Stats
Actions
Tags
From fablelayer
Compares LLM performance (Sonnet, Opus, local models) on coding, agentic, and planning tasks using blind pairwise rubrics. Generates cost estimates and structured RESULTS.md. Triggered by FableLayer benchmark or rubric design requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fablelayer:fablelayer-benchmarkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
FableLayer의 품질 주장을 재현 가능한 benchmark로 환원한다. “Fable 같다”는 인상평이 아니라 blind pairwise rubric, raw JSON, 비용 추정으로 남긴다.
FableLayer의 품질 주장을 재현 가능한 benchmark로 환원한다. “Fable 같다”는 인상평이 아니라 blind pairwise rubric, raw JSON, 비용 추정으로 남긴다.
bench/README.md: 실행 방법, fixture 설명.bench/RESULTS.md: 사람이 읽는 요약. 미실행이면 미실행이라고 표시한다._workspace/benchmark_schema.json: raw run schema.Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub voidlight00/fablelayer --plugin fablelayer