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

ordinary-claude-skills
Guidelines and examples for authoring Hookify rule files (.claude/hookify.*.local.md) that detect patterns (bash, file, prompt, stop) and surface warnings or bl

skills
A pay-per-use Security OS for autonomous agents on Base offering 31 tools for security, safety, research, data, and earning features.

cloak
Protects real .env secrets by replacing on-disk values with safe sandbox values and providing a secure vault and CLI for running processes with real secrets.

marketplace
Static pre-install security and provenance scanner for SKILL.md packages and marketplace listings.

galyarder-framework
Require and verify concrete evidence (command outputs, test results, build exit codes) before claiming work is complete or creating PRs.

reins
Deterministic runtime security hooks for agents: block dangerous shell and file actions, warn on risky ops, and log audits to Watchtower.

agentguard
Realtime pattern-based detection and sanitization for prompt and command injection, designed to screen GitHub issues, sanitize inputs, and stop dangerous comman