agentleFS
sponge-b0bsponge-b0b/Polaris/.agents/skills/conventional-commits/SKILL.md

conventional-commits

Skill4 starsChanged 4 months agoApache-2.0View on GitHub

Enforces strict adherence to the Conventional Commits 1.0.0 specification for staging and saving changes. Use when a user asks to commit files, draft a git message, or finalize code tasks.

59 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use github, code-review and 1 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

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 7 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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 53 edited versions we read keep these.

  • 2

    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:

    Every commit message must follow this structural schema exactly:

    line 17
  2. Distinctive:

    Type: Must be entirely lowercase.

    line 23
  3. Very specific:

    If an engineering operation changes the system's foundational layout or breaks backward compatibility, append an exclamation point (!) …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 53 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

Git Commit Guidelines

Objective

Structure every Git commit message in strict compliance with the Conventional Commits 1.0.0 specification. Never write generic, conversational, or vague commit summaries (e.g., do not use "wip", "updated files", or "fixed bug").

Message Structure Blueprint

Every commit message must follow this structural schema exactly:

<type>[scope]: <description>

[optional body describing why the change was made]
  • Type: Must be entirely lowercase. Use only the approved structural types listed below.
  • Scope: Required. Represents the specific software layer or folder module modified, wrapped in lowercase parentheses (e.g., (reranker), (api), (db)).
  • Description: Written in the imperative mood (e.g., use add instead of added, fix instead of fixes). Do not capitalize the first letter and do not add a trailing period.

Approved Structural Types

Map code changes strictly to these categories:

  • feat(scope): Used when introducing a brand-new application feature or operational capability to the codebase.
  • fix(scope): Used when correcting an active bug, permission block, error log, or software crash.
  • docs(scope): Used for changes restricted entirely to documentation layout text, markdown headers, and user guides.
  • chore(scope): Used for routine maintenance operations: package/dependency management, editing configurations (.gitignore, pyproject.toml, .graphifyignore), or adding static asset/image files.
  • refactor(scope): Used for optimization or structural alterations to production code that do not change its runtime features or behavior.
  • test(scope): Used when generating unit tests, increasing coverage matrix setups, or altering testing suites.
  • ci(scope): Used for orchestration scripts, automated pipelines, deployment assets, or Docker Compose structures.

Handling Breaking Changes

If an engineering operation changes the system's foundational layout or breaks backward compatibility, append an exclamation point (!) directly to the commit type prefix and write BREAKING CHANGE: in the commit message body explaining the required manual migration layout steps. Example: feat(db)!: switch token storage mapping to postgresql

Examples

Example 1: Standard Staging & Commit Flow

User: "Commit my backend updates." Agent Response: Runs git diff --cached to evaluate the staging area, determines that a new validation routine was added to an API component, and structures the commit message:

git commit -m "feat(api): include cross-encoder payload validation schemas"

Example 2: Bug Fix Flow

User: "Save the changes that fixed the permission crash." Agent Response: Evaluates changes and structures the commit:

git commit -m "fix(reranker): map container user permissions to prevent wsl lockouts"

Example 3: Infrastructure and Documentation Tasks

  • chore(git): add graphify local cache paths to gitignore file
  • docs(deployment): supplement setup documentation detailing offline launch instructions

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.