Conventions

Skill psenger/catholic-ai-skills/.claude/skills/conventions

Defines the commit message, branch naming, pull request, and release note conventions for the ai-agent-skills repository. Make sure to load this skill whenever writing a commit message, naming a branch, drafting a PR title or body, or writing CHANGELOG entries in this repo. Use when the user asks "how should I format this commit", "what's the branch naming convention", "how do I write the PR", "what commit type should I use", or before any git commit, PR creation, release note, or CHANGELOG task in this project.From its SKILL.md

Install

npx -y skills add psenger/catholic-ai-skills --skill conventions

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

One thing to look at

2 stars2 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.

SKILL.md

3.4 KB, 740 tokens by cl100k_base, as published. Nobody here has run it

Conventions — ai-agent-skills

Commit Messages

Format: type(scope): subject

Subject: imperative mood, lowercase, no trailing period, ≤72 characters
Scope: the skill name (vault-scribe, handoff) or a repo area (release, ci, readme)
Body: optional — explain why, not what; wrap at 72 chars
Footer: Closes #N or Fixes #N for GitHub issues; BREAKING CHANGE: <desc> for breaking changes

Types

Type	When
`feat`	New skill or new capability in an existing skill
`fix`	Bug fix in a skill's behaviour or instructions
`chore`	Release commits, tooling, config — no production change
`docs`	README, CHANGELOG, CONTRIBUTING only
`refactor`	Skill restructure with no behaviour change
`test`	Eval additions or changes

Release commit — always exactly:

chore(release): cut vX.Y.Z release

Examples

feat(handoff): add RESUME workflow and proactive suggestion trigger

fix(vault-scribe): prevent incompatible TOC directives

Closes #1

Branch Names

Pattern: type/issue-number-short-description

feature/14-add-handoff-skill
fix/23-vault-scribe-toc
chore/release-v1-1-0

feature/ for new skills or new capabilities
fix/ for bug fixes
chore/ for release and tooling work
Always include the issue number when one exists
2–4 words, hyphenated, no version dots (use dashes)

Pull Requests

Title: same format as a commit — type(scope): subject

Body:

## Summary
- <bullet 1>
- <bullet 2>

## Issue
Closes #N

## Test plan
- [ ] Skill activates on expected triggers
- [ ] Output matches documented format
- [ ] No regressions in adjacent skills

2–4 summary bullets
Always link the issue
Test plan as checkboxes

CHANGELOG Entries (Keep a Changelog 1.1.0)

### Added
- **skill-name** — What was added and why it matters. ([#N](url))

### Changed
- **skill-name** — What changed and the user-visible impact.

### Fixed
- **skill-name** — What was broken and what was fixed. ([#N](url))

Bold skill name, em dash, plain English, issue link at end
### Added for new skills, ### Changed for updates, ### Fixed for bugs
One bullet per logical change

Versioning

Semver from conventional commits since last tag:

Commit	Bump
`BREAKING CHANGE` or `type!:`	major
`feat`	minor
`fix`, `chore`, `docs`, `refactor`, `test`	patch

New skill = feat = minor bump. Tag format: vX.Y.Z (annotated tag).

What ships with it: 4 files

19.5 KB alongside SKILL.md

.workspace/

evals/evals.json2.6 KB
evals/results/2026-04-25_105542/results.json11.3 KB
evals/trigger-evals.json3.2 KB

README.md2.4 KB

Gives 0 of the 12 instructions most docs writing skills give in 740 tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

Use third-person for skill descriptionsin 54 of 1951, across 35 files
Start descriptions with Use whenin 43 of 1951, across 29 files
Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
Use active voicein 40 of 1951, across 36 files
Map file responsibilities before defining tasksin 36 of 1951, across 29 files
Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
Ask one question at a timein 35 of 1951
Offer execution options after saving the planin 33 of 1951, across 24 files
Include complete code in every stepin 33 of 1951, across 27 files
Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
Announce the skill usage at the startin 30 of 1951
Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

format commit messages as type(scope): subject
wrap commit bodies at 72 characters
use type/issue-number-short-description for branch names
include issue numbers in branch names
format pull request titles like commit messages
include a test plan with checkboxes in pull requests

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.