Commit working changes as small, reviewable conventional commits. Use when asked to commit, and at the end of any task before opening a PR.
Scanned 9/4/2026
Install to Claude Code
npx -y skills add chrille0313/agentic-monorepo-template --skill commit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Commit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/chrille0313-commit)More formats (shields.io, HTML) on the badges page.
---
name: commit
description: Commit working changes as small, reviewable conventional commits. Use when asked to commit, and at the end of any task before opening a PR.
---
Commit the relevant working changes as small, modular commits: one logical change each. Concerns a reviewer reads differently (behavior, refactors, tests, docs, config) get their own commits when separable. Each commit contains only what belongs to it; unrelated leftovers stay out of the series entirely (mention them instead).
Messages follow conventional commits (CI enforces the format). The title says **what** changed; the body says **why**: the intent or the problem being solved, never a summary of the diff.
Good:
```
feat(auth): add session timeout
Users stayed logged in indefinitely, a security risk on shared
devices. Sessions now expire after 24h of inactivity.
```
Bad: a body that restates what the diff already shows ("added a timeout and updated the hooks"), or says nothing ("fix: fix bug").
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...