Commit Message Generator

VerifiedSafe

Analyze staged changes and generate conventional commit messages. Supports Conventional Commits, GitHub-style, and custom formats.

Sby Skills Guide Bot
DevelopmentBeginner
7/22/2026
Claude CodeCursorWindsurfCopilotCodex
#git#commit-messages#conventional-commits#version-control#code-review

Recommended for

Automated summary

Analyzes staged or unstaged Git changes and proposes structured commit messages in Conventional Commits style, with concise, standard, or detailed variants.

Strengths

  • Explicit mapping of commit types (feat, fix, refactor, perf, docs, etc.) with clear formatting rules (imperative mood, 72 characters)
  • Suggests splitting into multiple commits when staged changes span several concerns, including the git commands to run
  • Also supports drafting PR descriptions and reviewing a branch's commit history for consistency
  • Flags sensitive changes (secrets, auth) in the footer and never auto-commits without user confirmation

Limitations

  • Relies entirely on git diff/git log output, so it is useless outside a repository with real changes
  • Beyond 20 files it only recommends a descriptive PR instead of proposing a message
  • Does not validate the correctness of the changes, only their formatting and categorization
When to use it

Use it when you need a clean commit message fast, want to split a large change into logical commits, or are writing a pull request description.

When not to use it

Avoid it if you need an in-depth code review or verification of the changes themselves, which this skill does not perform.

Security analysis

Safe
Quality score86/100

The skill is purely a commit-message helper built on standard read-only git inspection commands. The only state-changing commands (`git reset HEAD`, `git add`, `git commit`) are shown as suggestions and explicitly gated by a 'never auto-commit without confirmation' constraint. No exfiltration, obfuscation, or destructive behavior is present, so listing it is low risk.

Findings
  • •No allowed-tools declared, yet instructions direct the agent to run shell git commands (`git diff --cached`, `git diff`, `git status`, `git log`) — read-only, low risk.
  • •Step 4 suggests `git reset HEAD` followed by selective `git add`/`git commit`; this mutates repo/index state, though it is presented as commands for the user to run and the Constraints section forbids auto-committing without confirmation.
  • •No network calls, no credential/secret access, no obfuscated payloads, no destructive filesystem operations.
How this analysis is made

Examples

Basic commit message
Generate a commit message for my staged changes.
Split a large change
Commit this — but the staged changes touch auth, the API and dependencies, so suggest how to split them into separate commits.
PR description
Write a PR description for this branch: run git log --oneline origin/main..HEAD and summarize the changes.

Commit Message Generator

Description

Analyze staged changes and generate conventional commit messages. Supports Conventional Commits, GitHub-style, and custom formats. Can also review existing commit history for consistency.

Triggers

  • "Generate commit message", "Write commit message", "Commit this"
  • "What should I commit?", "Review my changes"
  • "Commit message for this PR", "Squash and rewrite commits"

Instructions

Step 1: Analyze Changes

  1. Run git diff --cached to see staged changes
  2. If nothing staged, run git diff and git status to show unstaged changes
  3. For PR reviews, use git log --oneline origin/main..HEAD to see all commits

Step 2: Categorize Changes

Map changes to conventional commit types:

  • feat: New feature, new API endpoint, new component
  • fix: Bug fix, error handling, edge case
  • refactor: Code restructure without behavior change
  • perf: Performance improvement
  • docs: Documentation only
  • style: Formatting, whitespace, semicolons
  • test: Adding/updating tests
  • chore: Build, CI, dependencies, tooling
  • ci: CI/CD configuration changes
  • revert: Reverting a previous commit

Step 3: Generate Message

Format (Conventional Commits):

<type>(<scope>): <subject>

<body>

<footer>

Rules:

  • Subject: imperative mood, lowercase, no period, max 72 chars
  • Body: explain what and why, not how, wrap at 72 chars
  • Footer: breaking changes (BREAKING CHANGE:), issue refs (Closes #123)
  • If multiple unrelated changes, suggest splitting into separate commits

Step 4: Multi-commit Suggestion

If staged changes span multiple concerns:

Suggested split:
1. feat(auth): add OAuth2 login flow
2. fix(api): handle null response in user endpoint
3. chore(deps): update axios to 1.7.0

Run these commands:
  git reset HEAD
  git add src/auth/oauth.py
  git commit -m "feat(auth): add OAuth2 login flow"
  git add src/api/users.py
  git commit -m "fix(api): handle null response in user endpoint"
  git add package.json package-lock.json
  git commit -m "chore(deps): update axios to 1.7.0"

PR Description Mode

When asked to write a PR description:

  1. Read all commits in the branch
  2. Categorize by type
  3. Generate:
    • Summary (2-3 sentences)
    • Changes (grouped by category)
    • Testing notes
    • Breaking changes (if any)
    • Checklist

Output Format

Provide 3 options: concise (subject only), standard (subject + body), detailed (subject + body + footer). Default to standard unless user specifies otherwise.

Constraints

  • Never auto-commit without user confirmation
  • For sensitive changes (secrets, auth), add a warning in the footer
  • If changes are too large (>20 files), suggest a descriptive PR instead

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/commit-message-generator-mrwakbww/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/commit-message-generator-mrwakbww' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/commit-message-generator-mrwakbww/download' --output '.skill-downloads/commit-message-generator-mrwakbww/SKILL.md.part' && mv '.skill-downloads/commit-message-generator-mrwakbww/SKILL.md.part' '.skill-downloads/commit-message-generator-mrwakbww/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/commit-message-generator-mrwakbww/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills