/commit-msg
Draft a Conventional Commit message for staged changes. Analyzes diffs, classifies change type, and formats scope/body.
$ npx -y skills add athola/claude-night-market --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/commit-msg
Context preview
What this command does when you run it.
Draft a Conventional Commit message for staged changes. Analyzes diffs, classifies change type, and formats scope/body.
Command definition
commit-msg.mddescription: Draft a Conventional Commit message for staged changes. Analyzes diffs, classifies change type, and formats scope/body.
model_hint: fast
Draft a Conventional Commit Message
Run these git commands to gather context, then draft the message.
Steps
1. **Gather context** (run in parallel):
- `git status -sb`
- `git diff --cached --stat`
- `git diff --cached`
- `git log --oneline -5`
2. **If nothing is staged**, tell the user and stop.
3. **Classify the change**: Pick a type from `feat`, `fix`, `docs`, `refactor`, `test`, `chore`, `style`, `perf`, `ci`. Pick an optional scope from the changed directory or module.
4. **Draft the message** in this format:
<type>(<scope>): <imperative summary, ≤50 chars>
<body: what and why, wrapped at 72 chars>
<footer: BREAKING CHANGE or issue refs, if any>
5. **Slop check**: the message must NOT contain: leverage, utilize, seamless, comprehensive, robust, facilitate, streamline, delve, multifaceted, pivotal, intricate, optimize, nuanced, furthermore, moreover, revolutionize, elevate, unlock, "it's worth noting", "at its core", "in essence", "a testament to"
If found, replace with plain words (use, smooth, complete, solid, enable, simplify, improve, explore, varied, key, detailed).
5a. **Character-level slop check**: load `shared/output-hygiene.md` (Contract A) and strip these from the message. Inline fallback if that module is absent:
- `"+"` used as a prose conjunction becomes `and`
(`parser + validator` becomes `parser and validator`). Keep `+` in version strings, math, and code.
- em-dash `—` becomes a colon, period, comma, or a rewrite.
- `--` used as prose punctuation becomes a colon or a rewrite.
- arrows `->` and `→` used as connectors become `to` or `into`.
- smart quotes `“ ” ‘ ’` become straight `"` and `'`.
5b. **Subject-matter check** (Contract B): describe the change by its reader-facing effect. Name neither the AI origin nor the specific marker removed. Do NOT write `remove AI slop`, `de-slop`, `AI-generated content`, `AI phrasing`, `replace em-dashes`, `remove smart quotes`, or similar. Test: if the subject only makes sense as "I cleaned up AI output", rewrite it. For example `docs: clarify the setup section`, not `style: replace em-dashes with colons`.
6. **Write** the message to `./commit_msg.txt` and preview it.
Rules
- **NEVER** use `git commit --no-verify` or `-n`.
- Write for humans. "fix auth bug" beats "streamline authentication
optimization."
Read more
description: Draft a Conventional Commit message for staged changes. Analyzes diffs, classifies change type, and formats scope/body. model_hint: fast
Draft a Conventional Commit Message
Run these git commands to gather context, then draft the message.
Steps
1. **Gather context** (run in parallel):
- `git status -sb`
- `git diff --cached --stat`
- `git diff --cached`
- `git log --oneline -5`
2. **If nothing is staged**, tell the user and stop.
3. **Classify the change**: Pick a type from `feat`, `fix`, `docs`, `refactor`, `test`, `chore`, `style`, `perf`, `ci`. Pick an optional scope from the changed directory or module.
4. **Draft the message** in this format:
<type>(<scope>): <imperative summary, ≤50 chars> <body: what and why, wrapped at 72 chars> <footer: BREAKING CHANGE or issue refs, if any>
5. **Slop check**: the message must NOT contain: leverage, utilize, seamless, comprehensive, robust, facilitate, streamline, delve, multifaceted, pivotal, intricate, optimize, nuanced, furthermore, moreover, revolutionize, elevate, unlock, "it's worth noting", "at its core", "in essence", "a testament to"
If found, replace with plain words (use, smooth, complete, solid, enable, simplify, improve, explore, varied, key, detailed).
5a. **Character-level slop check**: load `shared/output-hygiene.md` (Contract A) and strip these from the message. Inline fallback if that module is absent:
- `"+"` used as a prose conjunction becomes `and`
(`parser + validator` becomes `parser and validator`). Keep `+` in version strings, math, and code.
- em-dash `—` becomes a colon, period, comma, or a rewrite.
- `--` used as prose punctuation becomes a colon or a rewrite.
- arrows `->` and `→` used as connectors become `to` or `into`.
- smart quotes `“ ” ‘ ’` become straight `"` and `'`.
5b. **Subject-matter check** (Contract B): describe the change by its reader-facing effect. Name neither the AI origin nor the specific marker removed. Do NOT write `remove AI slop`, `de-slop`, `AI-generated content`, `AI phrasing`, `replace em-dashes`, `remove smart quotes`, or similar. Test: if the subject only makes sense as "I cleaned up AI output", rewrite it. For example `docs: clarify the setup section`, not `style: replace em-dashes with colons`.
6. **Write** the message to `./commit_msg.txt` and preview it.
Rules
- **NEVER** use `git commit --no-verify` or `-n`.
- Write for humans. "fix auth bug" beats "streamline authentication
optimization."
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Other commands on claude-night-market.
- /aggregate-logs
Generate LEARNINGS.md from skill execution logs.
Open command - /analyze-skill
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Open command - /bulletproof-skill
Harden skills against rationalization and bypass behaviors
Open command - /context-report
Generate context optimization report for skill directories
Open command - /create-command
Create slash commands with brainstorming and best practices
Open command - /create-hook
Create hooks with brainstorming and security-first design
Open command

