Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Verify composite action expansion output by comparing CLI-generated mermaid charts with actual GitHub Actions logs. Use when testing or debugging the --expand-composite-actions feature, especially to confirm that the original composite bar remains visible while expanded child rows appear beneath it. Triggered by requests like "composite展開を検証", "verify composite expansion", or "compare CLI output with logs".
Use when reviewing or auditing an existing codebase against production-proven implementation patterns — checking whether the patterns it already implements (actor model, rate limiter, circuit breaker, LRU cache, write-ahead log, semaphore, ...) actually honor the canonical invariants, whether any are mislabeled (a "semaphore" that is really a mutex; an "MVCC" that keeps one version), whether any diverge from the reference, and which catalog patterns are absent. Triggers on "audit our architecture against best practices", "do we implement X correctly", "are our patterns right", "pattern conformance", "is this really a <pattern>?". This grades patterns already present; its companion adopt-pattern adds new ones.
Write Go table-driven tests following Go community best practices and this repository's conventions. Use when writing or refactoring Go tests, especially when you notice repeated test patterns or copy-pasted test code.
E2E testing of kon using tmux sessions; IMPORTANT: only trigger this skill when user asks for e2e testing of kon
Use when validating markdown links or Mermaid diagrams.
Test the girl-agent WebUI end-to-end locally. Use when verifying profile setup, profile selection, config, assistant, addons, logs, memory, and runtime controls.
Turn acceptance criteria into a runnable Smithers eval suite (JSONL cases + rubric) and wire it to `smithers eval`. Use when a workflow's quality must be measured and regression-tested — not "looks good" once, but a repeatable check that fails when the model OR the harness regresses.
Structured performance opportunity investigation for SpiderMonkey (the Firefox JavaScript engine). Use this skill when the user wants to investigate JS engine performance, profile SpiderMonkey, find optimization opportunities, write performance patches, or evaluate benchmark regressions. Trigger on mentions of: profiling JS, SpiderMonkey performance, JIT optimization, benchmark regression analysis, shell benchmarking, or any request to make JS workloads faster. The methodolgy is described mostly for the JS shell but can be adapted to browser investigation.
Attach to a user's already-open Chromium-family browser for live inspection and light interaction after explicit local approval