health-audit
Plugin audit against detected stack (Python, Node, Rust, Go, Terraform, Docker, K8s). Use when cleaning up unused plugins or discovering stack-relevant ones for a project.
What this skill does
# /health:audit
Audit the project's enabled plugins against the actual technology stack. Identifies plugins that don't apply to this project and suggests relevant plugins that aren't enabled.
## When to Use This Skill
| Use this skill when... | Use another approach when... |
|------------------------|------------------------------|
| Reviewing plugin relevance for current project | General health diagnostics (use `/health:check`) |
| Cleaning up unused plugins | Plugin registry corruption (use `/health:plugins --fix`) |
| Discovering relevant plugins for tech stack | Agentic optimization audit (use `/health:agentic-audit`) |
| Optimizing project-specific plugin configuration | Installing specific plugin (install directly) |
| Onboarding to existing project | Need comprehensive settings validation |
## Context
- Current project: !`pwd`
- Project settings exists: !`find . -maxdepth 2 -path '*/.claude/settings.json'`
- Package.json exists: !`find . -maxdepth 1 -name 'package.json'`
- Cargo.toml exists: !`find . -maxdepth 1 -name 'Cargo.toml'`
- pyproject.toml exists: !`find . -maxdepth 1 -name 'pyproject.toml'`
- requirements.txt exists: !`find . -maxdepth 1 -name 'requirements.txt'`
- go.mod exists: !`find . -maxdepth 1 -name 'go.mod'`
- Dockerfile exists: !`find . -maxdepth 1 -name 'Dockerfile'`
- docker-compose exists: !`find . -maxdepth 1 \( -name 'docker-compose.yml' -o -name 'docker-compose.yaml' -o -name 'compose.yml' -o -name 'compose.yaml' \)`
- GitHub workflows: !`find .github/workflows -maxdepth 1 -name '*.yml' -quit -print`
- Terraform files: !`find . -maxdepth 2 -name '*.tf' -quit -print`
- Kubernetes manifests: !`find . -maxdepth 3 \( -path '*/k8s/*' -o -path '*/kubernetes/*' \) -name '*.yaml' -quit -print`
## Parameters
| Parameter | Description |
|-----------|-------------|
| `--fix` | Apply recommended changes to `.claude/settings.json` |
| `--dry-run` | Show what would be changed without modifying files |
| `--verbose` | Show detailed analysis of each plugin decision |
## Execution
Execute this plugin relevance audit:
### Step 1: Detect the project technology stack
Analyze project files from the context above to determine the technology stack. Match indicators against the tech stack mapping in [REFERENCE.md](REFERENCE.md).
### Step 2: Retrieve available plugins
Run `claude plugin list --json` to get all available plugins from configured marketplaces. Parse the output for plugin name, description, keywords, and category.
### Step 3: Read currently enabled plugins
Read `.claude/settings.json` and extract the `enabledPlugins` array. If the file does not exist or `enabledPlugins` is not set, treat as empty list.
### Step 4: Analyze plugin relevance
Compare each enabled plugin against the detected tech stack. Use the plugin relevance mapping in [REFERENCE.md](REFERENCE.md) to determine which plugins are relevant, irrelevant, or missing.
Categorize each plugin as:
- **RELEVANT** -- matches detected tech stack
- **NOT RELEVANT** -- no matching indicators found
- **MISSING** -- relevant plugin not currently enabled
### Step 5: Generate the audit report
Print a structured report covering:
1. Detected technology stack with evidence
2. Currently enabled plugins with relevance status
3. Suggested plugins to add (with reasons)
4. Suggested plugins to remove (with reasons)
5. Summary counts
### Step 6: Apply changes (if --fix)
When `--fix` is passed:
1. Back up current settings: `cp .claude/settings.json .claude/settings.json.backup`
2. Ask for confirmation before each category of changes (removals, additions)
3. Update `.claude/settings.json` -- remove confirmed irrelevant plugins, add confirmed relevant plugins, preserve other settings
4. Verify changes by re-reading the file, confirming valid JSON, and showing the diff
## User-Level vs Project-Level
Note: This command only manages **project-level** plugin settings in `.claude/settings.json`.
User-level plugins (in `~/.claude/settings.json`) are managed separately and don't need duplication at project level.
When analyzing, check if a plugin is already enabled at user level:
```bash
jq -r '.enabledPlugins[]? // empty' ~/.claude/settings.json 2>/dev/null
```
If a plugin is enabled at user level, it doesn't need to be in project settings unless you want project-specific behavior.
## Edge Cases
| Scenario | Behavior |
|----------|----------|
| No `.claude/settings.json` | Create it with recommended plugins |
| Empty `enabledPlugins` | Suggest adding relevant plugins |
| Monorepo with multiple languages | Suggest all matching plugins |
| Plugin not in marketplace | Flag as "unknown" but don't remove |
| User declined changes | Respect decision, show manual instructions |
## Agentic Optimizations
| Context | Command |
|---------|---------|
| Plugin relevance audit | `/health:audit` |
| Audit with auto-fix | `/health:audit --fix` |
| Dry-run mode | `/health:audit --dry-run` |
| List enabled plugins | `jq -r '.enabledPlugins[]? // empty' .claude/settings.json 2>/dev/null` |
| Detect project languages | `find . -maxdepth 1 \( -name 'package.json' -o -name 'Cargo.toml' -o -name 'pyproject.toml' \) -exec basename {} \;` |
## Flags
| Flag | Description |
|------|-------------|
| `--fix` | Apply recommended changes (with confirmation) |
| `--dry-run` | Show what would be changed without modifying |
| `--verbose` | Show detailed reasoning for each decision |
## See Also
- `/health:plugins` - Fix plugin registry issues
- `/health:check` - Full diagnostic scan
- `/configure:claude-plugins` - Initial plugin setup
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.