Create concise commit messages from a code diff, a file list, or a description of changes. The skill selects one emoji that matches the change’s purpose, follows gitmoji conventions, and explains the choice without running Git commands.
Generates commit messages following the gitmoji convention (https://gitmoji.dev) — picks the right emoji for the intent of the change and writes a well-formed message. Use when asked to "write a gitmoji commit", "add an emoji to my commit message", "which gitmoji should I use", "gitmoji this change", or when a project uses gitmoji-style commit messages. Works from a git diff, staged changes, or a plain description of the change. Generates the message only — does not run git commands.
Review the instructions the agent will receive before you install.
Generates commit messages that follow the gitmoji convention: every commit starts with an emoji that identifies the intent of the change at a glance. Given a diff, a list of staged files, or a plain description of a change, this skill picks the single most appropriate gitmoji and writes a concise, well-formed commit message around it.
This skill only generates the message — it never runs git commit or any other git command. The output is a copyable message for the user to use.
When not to use: if the project follows plain Conventional Commits (feat:, fix:, ...) without emojis, use the conventional-commit or commit-message-storyteller skill instead. If unsure which convention the project uses, ask the user to provide recent commit history (for example, the output of git log --oneline -10).
The gitmoji specification:
<intention> [scope?][:?] <message>
Examples:
✨ add multi-tenant support to the billing service
🐛 (auth) prevent token refresh loop on expired sessions
♻️ (api): extract pagination logic into shared helper
Gitmoji supports two equivalent notations:
| Style | Example | When to prefer |
|---|---|---|
| Unicode | ✨ add dark mode | Default — renders everywhere, shorter subject line |
| Shortcode | :sparkles: add dark mode | Platforms that render shortcodes (GitHub, GitLab) or teams that grep commit logs by code |
Match the repository's existing history. If recent commits use :sparkles:-style shortcodes, generate shortcodes; otherwise default to unicode emojis.
Work from whatever the user provides:
If the intent is genuinely ambiguous (e.g. "updated auth.js" could be a fix, a feature, or a refactor), ask one short clarifying question rather than guessing.
Determine the primary purpose of the change. Common intents and their gitmojis:
| Emoji | Shortcode | Intent |
|---|---|---|
| ✨ | :sparkles: | Introduce new features |
| 🐛 | :bug: | Fix a bug |
| 🚑️ | :ambulance: | Critical hotfix |
| 📝 | :memo: | Add or update documentation |
| ♻️ | :recycle: | Refactor code (no behavior change) |
| ✅ | :white_check_mark: | Add, update, or pass tests |
| ⚡️ | :zap: | Improve performance |
| 🎨 | :art: | Improve structure / format of the code |
| 🔥 | :fire: | Remove code or files |
| 🔒️ | :lock: | Fix security or privacy issues |
| ⬆️ | :arrow_up: | Upgrade dependencies |
| 🔧 | :wrench: | Add or update configuration files |
| 💄 | :lipstick: | Add or update the UI and style files |
| 💥 | :boom: | Introduce breaking changes |
| 🚨 | :rotating_light: | Fix compiler / linter warnings |
| 🌐 | :globe_with_meridians: | Internationalization and localization |
This is only the most common subset — always consult references/gitmoji-reference.md for the full official list of 75 gitmojis before settling on one; a more specific emoji often exists (e.g. 🩹 for a trivial fix, ✏️ for a typo, 🚚 for a file move).
Rules for ambiguous cases:
Produce the commit message in a copyable code block, followed by one line explaining why that gitmoji was chosen. Do not execute git commit.
Example output:
🐛 (auth) prevent token refresh loop on expired sessions
Expired sessions triggered a refresh that failed validation and
re-triggered itself, crashing the app. A recursion guard now aborts
the cycle and returns a clean 401.
Why 🐛: the change corrects incorrect runtime behavior — a bug fix, not urgent enough for 🚑️.
| Situation | How to Handle |
|---|---|
| Mixed changes (e.g. feature + refactor in one diff) | Pick the emoji for the dominant intent, and suggest splitting into separate commits if the concerns are unrelated |
| Breaking change | Use 💥 as the intention and describe the break in the body |
| Revert | ⏪️ with a subject referencing the reverted commit |
| Merge commit | 🔀 merge branch '<name>' into <target> |
| Initial commit | 🎉 begin project |
| Work in progress | 🚧 with a clear note of what remains |
| No matching emoji feels right | Re-scan the full reference; if still nothing fits, fall back to the closest generic intent (✨, 🐛, or ♻️) |
# Get your staged diff to paste into Copilot
git diff --staged
# Check which emoji style the repo already uses
git log --oneline -10
See references/gitmoji-reference.md for the complete official gitmoji list.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Map an existing codebase into seven documents covering its technology, structure, architecture, conventions, integrations, tests, and concerns. Link findings to file evidence, mark unknowns, and highlight differences between stated plans and the actual implementation.
Assess a repository’s readiness for AI agents with AgentRC and generate a standalone HTML dashboard. Review scores across nine areas, see prioritized improvements, and optionally apply scoring policies tailored to an organization.
Generate coding agent instruction files from a project's actual code using AgentRC. Capture detected languages, frameworks, and conventions in one shared file or split rules by topic and project area, with a preview before writing.
Customize AgentRC readiness assessments to match team or organization standards. Choose or create policies that adjust check importance, disable irrelevant checks, set pass thresholds, and define requirements for automated checks in CI workflows.
Analyze supplied ad performance data to identify wasted spend, strong campaigns, and next tests. Compare channels, assess whether test differences are meaningful, and produce budget reallocation recommendations with a prioritized action plan.
Turn code files into learning resources by adding comments that explain syntax, programming concepts, and design choices. Adjust explanation depth and repetition to the reader’s knowledge while preserving file structure, encoding, and syntax.