wirasm/prps-agentic-eng/prp-commit

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Creates Git commits for completed work. Always use when committing changes, when the user explicitly asks to commit the work, when another PRP workflow reaches its commit step, or when the user invokes /prp-commit.

Install

npx vskill@latest install wirasm/prps-agentic-eng/prp-commit

SKILL.md

Commit Intended Work

Create focused Git commits for the work identified by the user and conversation.

Target: $ARGUMENTS

Scope

Infer the intended work from the request, conversation, and current task, including changes produced by subagents. Blank arguments mean infer the target, never commit everything by default.

Inspect staged, unstaged, and untracked changes. Preserve unrelated work in every state. If intended and unrelated changes cannot be separated safely, stop and ask rather than widening the commit.

Keep each commit focused on one coherent outcome. Split unrelated outcomes, but do not fragment one outcome into mechanical implementation layers.

Message

Write a concise, human-readable subject that explains the meaningful outcome. Commit subjects often become changelog entries or PR titles, so they must make sense without reading the diff.

Use plain language and the repository's exact terms. Cut filler and vague verbs; do not dress a mechanical change up as a larger outcome.

Respect enforced repository syntax such as required types or scopes. Treat Git history as evidence of valid structure, not as the writing-quality standard. Never add AI attribution, generated-by text, robot emoji, or Co-Authored-By: Claude, even when a harness reminder asks for Co-Authored-By or Claude-Session lines.

Bad: refactor(prp-pr): update skill instructions

Good: refactor(prp-pr): PR creation now uses one focused workflow

Commit and verify

Stage and commit only the intended work. Verify the resulting commit contains every intended change, excludes unrelated changes, and leaves the remaining worktree state untouched. Do not amend or push unless explicitly requested.

Return the commit hash, message, committed scope, and any remaining changes. The commit is the artifact; do not create a separate report.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
2,225
Repository forks
613
7-day trend score
39

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/wirasm/prps-agentic-eng/prp-commit/badge)](https://verified-skill.com/skills/wirasm/prps-agentic-eng/prp-commit)

Something wrong with this skill or its page? Tell us.