PluginBench
Skill
Pass
Audit score 90

ce-commit

everyinc/compound-engineering-plugin

Create well-crafted git commits with clear, value-communicating messages following repo conventions.

What is ce-commit?

Generates a single or series of logically-grouped git commits with messages that follow your repository's established conventions (conventional commits, ticket prefixes, or custom patterns). Use this when you need to commit staged or unstaged changes with a message that clearly communicates the value and reasoning behind the change.

  • Analyzes recent commit history to detect and match your repo's message conventions automatically
  • Detects detached HEAD state and optionally creates a feature branch before committing
  • Groups related file changes into separate logical commits when appropriate
  • Stages files explicitly by name to avoid accidentally including sensitive files or unrelated changes
  • Generates commit messages in imperative mood focused on motivation and value, not just what changed
  • Confirms successful commits by running git status and reporting commit hashes

How to install ce-commit

npx skills add https://github.com/everyinc/compound-engineering-plugin --skill ce-commit
Prerequisites
  • Git repository initialized and configured
  • Current working directory is within a git repository
  • Git status shows staged or unstaged changes to commit
Claude Code
Cursor
Windsurf
Cline

How to use ce-commit

  1. 1.Gather git context (status, diff, branch, recent commits, default branch) — in Claude Code this is pre-populated
  2. 2.Determine the commit message convention by checking project docs or analyzing recent commits; defaults to conventional commits
  3. 3.Scan changed files for naturally distinct concerns and plan logical commit groups (file-level only, 2-3 commits max)
  4. 4.If on the default branch (main/master), automatically create a feature branch from the change content
  5. 5.Stage specific files by name and commit with a clear subject line and optional body explaining motivation
  6. 6.Run git status to confirm success and report the commit hash(es) and subject line(s)

Use cases

Good for
  • Committing a bug fix with a clear explanation of what was broken and how it's remedied
  • Saving a new feature with context about why it was added and how it improves the codebase
  • Creating separate commits for a refactor in one directory and a new feature in another
  • Committing changes while on the default branch (automatically creates a feature branch first)
  • Committing in a detached HEAD state with optional branch creation
Who it's for
  • Developers working in git repositories with established commit conventions
  • Teams that value clear, searchable commit history
  • Anyone committing changes that need to be understood by future readers

ce-commit FAQ

What if my repository is in a detached HEAD state?

The skill will detect this and ask whether you want to create a feature branch before committing. If you decline, it will proceed with the detached HEAD commit. If you accept, it derives a branch name from the change content and creates it automatically.

How does it choose the commit message format?

It follows this priority: (1) explicit conventions in project docs like AGENTS.md or CLAUDE.md if already loaded, (2) patterns detected in your 10 most recent commits, (3) conventional commits format (type(scope): description) as the default.

Can I split changes within a single file into separate commits?

No, the skill groups at the file level only and does not use interactive staging (git add -p). If you need to split hunks within a file, do that manually first or use git add -p separately.

What if I'm on the default branch (main or master)?

The skill automatically creates a feature branch before committing — committing directly to the default branch is not allowed. The branch name is derived from your change content.

How does it avoid committing sensitive files?

It stages specific files by name rather than using git add -A or git add ., giving you control over what gets included and reducing the risk of accidentally committing .env files or credentials.

Full instructions (SKILL.md)

Source of truth, from everyinc/compound-engineering-plugin.


name: ce-commit description: Create a git commit with a clear, value-communication message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.

Git Commit

Create a single, well-crafted git commit from the current working tree changes.

Context

On platforms other than Claude Code, skip to the "Context fallback" section below and run the command there to gather context.

In Claude Code, the five labeled sections below (Git status, Working tree diff, Current branch, Recent commits, Remote default branch) contain pre-populated data. Use them directly throughout this skill -- do not re-run these commands.

Git status: !git status

Working tree diff: !git diff HEAD

Current branch: !git branch --show-current

Recent commits: !git log --oneline -10

Remote default branch: !git rev-parse --abbrev-ref origin/HEAD 2>/dev/null || echo '__DEFAULT_BRANCH_UNRESOLVED__'

Context fallback

In Claude Code, skip this section — the data above is already available.

