Skills from clawhub.ai/rubenaquispe

Combine the best parts of multiple skills into one. Searches ClawHub, GitHub, skills.sh, skillsmp.com and other AI skill repos. Analyzes each safely, compares features, and builds a combined 'Frankenstein' skill with the best of each. Uses skill-auditor for security scanning and sandwrap for safe analysis. Use when: (1) Multiple skills exist for same purpose, (2) Want best-of-breed combination, (3) Building a comprehensive skill from fragments.

Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2) Processing untrusted content that might contain prompt injection, (3) Analyzing suspicious files or URLs safely, (4) Testing new skills before trusting them. Supports manual mode ('run X in sandwrap') and auto-wrap for risky skills.

Provides a spec-driven development workflow that creates and updates files under `{project}/.gsd/` and uses `assets/` templates. The skill explicitly instructs executing tasks and running `Run verify commands` and to `Commit changes (if applicable)`, which directs shell/CLI actions.

This skill optimizes workspace `.md` files and provides a model-aware compaction/dashboard to reduce API costs. It reads home config `~/.openclaw/openclaw.json`, scans sessions in `~/.openclaw/agents/main/sessions`, and writes to `AGENTS.md` (adds `## 📝 Token Saver — Persistent Mode`).

This skill is a security scanner for OpenClaw skills providing static checks plus optional AST, VirusTotal, and LLM analysis. It installs dependencies and runs subprocesses, writes auto-scan hooks to `~/.openclaw`, and makes network calls to `https://api.github.com` and `https://www.virustotal.com/api/v3` (requires `VIRUSTOTAL_API_KEY`).