commit
- Repo stars 1,537
- Author updated Live
- Author repo cafe-hass
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @FezVrasta · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: commit
description: Create a git commit. Always use this skill when the user asks to commit changes. Runs linting, t…
category: engineering
runtime: no special runtime
---
# commit output preview
## PART A: Task fit
- Use case: Create a git commit. Always use this skill when the user asks to commit changes. Runs linting, type checking, and formatting checks before committing to ensure all quality gates pass..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Step 1: Run quality checks / Step 2: Fix all issues / Step 3: Create the commit” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Create a git commit. Always use this skill when the user asks to commit changes. Runs linting, type checking, and formatting checks before committing to ensure all quality gates pass.”.
- **02** When the source has headings, the agent prioritizes “Step 1: Run quality checks / Step 2: Fix all issues / Step 3: Create the commit” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Step 1: Run quality checks / Step 2: Fix all issues / Step 3: Create the commit”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: commit
description: Create a git commit. Always use this skill when the user asks to commit changes. Runs linting, t…
category: engineering
source: FezVrasta/cafe-hass
---
# commit
## When to use
- Create a git commit. Always use this skill when the user asks to commit changes. Runs linting, type checking, and form…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Step 1: Run quality checks / Step 2: Fix all issues / Step 3: Create the commit” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "commit" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Step 1: Run quality checks / Step 2: Fix all issues / Step 3: Create the commit
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}The user wants to commit changes. Before creating any git commit, you MUST run all quality checks and fix any issues found. Follow these steps in order:
Step 1: Run quality checks
Run all checks in parallel:
yarn lint:biome --fix
yarn typecheck
yarn format:check --fix
yarn testStep 2: Fix all issues
If any check fails:
- Lint errors: Run
yarn lint:biome --fixto auto-fix, then manually fix remaining issues - Type errors: Fix TypeScript errors in the affected files
- Formatting: Run
yarn format(i.e.yarn format:check --fix) to auto-format all files
Re-run the failing checks after fixing until they all pass. Do NOT proceed to commit until every check passes with zero errors.
Step 3: Create the commit
Only after all checks pass, follow the standard commit process:
- Run
git statusandgit diffto review changes - Stage the relevant files with
git add <specific files> - Write a clear commit message following the existing style
- Create the commit using a heredoc for the message:
git commit -m "$(cat <<'EOF'
<message here>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
EOF
)"- Run
git statusto confirm the commit succeeded.
IMPORTANT: Never use --no-verify or skip hooks. Never commit if any lint, typecheck, or format check is failing.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review