porcupine-md/anoa-browser/assessing-code-health
Claude Code and agent skill by porcupine-md/anoa-browser
- community
Checking that the SKILL.md file is still in the repository.
Run linters/typecheckers to calculate health score.
Install
npx vskill@latest install porcupine-md/anoa-browser/assessing-code-healthSKILL.md
The same SKILL.md was published earlier as porcupine-md/jonggrang/assessing-code-health.
Assessing Code Health
Role Constraints: Reviewer (STRICTLY READ-ONLY for application code). You MAY NOT modify, fix, or write to application source code. File Access: Use the glob tool to search for the active feature directory under .jonggrang/.output/features/. You may only use the write tool to save your audit report inside this specific directory.
Objective
Run read-only static analysis tools (linters, typecheckers, etc.) to assess the code health of the current feature and calculate a health score.
Execution Steps
- Information Gathering:
- Find the active feature directory using
glob. - Identify the project's build and linting commands (e.g.,
package.jsonscripts likenpm run lint,tsc --noEmit).
- Run Analysis (READ-ONLY):
- Execute the linting and typechecking commands using the
bashtool. - DO NOT run commands that auto-fix or format code (e.g., do not use
--fix). - Capture the output and analyze the frequency and severity of errors/warnings.
- Calculate Health Score:
- Based on the findings, assign a composite health score (0-10).
- Document the major offending files and the types of errors encountered.
- Generate Report:
- Write the results and the calculated health score to
.jonggrang/.output/features/<active-feature-dir>/health-report.mdusing thewritetool.
Completion Signal
When the health assessment report is saved, output exactly:
HEALTH_ASSESSMENT_COMPLETE
Security
- Security scanPassed, 95 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 repositoryChecking.jonggrang/skills/library/backend/assessing-code-health/SKILL.md
Popularity
- 7-day trend score
- 5
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/porcupine-md/anoa-browser/assessing-code-health)