Run this single command to gather all context:

printf '=== STATUS ===\n'; git status; printf '\n=== DIFF ===\n'; git diff HEAD; printf '\n=== BRANCH ===\n'; git branch --show-current; printf '\n=== LOG ===\n'; git log --oneline -10; printf '\n=== DEFAULT_BRANCH ===\n'; git rev-parse --abbrev-ref origin/HEAD 2>/dev/null || echo '__DEFAULT_BRANCH_UNRESOLVED__'

Workflow

Step 1: Gather context

Use the context above (git status, working tree diff, current branch, recent commits, remote default branch). All data needed for this step is already available -- do not re-run those commands.

The remote default branch value returns something like origin/main. Strip the origin/ prefix to get the branch name. If it returned __DEFAULT_BRANCH_UNRESOLVED__ or a bare HEAD, try:

gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'

If both fail, fall back to main.

If the git status from the context above shows a clean working tree (no staged, modified, or untracked files), report that there is nothing to commit and stop.

If the current branch from the context above is empty, the repository is in detached HEAD state. Explain that a branch is required before committing if the user wants this work attached to a branch. Ask whether to create a feature branch now. Use the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_question in Antigravity CLI (agy), ask_user in Pi (requires the pi-ask-user extension). Fall back to presenting options in chat only when no blocking tool exists in the harness or the call errors (e.g., Codex edit modes) — not because a schema load is required. Never silently skip the question.

  • If the user chooses to create a branch, derive the name from the change content, create it with git checkout -b <branch-name>, then run git branch --show-current again and use that result as the current branch name for the rest of the workflow.
  • If the user declines, continue with the detached HEAD commit.

Step 2: Determine commit message convention

Follow this priority order:

  1. Repo conventions already in context -- If project instructions (AGENTS.md, CLAUDE.md, or similar) are already loaded and specify commit message conventions, follow those. Do not re-read these files; they are loaded at session start.
  2. Recent commit history -- If no explicit convention is documented, examine the 10 most recent commits from Step 1. If a clear pattern emerges (e.g., conventional commits, ticket prefixes, emoji prefixes), match that pattern.
  3. Default: conventional commits -- If neither source provides a pattern, use conventional commit format: type(scope): description where type is one of feat, fix, docs, refactor, test, chore, perf, ci, style, build.

When using conventional commits, choose the type that most precisely describes the change (the type list above). Where fix: and feat: both seem to fit, default to fix:: a change that remedies broken or missing behavior is fix: even when implemented by adding code. Reserve feat: for capabilities the user could not previously accomplish. Other types remain primary when they fit better. The user may override for a specific change.

Step 3: Consider logical commits

Before staging everything together, scan the changed files for naturally distinct concerns. If modified files clearly group into separate logical changes (e.g., a refactor in one directory and a new feature in another, or test files for a different change than source files), create separate commits for each group.

Keep this lightweight:

  • Group at the file level only -- do not use git add -p or try to split hunks within a file.
  • If the separation is obvious (different features, unrelated fixes), split. If it's ambiguous, one commit is fine.
  • Two or three logical commits is the sweet spot. Do not over-slice into many tiny commits.

Step 4: Stage and commit

If the current branch from the context above is main, master, or the resolved default branch from Step 1, automatically create a feature branch before committing. Derive the branch name from the change content, create it with git checkout -b <branch-name>, run git branch --show-current to confirm, and use the new branch as the current branch for the rest of the workflow. Do not ask whether to branch — committing on the default branch is not an option here.

Write the commit message:

  • Subject line: Concise, imperative mood, focused on why not what. Follow the convention determined in Step 2.
  • Body (when needed): Add a body separated by a blank line for non-trivial changes. Explain motivation, trade-offs, or anything a future reader would need. Omit the body for obvious single-purpose changes.

For each commit group, stage and commit in a single call. Prefer staging specific files by name over git add -A or git add . to avoid accidentally including sensitive files (.env, credentials) or unrelated changes. Use a heredoc to preserve formatting:

git add file1 file2 file3 && git commit -m "$(cat <<'EOF'
type(scope): subject line here

Optional body explaining why this change was made,
not just what changed.
EOF
)"

Step 5: Confirm

Run git status after the commit to verify success. Report the commit hash(es) and subject line(s).