agentleFS
Sign inStart free
ElasticKnown publisherelastic/docs-builder/.claude/skills/commit/SKILL.md

commit

Skill25 starsChanged 19 days agoApache-2.0View on GitHub

Stage relevant files and create a well-formed git commit for the docs-builder repo. Use this when the user asks to commit changes, save work, or create a commit.

  • Reads credentials

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .claude/skills/writing-style.md before writing the commit message.

    line 8
  2. Very specific:

    Do not run git config yourself.

    line 25
  3. Distinctive:

    Always pass the message via HEREDOC to avoid shell escaping issues:

    line 49
  4. Distinctive:

    If a hook fails:

    line 68
  5. Distinctive:

    Read the error output carefully

    line 69
  6. Very specific:

    Create a new commit — never git commit --amend for a failed commit, and never use --no-verify

    line 72

“Common” is measured: kept by at least 6 in 10 of the 169 edited versions of this file we could read. “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 Skill

Read .claude/skills/writing-style.md before writing the commit message.

Creates a clean, well-formed commit following the docs-builder project conventions.

Steps

1. Install Husky hooks if missing

Skip this step if .husky/_/husky.sh already exists. That file is generated by dotnet husky install and is gitignored, so a fresh worktree will not have it.

if [ ! -f .husky/_/husky.sh ]; then
  dotnet tool restore
  dotnet husky install
fi

Do not run git config yourself. Do not use --no-verify.

2. Understand what changed

git status
git diff
git diff --staged
git log --oneline -5

3. Stage files

Stage specific files by name — never git add -A or git add . blindly. Exclude:

  • .env files or anything with secrets/credentials
  • Large binaries not already tracked
  • Unrelated changes to the task at hand

4. Write the commit message

  • First line: Imperative mood, ≤72 chars, no trailing period. Front-load the outcome — a reader scanning git log sees this line only.
  • Body (optional): One short paragraph explaining why, not what. Skip if the title is self-explanatory. Follow the sentence mechanics in writing-style.md.
  • Trailer: Add a Co-Authored-By: line that identifies the model that helped write this commit. Use whatever attribution feels accurate — the model name you know yourself to be running as, or simply Claude if you are uncertain. The address is always noreply@anthropic.com. The point is honest attribution, not a precise version string.

Always pass the message via HEREDOC to avoid shell escaping issues:

git commit -m "$(cat <<'EOF'
Title here

Optional body explaining why.

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"

5. Handle hook failures

This project uses Husky.Net git hooks:

  • pre-commit: runs prettier, eslint, typescript-check
  • pre-push: runs dotnet-lint

If a hook fails:

  1. Read the error output carefully
  2. Fix the underlying issue (run /lint if it's a formatting problem)
  3. Re-stage the affected files
  4. Create a new commit — never git commit --amend for a failed commit, and never use --no-verify

6. Verify success

git status

Confirm a clean working tree.

7. Refresh the PR description if one exists

gh pr view --json number,url,isDraft,baseRefName --jq '{number,url,isDraft,baseRefName}' 2>/dev/null
  • No PR → done. Say nothing.
  • PR exists → compare the current body against the current diff versus the PR's base branch. A PR description always describes the current diff against the base branch. It is never a log of the commits on the branch and never records the direction the work took. If any section (## What, ## Verify, ## Check on the preview, **Affects:**, label) no longer describes that diff, the description is stale.
  • Stale description → read and follow pr's update path (step 7). Do not hand-edit the body inline from the commit skill. State plainly what was refreshed.
  • Still accurate → state that the description is still accurate. No edit needed.

Download now (ZIP)

  • Other versions189 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 3

    1. elastic/ai-dotnet★ 2181% same
    2. elastic/elastic-transport-net★ 2181% same
    3. elastic/elastic-ingest-dotnet★ 981% same

    Wrote their own version · 186

    1. microsoft/vscode★ 194ksame name
    2. TryGhost/Ghost★ 56ksame name
    3. ToolJet/ToolJet★ 41ksame name
    4. ShareX/ShareX★ 41ksame name
    5. openai/symphony★ 27ksame name
    6. ccusage/ccusage★ 19ksame name
    7. ryoppippi/ccusage★ 19ksame name
    8. windmill-labs/windmill★ 18ksame name
    9. EverMind-AI/EverOS★ 14ksame name
    10. EverMind-AI/EverMemOS★ 14ksame name

    176 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use validate-plan, act-on-feedback and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • shawn-dumasSkill

      validate-plan

      Validate an orchestration plan after pre-flight certification. Runs adversarial review, deep review (verify prompt data against codebase), and PoC gate for risky approaches. Auto-invoked by orchestrate-* skills at Step 8.

      Also in 5 projects that use this

    • MicrosoftSkill

      act-on-feedback

      Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

      Also in 3 projects that use this

    • decocmsSkill

      add-mcp-tools

      Guide for adding new MCP tools with consistent patterns for schemas, tool definitions, registry updates, and Better Auth integration

      Also in 3 projects that use this

    • MicrosoftSkill

      generate-run-commands

      Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

      Also in 3 projects that use this

    • decocmsSkill

      run-local-freestyle

      Run Studio locally with chats and task runs executing in real Freestyle sandboxes, reachable through an ngrok tunnel. Use when asked to "run locally with Freestyle", "test claude-code chats locally", "run the sandbox harness end to end", or to try daemon/harness-runner changes in a real sandbox.

      Also in 3 projects that use this

    • mitsuhikoSkill

      oebb-scotty

      Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

      Also in 3 projects that use this

  • In this repository12 other files it gives its agents.

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