Skip to content
Development
Skill

/commit-messages

Generates conventional commit messages from staged changes. Use when committing and needing a well-formatted message. Do not use for full PR prep; use pr-prep.

From plugin
claude-night-market
337200 skills59 agents162 commands1 MCP
Install
$ npx -y skills add athola/claude-night-market --skill commit-messages --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/commit-messages

Context preview

The summary Claude sees to decide when to auto-load this skill.

Generates conventional commit messages from staged changes. Use when committing and needing a well-formatted message. Do not use for full PR prep; use pr-prep.

SKILL.md

commit-messages.SKILL.md
name: commit-messages
description: Generates conventional commit messages from staged changes. Use when committing and needing a well-formatted message. Do not use for full PR prep; use pr-prep.
alwaysApply: false
category: artifact-generation
tags:
- git
- commit
- conventional-commits
tools: []
complexity: low
model_hint: fast
estimated_tokens: 350

Conventional Commit Workflow

When To Use

  • Generating conventional commit messages from staged changes

When NOT To Use

  • Full PR preparation: use sanctum:pr-prep
  • Amending existing commits: use git directly

Steps

1. **Gather context** (run in parallel):

  • `git status -sb`
  • `git diff --cached --stat`
  • `git diff --cached`
  • `git log --oneline -5`
  • When sem is available (see `leyline:sem-integration`):

`sem diff --staged --json` for entity-level changes

If nothing is staged, tell the user and stop.

When sem output is available, use entity names (function, class, method) in the commit subject and body instead of parsing raw diff hunks. For example, "add function validate_webhook_url" instead of "add validation logic to notify.py".

2. **Classify**: Pick type (`feat`, `fix`, `docs`, `refactor`, `test`, `chore`, `style`, `perf`, `ci`) and optional scope.

3. **Draft the message**:

  • **Subject**: `<type>(<scope>): <imperative summary>` (50 chars max)
  • **Body**: What and why, wrapped at 72 chars
  • **Footer**: BREAKING CHANGE, issue refs, and the

discussion trailer below

3a. **Discussion trailer**: when the change resolves a finding from the Discussions board, add a trailer on its own line:

   Addresses-Discussion: #654
   Addresses-Discussion: #604, #610

This is the only signal `scripts/reconcile_discussions.py` accepts as proof a finding is done. It posts the resolution comment and closes the discussion, so the board stops carrying work that is already finished.

**Only add it when this commit resolves the finding.** Prose that merely names a discussion is read as a mention and is never written back. That distinction is load-bearing: `6b28aa1a` says "posted 13 insights to discussions #424-#436", which is the commit that *opened* those discussions. A trailer there would have announced "Addressed" on findings nobody had looked at yet.

Cite a discussion in the body for context as often as it helps. Reserve the trailer for resolution.

4. **Slop check**: reject these words and replace with plain alternatives:

| Reject | Use instead | |--------|-------------| | leverage, utilize | use | | seamless | smooth | | comprehensive | complete | | robust | solid | | facilitate | enable | | streamline | simplify | | optimize | improve | | delve | explore | | multifaceted | varied | | pivotal | key | | intricate | detailed |

Also reject: "it's worth noting", "at its core", "in essence", "a testament to"

4a. **Character-level slop check**: load `shared/output-hygiene.md` (Contract A) and strip these markers. Inline fallback if that module is absent:

| Marker | Replace with | |--------|--------------| | `"+"` as a prose conjunction | `and` (keep `+` in versions/code) | | em-dash `—` | colon, period, comma, or rewrite | | `--` as prose punctuation | colon or rewrite | | arrows `->` / `→` as connectors | `to` / `into` | | smart quotes `“ ” ‘ ’` | straight `"` and `'` |

4b. **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`, or `remove smart quotes`. 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`.

5. **Write** to `./commit_msg.txt` and preview.

Rules

  • NEVER use `git commit --no-verify` or `-n`
  • Write for humans, not to impress
  • If pre-commit hooks fail, fix the issues
  • This skill drafts a message, it does not commit. Whoever commits

confirms HEAD advanced (`git rev-parse HEAD` before and after) before reporting the commit as landed. An auto-fixing hook aborts the commit while printing a tail that reads like success, so hook output is not evidence. See discussion #614.

Exit Criteria

  • [ ] `commit_msg.txt` written to the working directory containing

the drafted conventional commit message

  • [ ] Subject line follows `<type>(<scope>): <summary>` format and

is at most 50 characters

  • [ ] Slop word check passes: none of the banned words (leverage,

utilize, seamless, comprehensive, robust, etc.) appear in the message

  • [ ] Character-level check passes: no em-dashes, no `+` as prose

conjunction, no smart quotes, no `->` as prose connector

  • [ ] If nothing is staged, skill halts immediately and reports

"nothing staged" without producing a commit message

Read more
Ships withclaude-night-market

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.

Get the whole plugin

Other skills on claude-night-market.