Agent skill
commit-message
Format git commit messages combining Conventional Commits summary lines with Linux kernel-style bodies. Use when writing, reviewing, or formatting commit messages.
Install this agent skill to your Project
npx add-skill https://github.com/Chemiseblanc/ai/tree/main/plugins/general/skills/commit-message
SKILL.md
Commit Message Formatting
Summary Line
Use Conventional Commits format:
<type>(<scope>): <description>
- type (required):
feat,fix,docs,style,refactor,perf,test,build,ci,chore - scope (optional): component or area affected, in parentheses
- description: imperative mood, lowercase start, no period, max 50 chars (hard limit 72)
- For breaking changes: add
!before colon:feat(api)!: remove deprecated endpoint
Body
Separate from summary with blank line. Follow kernel style:
- Wrap at 72 columns
- Imperative mood ("Add feature" not "Added feature")
- Explain why, not what (the diff shows what)
- Describe user-visible impact and motivation
- Quantify improvements with numbers when applicable
When referencing commits, use 12+ char SHA with summary:
Commit e21d2170f36602ae2708 ("video: remove unnecessary
platform_set_drvdata()") introduced a regression...
No Trailers
Omit all trailers: no Signed-off-by, Reviewed-by, Acked-by, Tested-by, Cc, Fixes, Link, etc.
Examples
Single-line fix:
fix(parser): handle empty input without panic
Feature with body:
feat(auth): add OAuth2 PKCE flow support
Mobile and SPA clients cannot securely store client secrets. PKCE
allows these clients to authenticate safely without exposing
credentials in client-side code.
This reduces authentication failures for mobile users by eliminating
the insecure implicit flow workaround.
Breaking change:
feat(api)!: require authentication for all endpoints
Anonymous access created security vulnerabilities and complicated
rate limiting. Requiring auth simplifies the security model and
enables per-user quotas.
Clients must now include a valid Bearer token with every request.
Refactor:
refactor(db): extract connection pooling into dedicated module
The monolithic database module grew to 2000+ lines, making
maintenance difficult. Separating connection pooling improves
testability and allows independent configuration tuning.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
Chemiseblanc/ai
feature-file
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.
Chemiseblanc/ai
waterfall-development
Enforces strict waterfall development workflow with phase gates. Use when (1) features.yml exists in project root, (2) user asks to implement/develop/build a feature, (3) user explicitly requests waterfall workflow. Creates features.yml if missing when invoked.
Chemiseblanc/ai
git-commit
Guide for breaking changes into logical, atomic commits using interactive staging. Use when committing changes that span multiple concerns, when needing to stage parts of files (hunks), when asked to create well-organized commit history, or when changes should be split into multiple commits.
Chemiseblanc/ai
software-architecture
Document software architecture using ARCHITECTURE.md and docs/*.md files with Mermaid diagrams. Use proactively when ARCHITECTURE.md exists in project root, or invoke to create initial architecture documentation. Covers system design, data flows, component relationships, and code organization with references to key entry points and abstractions.
Chemiseblanc/ai
structured-logging
Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.
Chemiseblanc/ai
tlaplus-modeling
Model and reason about concurrent or distributed systems with TLA+ and PlusCal. Use when: designing multithreaded or distributed behavior before code exists, deriving invariants from an informal design, writing TLA+ specs, creating PlusCal algorithms, model checking with TLC, organizing multi-module specifications, debugging verification failures, or reducing state space. Covers informal concurrency design, MCP tool usage, PlusCal preferred syntax (call/await over goto), TLA+ module organization, and state-space optimization.
Didn't find tool you were looking for?