code-health
The code-health skill runs a comprehensive scan of a codebase to identify dead code, outdated dependencies, code smells, and unresolved technical debt, then generates a detailed report with prioritized findings. Use it before releases, after major refactoring, during periodic maintenance checks, or when assessing code quality for onboarding purposes.
git clone --depth 1 https://github.com/davepoon/buildwithclaude /tmp/code-health && cp -r /tmp/code-health/plugins/agent-triforce/skills/code-health ~/.claude/skills/code-healthSKILL.md
# Code Health
Runs a comprehensive code health scan using the Centinela (QA) agent.
## When to Use This Skill
- Periodic codebase hygiene check
- Before a release to ensure no dead code or unresolved debt
- After a large refactoring to verify cleanliness
- When onboarding to understand current code quality
## What This Skill Does
1. Runs the SIGN IN checklist
2. Scans for dead code (unused imports, variables, functions, commented-out blocks, unreachable code)
3. Checks for outdated and vulnerable dependencies
4. Detects code smells (long functions, deep nesting, duplication)
5. Audits TODO/FIXME comments for issue references
6. Runs the Scan Complete checklist (TIME OUT)
7. Writes findings to `docs/reviews/code-health-{date}.md`
8. Prepares findings handoff to Dev agent
## How to Use
### Basic Usage
```
/code-health
```
## Example
**User**: `/code-health`
**Output**: A code health report at `docs/reviews/code-health-2026-02-23.md` with:
- Dead code findings (verified, not false positives)
- Dependency status and vulnerabilities
- Code smell inventory
- TODO/FIXME audit
- Prioritized findings: Critical > Warning > Suggestion
## Tips
- Scans all source directories, not just `src/` — includes `tests/` and config files
- Previous scan findings are compared to track recurring issues
- Findings are verified to avoid false positives from dynamic imports or pluginsAutomate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
Sonnet Amplified fullstack engine. 34 modes, SEC-01~15 OWASP security, 13 runtime hooks, 75% token reduction. Install: npx @smorky85/aurakit
Automate BambooHR tasks via Rube MCP (Composio): employees, time-off, benefits, dependents, employee updates. Always search tools first for current schemas.