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 add-skill 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.
Codex skill for initializing repository guardrails for AI agents and human review
embodied AI operating system (EAIOS)
The self-improving expertise system for Claude
Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.
Spec-Driven Flow — a structured development framework for Claude Code. Discovery → Spec → Build → Verify → Document.
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration