agentleFS
Sign inStart free
thoitiettxl-cyberthoitiettxl-cyber/Claw-II/skills/commit-commands/SKILL.md

commit-commands

Skill2 starsChanged 7 months agoMITView on GitHub

Standardize commit workflow (message quality, scope integrity, preflight checks) for OpenClaw workspace.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the staged diff and determine the change intent.

    line 50
  2. Distinctive:

    Run the preflight checklist.

    line 52
  3. Distinctive:

    If the user agrees, execute the commit.

    line 53
  4. Distinctive:

    No staged changes: clearly indicate and suggest stage files.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

commit-commands

Indexed Reference Map

  • @[SKILL.md#L1-L64] Frontmatter + workflow rules
  • @[references/INDEX.md#L1-L12] Reading order
  • @[references/QUICK_REFERENCE.md#L1-L14] Commit message conventions
  • @[references/CORE_API.md#L1-L24] Preflight/check/output schema
  • @[references/PATTERNS.md#L1-L11] Good/bad commit patterns
  • @[references/EXAMPLES.md#L1-L13] Commit examples
  • @[references/AI_WORKFLOW.md#L1-L7] Execution flow

Scope

  • In-scope:
    • Generate standard commit message (type/scope/subject/body).
    • Preflight check: staged files, light secret scan, scope fit.
    • Chia commit logic theo atomic change.
  • Out-of-scope:
    • Force rewrite history (rebase/reset) if the user has not requested it.
    • Auto-push remote by default.

Reading Order

  1. references/QUICK_REFERENCE.md
  2. references/CORE_API.md
  3. references/PATTERNS.md
  4. references/EXAMPLES.md
  5. references/AI_WORKFLOW.md

Coverage Matrix

  • Conventional style: yes
  • Atomicity check: yes
  • Secret hygiene preflight: basic
  • Remote push control: gated

Trigger Rules

  • Positive: Used when the user needs to create/edit a commit message or commit workflow.
  • Negative: Do not use for tasks unrelated to git commit.
  • Escalation: If the operation affects extended history or remote push, please approve first.

SOP

  1. Read the staged diff and determine the change intent.
  2. Suggested commit title/body + rationale.
  3. Run the preflight checklist.
  4. If the user agrees, execute the commit.
  5. Report the result: hash + files + next step.

Error Handling

  • No staged changes: clearly indicate and suggest stage files.
  • Mixed-scope diff: proposes to split the commit.
  • Preflight fail (secret/risky file): block and request processing.

Output Contract

  • Artifact: commit_plan + commit_result (if already running).
  • Validation: message format + atomicity pass.
  • Compliance Verdict: PASS when committing is clear, does not reveal secrets, and has reasonable scope.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free