Curated, MIT-licensed Agent Skills, subagents & rules from shimo4228's harness — open Agent Skills standard, not Claude-Code-only. Lift what you want.
Agent
Strict Architecture Decision Record reviewer. Reviews ADRs for section completeness, context-decision alignment, straw-man alternatives, one-sided consequences, unsourced numeric claims, and unstated override relationships with prior ADRs. Use PROACTIVELY after writing or substantially revising an ADR, before commit.…
Agent
Render a single Architecture Decision Record file from an already-decided decision packet, conforming to the harness ADR template (Status / Date / Context / Decision / Review-when / Alternatives Considered / Consequences). Use when the user explicitly records a design decision, when context-sync Phase 3 needs to…
Agent
Generate or refresh docs/CODEMAPS/ for the current repo. Use when the user runs /update-codemaps, when context-sync Phase 0 detects stale codemaps, or when an LLM needs token-lean architecture documentation for an unfamiliar codebase. Scans source dirs, produces INDEX.md + up to five role-specific codemaps…
Agent
Context-starved prompt forager for diversity injection. Receives ONE line (a purpose) and deliberately nothing else, then searches external creativity-technique catalogs and prompt collections for 3-5 prompts from angles the requesting session would not produce itself. Dispatched by the prompt-perturb skill — not for…
Agent
Generate concise, focused prompts using a lightweight model. Use when creating or rewriting LLM prompt templates.
Agent
Pre-implementation solution discovery. Use PROACTIVELY before writing custom code — NOT for general research or deep dives. Searches npm, PyPI, MCP registries, GitHub, and web for battle-tested alternatives.
Agent
Expert Swift / SwiftUI code reviewer specializing in Swift 6 strict concurrency, value semantics, SwiftUI state management, memory management (retain cycles), and HIG compliance. Use for all Swift code changes in iOS / macOS projects. MUST BE USED for Swift projects.