Dev & Coding

A repo-maintenance skill that audits and fixes every skill, agent, index, and cross-reference doc in the Han plugin repository.

Audits a codebase for coupling imbalances using Vlad Khononov's Balanced Coupling model and writes an architecture review document.

Build and train self-learning agents using AgentDB's nine reinforcement learning plugin templates.

Teaches Claude AgentDB's advanced stack — QUIC sync, hybrid vector+metadata search, multi-DB sharding, MMR and production hardening.

Guides Claude through building and debugging Arcium encrypted (MPC) apps on Solana across circuit, program and client layers.

Generates ACSL formal specifications — function contracts, loop invariants and memory-safety clauses — for C/C++ code so it can be proven with Frama-C.

Infers loop invariants, preconditions and postconditions via abstract interpretation and emits them in Dafny, Isabelle, Coq or ACSL syntax.

An SST v4 (Ion) expert skill for authoring, testing, deploying and troubleshooting sst.config.ts and infra/ modules on AWS.

An expert skill for deploying, operating, and evaluating AI agents across all nine AWS Bedrock AgentCore services.

A developer reference for wiring Agentica agents to a Claude Code CLI proxy, covering required flags, response formats, and common failures.

A diagnostic skill that scores Claude Code skill bundles across 10 categories — structure, version sync, skill quality, workflow integration and security — and writes a Go/No-Go audit report.

A rigorous pre-implementation planning skill: 10+ scoping questions, web research, and reviewer/criticizer rounds until the plan converges.

Generates new bundle-plugin project structure and adds, migrates, or removes platform support across Claude Code, Cursor, Codex, OpenCode and Gemini CLI.

An orchestrator that diagnoses a Claude Code skill or bundle-plugin and improves its triggering description, token cost, workflow chain and security findings step by step.

A lookup skill covering the Agentica multi-agent framework's pattern classes, core infrastructure, and primitives.

A multi-agent execution rulebook: decompose plans into tasks, isolate each task on its own branch, enforce two-stage review, and gate merges behind human checkpoints.