Component Benchmark Synthesizer — Testing & QA agent for Claude Code
Reads a raw harvest file from .design/benchmarks/raw/ .md and emits a canonical component spec at reference/components/ .md using the locked TEMPLATE.md shape.
How to install Component Benchmark Synthesizer
Installs to ~/.claude/agents/hegemonart-ultimate-design-component-benchmark-synthesizer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/hegemonart/ultimate-design/HEAD/agents/component-benchmark-synthesizer.md -o ~/.claude/agents/hegemonart-ultimate-design-component-benchmark-synthesizer.md Restart Claude Code, or start a new session, for it to be picked up.
What Component Benchmark Synthesizer does
name: component-benchmark-synthesizer description: Reads a raw harvest file from .design/benchmarks/raw/.md and emits a canonical component spec at reference/components/.md using the locked TEMPLATE.md shape. Spawned by /gdd:benchmark after harvesting. tools: Read, Write, Grep, Glob color: green default-tier: sonnet tier-rationale: "Synthesis across ≥4 sources with explicit convergence analysis requires multi-step reasoning; Haiku loses cross-source nuance, Opus overkill for
Alternatives in Testing & QA
- Component Config Reader — Extracts the test surface (properties, styles, events, defaults, nested variants) from a ToolJet app-builder c 41k ★
- Confluence Searcher — Searches Confluence and related tickets for product, architecture, rollout, and test-data context 548 ★
- Omd Locale Adapter — 한국어 canonical content를 EN/JA/ZH-CN/ZH-TW로 독립 adaptation한다 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Staff Code Reviewer
Use for adversarial pre-merge code review. Leads with the verdict path (could this produce a false SAFE?), the
Ff Vision
Flapforge vision and design analyst: reads reference screenshots and writes the canonical visual spec that eve
Ds Visual QA
Use after ds-component-builder finishes a batch, to check EVERY story of each component (not just Default) aga
Go Test Generator
Generates comprehensive Go tests including unit tests, table-driven tests, benchmarks, and test fixtures. Dele
Brain Eval Engineer
Evaluation engineer — question set tooling, layered metrics (harvest/graph/retrieval/answer), fixed-strategy a
Ba Agent
BA Agent — Viết PRD, User Stories, Release Notes cho mọi dự án. Dùng khi cần product spec, feature spec, GDD,
Related Skills
Arcanea Author Council
THE locked Arcanea instance — seven seats (Sanderson, Tolkien, Le Guin, Herbert, Bakker, Erikson, Gaiman), Lum
Sync All Md
Reconcile every Markdown doc in the repo against a single source of canonical facts, fix cross-doc drift, refr
Gql Performance Benchmark
Run GraphQL performance benchmarks against the Alkemio API and compare against a stored baseline