Delegate coding tasks to Mistral Vibe CLI while Claude decomposes, supervises via git diff, and reports token cost.
Designs property-service operations with an ontology plus DMAIC control plan covering work orders, dispatch, quotes, evidence, CTQs and control dashboards.
A meta-skill that upgrades one existing Lattice skill through a fixed six-step pipeline: baseline diff, dependency map, precision rewrite, three-tool QA gate, and independent verification.
A framework for scoring AI agent output quality against fixtures and baselines so regressions are caught before they ship.
Guides Claude through using rdc-cli to open RenderDoc .rdc captures, trace draws/shaders/pixels, and run GPU assertions in CI.
A rulebook for delegating independent, non-overlapping tasks to parallel agent workers or selected persistent role sessions.
Guides Claude through building and debugging Arcium encrypted (MPC) apps on Solana across circuit, program and client layers.
A judgment skill that returns a single artifact-free CONTINUE/STOP verdict on whether a work traversal earns its cost or is just process ceremony.
Sends one question to several Chinese AI platforms, preserves each raw answer and citation, aligns the claims point by point, and verifies them with authoritative evidence across four separate reports.
A scheduled maintenance skill that closes already-shipped issues and keeps a curated 15–25 issue contributor backlog for the awesome-claude repo.
Generates ACSL formal specifications — function contracts, loop invariants and memory-safety clauses — for C/C++ code so it can be proven with Frama-C.
A static-analysis skill that applies abstract interpretation to infer variable ranges and flag potential runtime errors — out-of-bounds, null dereference, divide-by-zero, integer overflow — without running the code.
Infers loop invariants, preconditions and postconditions via abstract interpretation and emits them in Dafny, Isabelle, Coq or ACSL syntax.
Analyzes German cease-and-desist letters over unfair T&C clauses and drafts a narrowed cease-and-desist undertaking with cost and risk assessment.
A repo-specific conventions skill that teaches Claude the Claude Code CLI codebase layout, tool/command patterns, and naming rules.
Turns any source that describes how a task gets done — a SKILL.md, chat log, runbook, or plain prose — into a runnable Flowtrace DAG and drives the full run lifecycle to verify it.
A repo-maintenance skill that audits and fixes every skill, agent, index, and cross-reference doc in the Han plugin repository.
An experimental harness skill that builds a six-step incident post-mortem to measure agent behavior across a context fork.
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.