agentleFS
Didib-LabDidib-Lab/didib-skillhub/skills/conventional-commits/SKILL.md

conventional-commits

Skill0 starsChanged 29 days agoMITView on GitHub

Write, review, and validate Conventional Commits messages so changelogs and semantic releases can be generated automatically. Use when the user asks for a commit message, asks to commit staged changes, wants a PR squash title, needs to fix a bad commit message, or when a repo enforces commitlint / semantic-release conventions.

56 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use github, grilling and 9 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.
  • NVIDIASkill

    github

    Interact with GitHub using the gh CLI restricted to REST API only (no GraphQL). Use when the user wants to work with GitHub issues, pull requests, repos, releases, or Actions — especially in sandboxed environments where the GraphQL endpoint may be blocked. Trigger keywords - github, gh, pull request, PR, github issue, github actions, workflow, release, gh api.

    Also in 3 projects that use this

  • GoogleSkill

    grilling

    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

    Also in 5 projects that use this

  • GoogleSkill

    domain-modeling

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

    Also in 4 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 5 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 5 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

  • +5 more from google

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the actual change before writing a word: Run git diff --staged (or git diff when nothing is staged).

    line 34
  2. Distinctive:

    Add a body: only when the diff cannot speak for itself — record *why*, not *what*.

    line 47
  3. Distinctive:

    Validate: before handing the message over:

    line 50
  4. Very specific:

    If something user-visible would be missing from the changelog, it is almost always a feat or a fix.

    line 72
  5. Distinctive:

    If none of the last twenty subjects contains a colon-delimited type, the repo does not use Conventional Commits — match the existing style …

    line 132

“Common” is measured: kept by at least 6 in 10 of the 51 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

Conventional Commits

Produce commit messages that comply with Conventional Commits v1.0.0 and that tooling such as commitlint, semantic-release, and standard-version can parse without manual cleanup.

The shape of a message

<type>[optional scope][!]: <description>

[optional body]

[optional footer(s)]

A commit that only changes the message itself must still parse; anything the parser cannot read is invisible to the changelog.

Workflow

  1. Read the actual change before writing a word. Run git diff --staged (or git diff when nothing is staged). Never infer the type from the file name or from what the user said they were doing.
  2. Pick exactly one type using the table below. If a change spans two types, that is a signal to split it into two commits — say so instead of picking the "bigger" one.
  3. Pick a scope from the repository's existing scopes. Discover them with:
    git log --format='%s' -500 | grep -oP '^\w+\(([^)]+)\)' | sort -u
    Omit the scope when the change is genuinely repo-wide.
  4. Write the description in the imperative mood, lowercase, no trailing period, at most 72 characters including the type and scope prefix.
  5. Add a body only when the diff cannot speak for itself — record why, not what. Wrap at 72 columns.
  6. Add footers for breaking changes and issue references.
  7. Validate before handing the message over:
    python scripts/commit_lint.py --file -   # lint a message from stdin

Type selection

TypeUse it when the change…Triggers a release
featadds a capability a user can observeminor
fixrepairs incorrect behaviourpatch
perfmakes existing behaviour faster without changing itpatch
refactorrestructures code with no behaviour changenone
docstouches documentation onlynone
testadds or repairs tests onlynone
buildchanges the build system or dependenciesnone
cichanges CI configuration or scriptsnone
choreroutine maintenance not covered abovenone
styleformatting only, no semantic changenone
revertreverts an earlier commitnone

feat and fix are the only types that generate changelog entries by default. If something user-visible would be missing from the changelog, it is almost always a feat or a fix.

Breaking changes

Signal a breaking change twice — with ! and with a footer:

feat(api)!: drop support for the v1 token endpoint

BREAKING CHANGE: requests to /v1/token now return 410. Clients must migrate
to /v2/token, which accepts the same payload.

The ! makes the change visible at a glance in git log --oneline; the BREAKING CHANGE: footer is what release tooling actually reads. Use the uppercase spelling exactly — BREAKING-CHANGE: is accepted as a synonym, breaking change: is not.

Footers

Refs: #412
Closes: #418, #420
Co-authored-by: Jae <jae@example.com>
Reviewed-by: Kim <kim@example.com>

One token, then : or #, then the value. Closes and Fixes must contain the issue reference for GitHub to close the issue automatically.

Common mistakes to correct

  • feat: Added new login flow. — past tense and a trailing period. Write feat(auth): add SSO login flow.
  • fix: bugfix — says nothing. Name the symptom that is gone.
  • update stuff — no type. The parser drops the commit from the changelog.
  • feat: add user API and fix the login redirect — two types in one commit. Split it.
  • BREAKING CHANGE inside the description line instead of the footer — release tooling will not see it.

Reference material

  • references/spec.md — the complete v1.0.0 grammar, including edge cases for footers, revert commits, and merge commits.
  • references/examples.md — twenty real messages annotated with why they pass or fail, plus the correct rewrite for each failure.
  • scripts/commit_lint.py — dependency-free linter used by the workflow above.

When NOT to use this skill

Repositories that enforce a different convention (for example Gerrit Change-Id trailers without types, or a corporate ticket-prefix scheme) should follow their own rules. Detect this first:

git log --format='%s' -20

If none of the last twenty subjects contains a colon-delimited type, the repo does not use Conventional Commits — match the existing style instead.

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.