SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

agentfactory-business-plugins
Classify, score, and produce structured vendor assessments (Kraljic matrix + six-dimension evaluation) with clear findings, flags, and prioritized remediation a

gsd-skill-creator
Security hygiene guidelines for self-modifying agent systems: path sanitization, safe YAML handling, data poisoning checks, and staging/quarantine practices to

tradecat
Operate and inspect the TradeCat public terminal project: run CLI/TUI flows, validate installers, inspect Google Sheets CSV caches, and maintain the cache-first

claude-mcp-sentinel
Security monitoring and runtime protection for Claude Skills and MCP servers: static scans, update-diff analysis, threat intelligence, and an optional PreToolUs

skill-vetter
Pre-install security gate that scans a skill for prompt-injection, secrets, and other vulnerabilities before installation.

asi
Framework treating pill dispensers as network devices: routing, access control, scramble-indexing and confidential supply tracking for custom dispenser workflow

claude-skill-registry
Run a zero-assumption audit of project dependencies: CVEs, maintenance, license risk, bundle cost, bus factor, and recommendations to remove or replace risky pa

skills
Static security assessment for OpenClaw: configuration audit plus skill static analysis to find high-risk behaviors before install.

babysitter
Advanced capacity requirements planning with demand-capacity gap analysis and resource strategy recommendations.

Prism Scanner
Open-source security scanner that detects malicious code, supply-chain risks, and residue in AI Agent skills, plugins, and MCP servers.

decepticon
Adversary-emulation profile that maps APT29 (Cozy Bear) ATT&CK TTPs to Decepticon tooling for realistic, cloud- and identity-focused red-team exercises.

openclaw-skills-security
Audit an OpenClaw installation and generate a prioritized, ready-to-apply hardening plan for AGENTS.md, gateway, sandbox, and permissions.