danygiguere/audit-skills
Language- and framework-agnostic audit checklists for AI coding agents — security, correctness, and operability. Works with Claude Code, GitHub Copilot, Cursor, Codex CLI, OpenCode, and any agent that can read files.
Language- and framework-agnostic audit checklists for AI coding agents — security, correctness, and operability. Works with Claude Code, GitHub Copilot, Cursor, Codex CLI, OpenCode, and any agent that can read files.
npx add-skill danygiguere/audit-skillsLanguage- and framework-agnostic audit checklists for AI coding agents — security, correctness, and operability. Works with Claude Code, GitHub Copilot, Cursor, Codex CLI, OpenCode, and any agent that can read files.
The most powerful AI coding agent. 5.7MB. Supports DeepSeek, MiMo, OpenAI, Claude. One binary, zero dependencies.
Automate Strava tasks via Rube MCP (Composio). Always search tools first for current schemas.
DryDock - Local CLI coding agent optimized for SWE-bench.
AI Agent安全测试skill
一个 Claude / OpenClaw Skill，专治"想做个 Skill 但说不清需求"。通过引导式讨论帮你把模糊想法变成精确的 Skill 规格，自动生成带版本管理和讨论记录的完整 Skill 目录。
ARG Action Chain: a Step Contract based execution pattern for controlling LLM Agent drift, hallucination, and self-verification