greenfield-inc/pane/refactor-apply
Claude Code and agent skill by greenfield-inc/pane
- community
Checking that the SKILL.md file is still in the repository.
Applies a refactor plan written by refactor-simple, refactor-deep, or the refactor orchestrator's merged report - auto-fixable items first, then manual items one at a time with the user, verifying with the repo's own checks after each group. Use only after the user has reviewed the plan and said to apply it.
Install
npx vskill@latest install greenfield-inc/pane/refactor-applySKILL.md
Refactor Apply
Turns a reviewed plan into edits. Never runs unasked; the plan it consumes was shown to the user first, by refactor or by the user invoking an analysis directly.
Input
One plan file: an individual ./tmp/simple-refactor-plan-*.md or ./tmp/deep-refactor-plan-*.md, or the orchestrator's ./tmp/refactor-merged-*.md. All three share the same shape - Critical / Warning / Info sections, each item with file:line, a fix, and an Auto-fixable: Yes/No flag.
Process
1. Read the plan and the repo's checks
Parse every item. Then find what "passing" means in this repository - its lint, typecheck, and test commands from package.json, Makefile, CLAUDE.md or AGENTS.md. Run them once before touching anything so a pre-existing failure is not mistaken for one you caused.
2. Auto-fixable first
Apply every Auto-fixable: Yes item, grouped by file. Rules:
- Change only the lines the finding names and what the fix strictly requires.
A refactor pass does not widen a PR's scope.
- Never alter behaviour to satisfy a convention; if a fix would, it is not
auto-fixable - move it to manual and say why.
- After the group, run the repo's checks. Fix straightforward failures you
introduced; revert an item you cannot make pass and report it.
--auto-only stops here with a summary.
3. Manual, one at a time with the user
For each Auto-fixable: No item, in plan priority order - Critical first: state the finding, the proposed change, and any judgment call it needs; wait for the user's answer; apply; run the checks. The user may skip any item; a skipped Critical is recorded, not argued.
4. Report
Do not commit. The user (or prepare-pr) owns the commit, and the diff should be reviewable as its own step.
Rules
- No blanket rewrites; every edit traces to a plan item.
- Behaviour-preserving only. If a change would alter behaviour, it needs the
user's explicit yes and a test.
- Pre-existing debt marked "not against this PR" is not applied unless the
user asks for it by name.
- Secrets, credentials, and generated files are stop conditions.
Security
- Security scanPassed, 96 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
- SKILL.md in the repositoryCheckingmain/src/services/paneChatBundle/skills/refactor-apply/SKILL.md
Popularity
- 7-day trend score
- 0
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
[](https://verified-skill.com/skills/greenfield-inc/pane/refactor-apply)