Systematic audit of Claude Code configuration, rules, skills, hooks, and collaboration patterns.
Works with
Detects project tier (Simple/Standard/Complex) and applies tier-appropriate checks to avoid false positives
Audits six-layer framework: CLAUDE.md, rules, skills, hooks, subagents, and verifiers for drift and misalignment
Runs two parallel diagnostic agents: one for context/security, one for control/behavior patterns from conversation history
Flags critical issues (rule violations, dang
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionhealthExecute the skills CLI command in your project's root directory to begin installation:
Fetches health from tw93/claude-health and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate health. Access via /health in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
1.3K
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
1.3K
stars
Audit the current project's Claude Code setup with the six-layer framework:
CLAUDE.md → rules → skills → hooks → subagents → verifiers
The goal is to find violations and identify the misaligned layer, calibrated to project complexity.
Output language: Check in order: (1) CLAUDE.md ## Communication rule (global takes precedence over local); (2) language of the user's recent conversation messages; (3) default English. Apply the detected language to all output.
Keep the user informed of progress through the three steps: data collection, analysis, and synthesis.
Pick tier:
| Tier | Signal | What's expected |
|---|---|---|
| Simple | <500 project files, 1 contributor, no CI | CLAUDE.md only; 0–1 skills; no rules/; hooks optional |
| Standard | 500–5K project files, small team or CI present | CLAUDE.md + 1–2 rules files; 2–4 skills; basic hooks |
| Complex | >5K project files, multi-contributor, multi-language, active CI | Full six-layer setup required |
Apply only the detected tier's requirements.
Run bash "$CLAUDE_SKILL_DIR/scripts/collect-data.sh" to collect all configuration data. The script outputs labeled sections covering: tier metrics, CLAUDE.md (global + local), settings/hooks/MCP, rules, skill inventory, context budget, conversation history, and skill security content.
After the bash block completes, for each MCP server listed in the settings, attempt to call it and verify it actually responds. Do this before launching analysis agents.
For each server name found in Step 1:
list_tools or any known lightweight tool from that server).live=yes.live=no, note the error.Record the result as a table:
MCP Live Status:
server_name live=yes (N tools available)
other_server live=no error: connection refused / tool not found / API key invalid
Pass this table to Agent 1 for inclusion in the MCP findings section.
If API keys are required: look for relevant env var names in the server config (e.g., XCRAWL_API_KEY, OPENAI_API_KEY). Do not attempt to validate the key value itself -- just note whether the env var is set: echo $VAR_NAME | head -c 5 (5 chars only, do not print the full key).
Before interpreting Step 1 output, check these known failure modes.
Data collection silent failures
jq not installed: conversation extraction prints (unavailable: jq not installed or parse error). BEHAVIOR section will be empty -- treat as [INSUFFICIENT DATA], not a finding.python3 not on PATH: all MCP/hooks/allowedTools sections print (unavailable). Do not flag those areas when the data source itself failed.settings.local.json absent: hooks, MCP, and allowedTools all show (unavailable). Normal for projects using global settings only -- not a misconfiguration.MEMORY.md path construction
sed 's|[/_]|-|g' on pwd. Unusual characters produce the wrong project key. If MEMORY.md shows (none) but the user mentions prior sessions, verify the path manually before flagging as [!].Conversation extract scope
.jsonl files are sampled, skipping the active session. Findings from fewer than 2 files carry low signal, always tag [LOW CONFIDENCE].MCP token estimate
Tier misclassification edge cases
node_modules/, dist/, and build/, but not all generators. Monorepos with .next/, __pycache__/, or .turbo/ output can inflate the file count and trigger COMPLEX tier falsely. Recheck manually if the tier feels wrong.Summarize what was collected (word counts, skills found, conversation files sampled), confirm the tier, then proceed:
[REDACTED].Fallback: If either subagent fails (API error, timeout, or empty result), do not abort. Analyze that layer locally from Step 1 data instead and note "(analyzed locally -- subagent unavailable)" in the affected section of the report.
Read agents/inspector-context.md from this skill's directory. It specifies which Step 1 sections to paste and the full audit checklist.
Read agents/inspector-control.md from this skill's directory. It specifies which Step 1 sections to paste and the full audit checklist.
Aggregate the local analysis and any agent outputs into one report:
Health Report: {project} ({tier} tier, {file_count} files)
Render a compact table of checks that passed. Include only checks relevant to the detected tier. Limit to 5 rows. Omit rows for checks that have findings.
| Check | Detail |
|---|---|
| settings.local.json gitignored | ok |
| No nested CLAUDE.md | ok |
| Skill security scan | no flags |
Rules violated, missing verification definitions, dangerous allowedTools, MCP overhead >12.5%, required-path Access denied, active cache-breakers, and security findings.
CLAUDE.md content that belongs elsewhere, missing hooks, oversized skill descriptions, single-layer critical rules, model switching, verifier gaps, subagent permission gaps, and skill structural issues.
New patterns to add, outdated items to remove, global vs local placement, context hygiene, HANDOFF.md adoption, skill invoke tuning, and provenance issues.
If all three issue sections are empty, output one short line in the output language like: All relevant checks passed. Nothing to fix.
Stop condition: After the report, ask in the output language:
"Should I draft the changes? I can handle each layer separately: global CLAUDE.md / local CLAUDE.md / rules / hooks / skills / MCP."
Do not make any edits without explicit confirmation.
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
health fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
health has been reliable in day-to-day use. Documentation quality is above average for community skills.
Registry listing for health matched our evaluation — installs cleanly and behaves as described in the markdown.
health reduced setup friction for our internal harness; good balance of opinion and flexibility.
health has been reliable in day-to-day use. Documentation quality is above average for community skills.
health fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
We added health from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Registry listing for health matched our evaluation — installs cleanly and behaves as described in the markdown.
Solid pick for teams standardizing on skills: health is focused, and the summary matches what you get after install.
health has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 46