fabriqaai/clawpatch-report-only-skill/clawpatch-report-only-skill
Claude Code and agent skill by fabriqaai/clawpatch-report-only-skill
- community
Checking that the SKILL.md file is still in the repository.
Use when asked to run ClawPatch, review code with ClawPatch, generate a ClawPatch findings report, inspect findings, triage findings, or revalidate findings without changing source code.
Install
npx vskill@latest install fabriqaai/clawpatch-report-only-skill/clawpatch-report-only-skillSKILL.md
ClawPatch Report-Only
Use this skill when the user wants ClawPatch to review a repository and produce findings without applying source changes.
Safety Rules
- Default to report-only.
- Do not run
clawpatch fixunless the user explicitly asks for a fix for a specific finding. - Before any non-dry-run fix, run
clawpatch fix --finding <id> --dry-runand show the result. - Do not commit, push, create a PR, create a branch, create a worktree, switch branches, or run destructive git commands from this workflow.
- Use a repository-local
.clawpatch/state directory and keep it ignored by git. - Treat findings as candidates. Inspect evidence before recommending action.
State Directory
Run from the target repository root:
If .clawpatch/ is not ignored, add it to the repository's ignore file before running ClawPatch.
Report-Only Workflow
Use --limit 3 --jobs 1 for the first pass in large repositories. Increase --limit only after the first report is useful and stable.
Inspect Findings
Show a finding before proposing a fix:
Re-check a finding without editing source files:
Mark a finding without source edits:
If The User Explicitly Asks For Fix
Only proceed when the user names one finding or clearly points to one finding.
First run a dry run:
Do not run non-dry-run fix unless the user approves that next step after seeing the dry-run result.
Final Response
Include:
- State directory and report path.
- Top findings ordered by severity and confidence.
- Which findings need human review before action.
- Any commands that failed or could not run.
- A note that no fixes, commits, branches, worktrees, pushes, or PRs were created.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingSKILL.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/fabriqaai/clawpatch-report-only-skill/clawpatch-report-only-skill)