Research-backed AI self-audit skill for Claude Code / Codex / OpenClaw. Verifies high-stakes answers via independent re-solve + cross-method probe — not by critique. Honest about limits; every design choice has a paper citation.
npx skills add guoyurui138-hue/audit-loopResearch-backed AI self-audit skill for Claude Code / Codex / OpenClaw. Verifies high-stakes answers via independent re-solve + cross-method probe — not by critique. Honest about limits; every design choice has a paper citation.
Agent Skills
Define an AI agent once, generate the config every tool expects (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules). Clean-room, built on open-gitagent (MIT).
Deploy custom ai agents that bring real value to your org in minutes. No coding required. Upload your skill bundles. Select tools for the agent. Sandboxed in the cloud. Observable by default.
Custom Hermes Agent skills: nobody, grill-me, mao-mentor, agent-monitoring
OpenClaw-native Delx Wellness profile pack with onboarding, skills and MCP connector presets
runs anywhere. uses anything