Commit

Community

elianiva

commit

Conventional commit message generator for jj and git repos. Analyzes diffs and produces scoped, well-formed commit messages. Use whenever the user says "commit", "make a commit", "write commit message", or similar.

Overview

Publisher	elianiva
Repository	`dotfiles`
Skill name	`commit`
Stars	204
Forks	9
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by elianiva on GitHub. Read the source before you install it.

Installation

Install the Commit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/elianiva/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/agents/skills/commit .claude/skills/commit

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Commit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Commit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Commit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Commit Skill

Commit based on previous conversation if there's any, otherwise check the diff.

Detection

bash
# returns "jj" or "git"
which jj 2>/dev/null && jj root 2>/dev/null && echo "jj" || (git rev-parse --show-toplevel 2>/dev/null && echo "git")

Prefer jj if both work — it's the user's primary VCS.

jj

Check state

bash
jj status           # changed files
jj diff             # full diff
jj diff <file>      # specific file

Commit (set message on working copy)

bash
jj describe -m "<type>(<scope>): <subject>"

With body:

bash
jj describe -m "$(cat <<'EOF'
<type>(<scope>): <subject>

<body>
EOF
)"

Drop unrelated files before committing

bash
jj restore --from @- <file1> <file2>

Git

bash
git status                       # check state
git diff HEAD                    # all changes
git add <file>                   # stage
git commit -m "<type>(<scope>): <subject>"
git commit -m "$(cat <<'EOF'
<type>(<scope>): <subject>

<body>
EOF
)"

Conventional Commit Format


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

<body>

Types: feat fix refactor perf style test docs chore revert

Scope: module changed, 1-2 words

Subject: imperative, no period, ≤72 chars

Body (optional): what and why, not how (diff shows how)

Breaking: add ! after type — feat!(api): change pagination response

Writing the Message

Read jj diff / git diff — understand every change
Identify primary intent — feat? fix? refactor?
Pick type + scope from that
Skim each hunk — if any doesn't serve the primary intent, flag it
Write imperative subject — "add X", "remove Y", "fix Z in W"
Body only when why isn't obvious — platform quirk, perf trade-off, migration step

Examples

✅ Right

Change	Message
New API route	`feat(flights): add GET /api/flights/:id`
Modal bug	`fix(responsive-modal): stop blurring select on mobile after scroll`
Rename function	`refactor(utils): rename fetchWrapper to useFetchWrapper`
Bump dep	`chore(deps): bump radix-ui/react-select to 2.2.6`
Remove dead code	`chore(auth): remove legacy session shim`
Perf	`perf(table): memoize row renderer`
Breaking change	`refactor!(db): drop legacy fuel_storage table`

❌ Wrong

Message	Why
`fix: fix bug`	Zero info
`fixed the modal`	Past tense, no scope
`fix(modal):fixed`	Missing space after colon
`feat(auth): add login page with form validation, error handling, remember-me, password reset, OAuth buttons`	Subject >72 chars
`fix(cache): change gcTime from 5min to 30min in queryClient config`	Describes how (diff shows it), not why
`✨ feat(ui): add spinner`	Emojis are noise in terminal
`fix #1234`	No description
`Bump lodash to 4.17.21 (#4567)`	GitHub auto-suffix noise

Rules

One logical change per commit — drop unrelated files before committing
Don't commit stray pnpm-lock.yaml — restore them out unless the change intentionally modifies deps
Don't use git add . / jj restore blindly — check what's in working copy first
Don't write subjects longer than 72 chars — body exists for details
Don't omit scope — fix: ... is ambiguous, fix(tooltip): ... is not
Don't use chore: wip — either write a meaningful subject or leave undescribed

Frequently asked questions

What does the Commit AI skill do?

Why use Commit on TypingMind?

Because you install it once and use it with any model. Commit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Commit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/elianiva/dotfiles/tree/master/agents/skills/commit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Commit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Commit?

As many as you like. As long as a model supports skills, you can use Commit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Commit AI skill free?

It is published on GitHub by elianiva. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Writing Plans

obra

CommunityPopular

Use when you have a spec or requirements for a multi-step task, before touching code

Ask Matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

Code Review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what…

Codebase Design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Commit Skill

Detection

jj

Check state

Commit (set message on working copy)

Drop unrelated files before committing

Git

Conventional Commit Format

Writing the Message

Examples

✅ Right

❌ Wrong

Rules

Frequently asked questions

Related AI Skills

Set up your own AI workspace now