commit
Create a commit following message rules and writing style guidelines
Skill by MihaiOnSoftware
Chalk Labs
Need help deploying commit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mihaionsoftware-commit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/commit
What's inside
- Skill name
commit- Description
- Create a commit following message rules and writing style guidelines
- License
- MIT
- Metadata
- category: git
- Instructions
- 101 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- good-bad-messages.md · examples/
- session.md · examples/
SKILL.md (first lines)
Read current changes and create a proper commit following commit message rules and writing style guidelines. ## What This Command Does **Input**: None (examines current git state) **Output**: A commit with a properly formatted message **Does NOT**: - Run tests - Run cleanup commands - Modify code - Stage files (assumes files are already staged or will stage all changes) ## Workflow ### Step 1: Read Rules Read `~/.ai/rules/6_writing_style.md` for writing style guidelines. Apply these commit message rules: - Only mention things that are different from the last commit - Do not mention intermediary steps or changes that were added and then removed within the same commit session - Focus on the final state, not the process of getting there - Keep explanation of what was done short, quick, and direct - Only add additional context beyond the first line if explaining why or if something is not easily inferred from the code ### Step 2: Examine Changes Run these git commands to understand what's being committed: 1. **Check status**: `git status` - See what files are staged/unstaged - Understand overall scope of changes 2. **View diff**: `git diff HEAD` or `git diff --cached` (if files are staged) - See actual changes being committed - Understand what was added, modified, or removed 3. **Check recent commits**: `git log -3 --oneline` - Understand commit message style in this repo - See what's been done recently for context ### Step 3: Determine What to Stage **If files are already staged**: - Use staged files as-is **If no files are staged**: - Stage all modified/new files: `git add -A` ### Step 4: Draft Commit Message Following the commit message rules above and `6_writing_style.md`: **Structure**: ``` [First line: concise description of what changed] [Optional body: additional context if needed] ``` **Rules to follow**: - **First line**: Short, direct, describes final state (not process) - **Active voice**: "Add feature" not "Added feature" or "Feature was added" - **Focus on what changed**: Only mention differences from last commit - **No process details**: Don't mention "first tried X, then Y" - **Simple language**: Use common words, be direct (per `6_writing_style.md`) - **No buzzwords**: No corporate speak or passive voice - **Body optional**: Only add if explaining why or if not easily inferred ### Step 5: Create Commit Create the commit using heredoc format for proper formatting: ```bash git commit -m "$(cat <<'EOF' [Commit message first line] [Optional body] EOF )" ``` ## Anti-Patterns to AVOID **DO NOT**: - Make commits without examining the actual changes - Write vague messages like "update files" or "fix issues" - Bypass pre-commit hooks with `--no-verify`. If a hook fails, fix the cause (run the formatter/linter, e.g. `yarn purtyhere`) and commit again. See `~/.ai/rules/10_commit_standards.md`. For message-style rules (active voice, no buzzwords, focus on final state, etc.) trust the commit message rules and `~/.ai/rules/6_writing_style.md` — already covered in Step 1 — instead of restating them here. For a worked example session, see [examples/session.md](examples/session.md). For good and bad commit message examples, see [examples/good-bad-messages.md](examples/good-bad-messages.md).
From MihaiOnSoftware/.ai, MIT.
More from MihaiOnSoftware/.ai
- 0.592score
mihai-code-review
MihaiOnSoftware
Review a PR, branch, or diff the way Mihai would: mechanical style/test sweeps first, then precedent diffing, then an adversarial correctness hunt.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
shape-review-comments
MihaiOnSoftware
Shapes raw review findings into postable file:line comments written in Mihai's voice.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
review-pipeline
MihaiOnSoftware
Parallel code review pipeline: run adversarial-review-loop and mihai-code-review simultaneously, merge their findings, shape into postable comments, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
monitor-gh-pr
MihaiOnSoftware
Monitor a GitHub PR for CI failures, CI success, and new comments (including inline review comments).
SkillAFreshness: A★ 1Claude Code +9 - 0.502score
adversarial-review-loop
MihaiOnSoftware
Run fresh adversarial subagent, incorporate findings, repeat until findings are weak/repeated/invalid.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
create-implementation-plan
MihaiOnSoftware
Break a large task into incremental slices using story splitting patterns.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
adversarial-review
MihaiOnSoftware
Spawn a fresh-context subagent that is told a mistake exists in your work and tasked with finding it.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
solve-this-problem
MihaiOnSoftware
End-to-end: problem → design → plan → TDD slices.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
tdd-slice
MihaiOnSoftware
Implement a complete TDD slice with multiple micro-tdd cycles and validation
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
explore-and-design
MihaiOnSoftware
Investigate, scope, and shape a solution before breaking it into implementation slices.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
write-validation-report
MihaiOnSoftware
Write a validation report with pass/fail verdict
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
write-agent-report
MihaiOnSoftware
Write an agent report with proper naming and location
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 13, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MihaiOnSoftware/.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MihaiOnSoftware
- 0.592score
shape-review-comments
MihaiOnSoftware
Shapes raw review findings into postable file:line comments written in Mihai's voice.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
review-pipeline
MihaiOnSoftware
Parallel code review pipeline: run adversarial-review-loop and mihai-code-review simultaneously, merge their findings, shape into postable comments, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
mihai-code-review
MihaiOnSoftware
Review a PR, branch, or diff the way Mihai would: mechanical style/test sweeps first, then precedent diffing, then an adversarial correctness hunt.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
monitor-gh-pr
MihaiOnSoftware
Monitor a GitHub PR for CI failures, CI success, and new comments (including inline review comments).
SkillAFreshness: A★ 1Claude Code +9 - 0.502score
adversarial-review-loop
MihaiOnSoftware
Run fresh adversarial subagent, incorporate findings, repeat until findings are weak/repeated/invalid.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
create-implementation-plan
MihaiOnSoftware
Break a large task into incremental slices using story splitting patterns.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get commit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
commit skill. Agent Mart. https://agentmart.dev/skills/mihaionsoftware-commit (last updated 2026-10-24)