stars~3.5k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed
  • GitHub Workflow

    transilienceai/communitytools

    GitHub workflow automation — branching, committing, pushing, pull requests, issues, and code review.

    559 GitHub stars~812 tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes
  • Commit

    ZhangShenao/harness9

    A skill your agent uses when the user invokes /commit or asks to commit changes, after a code review has been completed and the changes are confirmed ready to stage and commit to git.

    141 GitHub stars~327 tokensUpdated today
    DevelopmentAuto-check: notes
  • Speckit Git Commit

    kunstmusik/blue

    Auto-commit changes after a Spec Kit command completes. An agent skill from kunstmusik/blue.

    154 GitHub starsUsed in 5 repos~492 tokens
    DevelopmentAuto-check passed
  • Ship This

    planetabhi/riseofmachine

    Load this skill before shipping a UI change, to statically review the diff for design-craft regressions (accessibility, motion, responsive, and visual or UX drift), correctness and security issues…

    111 GitHub stars~2.9k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Aube Bump

    nubjs/nub

    Bump nub's vendored aube engine to a newer jdx/aube upstream.

    4.4k GitHub stars~4.3k tokensUpdated today
    DevelopmentAuto-check: warnings

More from LeoYeAI/openclaw-master-skills

All 1,215 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Cr Commit Check

What does Cr Commit Check do?

【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 codereview 阶段自动调用,不建议单独触发。. Cr Commit Check is an agent skill from LeoYeAI/openclaw-master-skills.

When should I use Cr Commit Check?

Cr Commit Check fits situations like: tasks that involve Spec-driven development; tasks that involve Commit messages; tasks that involve Code review.

How do I install Cr Commit Check in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill cr-commit-check -a claude-code`. Or copy the skill folder (skills/spec-driven-dev/sub-skills/cr-commit-check in LeoYeAI/openclaw-master-skills) into .claude/skills/cr-commit-check in your project. Claude Code loads it when a task matches its description.

How do I install Cr Commit Check in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill cr-commit-check -a codex`. Or copy the skill folder (skills/spec-driven-dev/sub-skills/cr-commit-check in LeoYeAI/openclaw-master-skills) into .agents/skills/cr-commit-check in your project. Codex loads it when a task matches its description.

Can I use Cr Commit Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill cr-commit-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cr-commit-check, .gemini/skills/cr-commit-check, .github/skills/cr-commit-check and .opencode/skills/cr-commit-check in your project.

What does Cr Commit Check need to run?

Going by SKILL.md and its folder, Cr Commit Check needs the command-line tools its instructions call (git).

Does Cr Commit Check access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cr Commit Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cr Commit Check use?

Cr Commit Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cr Commit Check use?

About 943 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cr Commit Check?

Skills that share tags, products or a category with Cr Commit Check: Tbd (jlevy/strif, 131 stars), GitHub Workflow (transilienceai/communitytools, 559 stars), Commit (ZhangShenao/harness9, 141 stars) and Speckit Git Commit (kunstmusik/blue, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cr Commit Check?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,158 GitHub stars. The repository holds 1,215 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.