agentsclimarketplace

Commit

Skill tartinerlabs/skills/skills/commit

Use when committing changes, staging files, saving work, or making a git commit. Creates clean commits in the repository's own convention (conventional commits, area prefix, tracker ID, or plain) with secret scanning (GitLeaks).From its SKILL.md

Install
npx -y skills add tartinerlabs/skills --skill commit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 3 commands, including `gitleaks git --staged --redact --verbose` and 2 more.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, 619 tokens by cl100k_base, as published. Nobody here has run it

You create git commits with short, readable messages that match the repository's existing convention.

Load an ecosystem guide only when rules/convention-detection.md reaches Tier 3 and the manifest matches it: references/go.md, references/swift.md, references/python.md, references/systems.md.

Rules Overview

RuleImpactFile
Convention detectionHIGHrules/convention-detection.md
Message formatHIGHrules/message-format.md
Commit type selectionHIGHrules/commit-type.md
Issue referencesMEDIUMrules/issue-references.md
Change scopeMEDIUMrules/change-scope.md

Pre-Commit Security Check

Scan staged changes for secrets before every commit, using the project's secret scanner. GitLeaks is the default; TruffleHog is accepted if the project already uses it.

  1. Run the scanner over staged changes after staging — GitLeaks: gitleaks git --staged --redact --verbose; TruffleHog: trufflehog git file://. --since-commit HEAD --results=verified,unknown --fail (include unknown so credentials TruffleHog cannot verify online still block the commit, matching GitLeaks).
  2. If the scanner reports a leak, STOP — do not commit. Report the finding and ask the user to remove the secret (and rotate it if it was ever pushed).
  3. If no secret scanner is installed (command not found), STOP — do not commit and do not install one implicitly. Tell the user to install one (brew install gitleaks or equivalent) and re-run.

Never edit .husky/, commitlint, or other project tooling as part of a commit. If pre-commit hooks are missing, report that and point the user to the setup skill instead of configuring it yourself.

Workflow

A commit request stages and commits only — it must never pull, stash, restore stashes, or rewrite project tooling.

  1. Show current git status and analyse all changes
  2. Detect the repository's commit convention (see rules/convention-detection.md)
  3. Check conversation context for issue references (see rules/issue-references.md)
  4. Assess scope of changes (see rules/change-scope.md)
  5. Stage only the explicit, related paths for this change — never blanket-stage unrelated modifications
  6. Choose the commit type or leading verb from branch context, not the staged diff alone (see rules/commit-type.md)
  7. Run the Pre-Commit Security Check above
  8. Create the commit with a message following rules/message-format.md

When the convention came from Tier 3 or Tier 4 of detection — an ecosystem default or the plain fallback rather than enforced tooling or clear history — state which convention was used and why, so a wrong guess is visible.

What ships with it: 9 files

24.0 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most pr commit review skills give in 619 tokens

Counted across 1,055 of the 1,911 authors here whose files we hold, read 2026-09-06

  • Use conventional commit message formatin 150 of 1055, across 145 files
  • Announce skill usage at startin 78 of 1055
  • Use imperative mood for commit descriptionsin 54 of 1055, across 51 files
  • Add directory to gitignore if not ignoredin 52 of 1055, across 41 files
  • Use imperative mood for commit subjectin 52 of 1055
  • Run tests to verify clean baselinein 42 of 1055, across 32 files
  • Push branch to originin 40 of 1055, across 38 files
  • Verify worktree directory is ignored before creationin 39 of 1055, across 32 files
  • Delete branches after mergingin 38 of 1055, across 30 files
  • Create worktree with new branchin 37 of 1055, across 32 files
  • Wrap body text at 72 charactersin 36 of 1055, across 34 files
  • Auto-detect and run project setupin 35 of 1055, across 27 files

Said here and by no other author read

  • scan staged changes for secrets
  • state convention used if detection is low confidence

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.