Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.

Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]

🧠 AI Agent skills for LLMs and AI Agents - Claude, Codex, Cursor etc.

Claude Code skill plugin for cleaning up and bringing Lean 4 code to mathlib standards.

Security audit skill for LLM agents - prompt injection scanner, attack catalog & defense checklist

A reusable AI agent skill for managing the full software development lifecycle with plain language requests.

Unified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, solana-game, trailofbits, cloudflare, qedgen, colosseum, solana-new, ghostsecurity, defending-code) and local skills. Progressive disclosure — read only what you need.

Retrieval-Augmented Theorem Provers for Lean

An annotated library of real AI writing failure patterns with full dissection. Use to teach a writer what AI slop actually looks like, diagnose why a specific passage reads as machine-written, or explain the mechanism behind a pattern.

Review changed code for YAGNI, removable over-complexity, reuse, code quality, and efficiency, then apply worthwhile simplifications. Use when the user asks to simplify, clean up, tighten, de-hack recent changes, identify logic that can be dropped, or review whether added safeguards and edge-case handling are actually needed.

Review changes on current branch and output a structured review. Optionally post to PR with --pr flag, or apply non-blocking follow-ups inline with --apply-followups.