Skill Radar

Scan, analyze, and optimize your AI skill ecosystem. Diagnose skill usage, discover capability gaps, and check version updates in one command. Trigger on "sk...

Security Scan

The skill's code, dependencies, and runtime actions are consistent with its stated purpose (scanning and analyzing installed Skills), though it reads sensitive local workspace/session files and creates caches under ~/.openclaw which you should be aware of.

Purpose & Capability

Name/description (Skill Radar) align with required binaries (python3, openclaw) and the code: it reads OpenClaw skill lists, checks ClawHub versions, searches ClawHub and inspects skills. Required tools and operations are proportional to scanning, version checks, usage analysis and recommendations.

Instruction Scope

The runtime will read user workspace files and logs (e.g., ~/.openclaw/workspace/MEMORY.md, HEARTBEAT.md, AGENTS.md, session logs in ~/.openclaw/agents/main/sessions) and optional mem0 data. This is necessary for usage analysis and recommendations, but these are sensitive data sources (conversation history, configs). It also invokes external CLIs (openclaw, npx clawhub) and may run a mem0 list.py if present.

Install Mechanism

No install script — instruction-only with bundled Python scripts. No downloads or remote installers. The skill writes cache files under ~/.openclaw/workspace (ClawHub and security caches) which is expected for local caching.

Credentials

The skill declares no required environment variables or credentials. It does call system CLIs and reads files under the user's home/openclaw workspace; those accesses are consistent with analyzing local skills and user session data.

Persistence & Privilege

always is false and the skill does not request system-wide privileges. It creates and updates local cache files (~/.openclaw/workspace/.skill-radar-*.json) and may inspect installed skill directories (including detected bundled OpenClaw paths). This is normal for its purpose but means it will persist scan/cache state locally.

Assessment

This skill appears to do what it says: it inspects your installed Skills, reads local workspace files and session logs, queries ClawHub via npx, and writes caches under ~/.openclaw/workspace. Before installing, consider: 1) it will access sensitive conversation logs and workspace configs — only use it if you trust the skill and its source; 2) it calls external CLIs (openclaw, npx clawhub) which may contact remote services; ensure those CLIs are from trusted origins; 3) it may execute a local mem0 list.py if present — review that script before allowing it to run; 4) caches are stored in your home directory and can be removed by deleting ~/.openclaw/workspace/.skill-radar-*.json. If you want extra assurance, run it in a constrained or non-production environment first and inspect its output and created cache files.

Your AI Skill Manager — Make every installed Skill count

Core Philosophy

Make Skill management simpler and more efficient.

• Simpler — See the full picture with one command, no more getting lost in 100+ Skills
• More Efficient — Precisely identify idle skills and gaps, maximize every investment
• Smarter — Data-driven decisions, not guesswork

Trigger Conditions

• "check skill", "skill radar", "skill diagnostics", "skill management", "skill optimization"
• "skill usage", "skill insight"
• "which skills am I not using", "should I install this skill", "do my skills need updating"

Features

Command	Description
usage	📊 Usage Value Assessment (based on 5 data sources)
status	📋 Missing/Ready Status Check
recommend	💡 Smart Recommendations (discover capability gaps from conversation history)
versions	🔄 Version Check
all	Full Report (all commands above)

Usage

# Full report (recommended for first use)
python3 <skill-path>/scripts/health_check.py all

# Individual checks
python3 <skill-path>/scripts/health_check.py usage       # Usage value assessment
python3 <skill-path>/scripts/health_check.py status      # Status check
python3 <skill-path>/scripts/health_check.py recommend   # Smart recommendations
python3 <skill-path>/scripts/health_check.py versions    # Version check

# Output as Markdown
python3 <skill-path>/scripts/health_check.py all > report.md

Usage Value Assessment

Integrates 5 data sources to infer each Skill's usage:

Data Source	Content	Weight
Daily Memory	Events, decisions, progress	⭐⭐⭐
MEMORY.md	Core config, preferences	⭐⭐⭐
HEARTBEAT.md	Scheduled task config	⭐⭐
Session Logs	Raw conversation records	⭐⭐
AGENTS.md	Work rules	⭐⭐

Scoring: 🔵 High (core tool) / 🟢 Medium / 🟡 Low / 🔴 Unused

Dependencies

• Python 3.8+ (pure standard library, no external dependencies)
• OpenClaw CLI (openclaw)
• ClawHub CLI (npx clawhub, only for version check and recommendations)