메뉴
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
ann-benchmarks フレームワーク規約(algos.yaml/HDF5/Pareto frontier分析)と ANN ベクトル検索の SIMD 距離カーネル最適化における落とし穴パターン(AVX2/AVX-512 ディスパッチャ検証・量子化の数学的等価性確認・部分集合とフルスケールの混同防止)。ArcFlare/NGT/NGTAQ 等の ANN R&D 作業時の参照用。実装作業自体は ann-perf-engineer agent に委譲する。
Claude API / Anthropic Go SDK usage patterns, prompt caching, streaming, tool use, and model selection for Go applications.
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
非推奨・後方互換用リダイレクト。旧 dig（コードベース深掘り分析→設計インタビュー→実装計画→自律実行）は swarm-loop に完全統合された。/dig と入力された場合は本ファイルの指示に従い、そのまま swarm-loop skill を 同じ目標・同じ引数で起動すること。dig 独自のロジックはここには存在しない。
GitHub Actions workflow design, matrix builds, secrets management, caching, and CI/CD patterns for Go/Rust/Protobuf projects with make-based build systems.
| name | benchmark |
| description | Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives. |
Measures real browser metrics via browser MCP:
1. Navigate to each target URL
2. Measure Core Web Vitals:
- LCP (Largest Contentful Paint) — target < 2.5s
- CLS (Cumulative Layout Shift) — target < 0.1
- INP (Interaction to Next Paint) — target < 200ms
- FCP (First Contentful Paint) — target < 1.8s
- TTFB (Time to First Byte) — target < 800ms
3. Measure resource sizes:
- Total page weight (target < 1MB)
- JS bundle size (target < 200KB gzipped)
- CSS size
- Image weight
- Third-party script weight
4. Count network requests
5. Check for render-blocking resources
Benchmarks API endpoints:
1. Hit each endpoint 100 times
2. Measure: p50, p95, p99 latency
3. Track: response size, status codes
4. Test under load: 10 concurrent requests
5. Compare against SLA targets
Measures development feedback loop:
1. Cold build time
2. Hot reload time (HMR)
3. Test suite duration
4. TypeScript check time
5. Lint time
6. Docker build time
Run before and after a change to measure impact:
/benchmark baseline # saves current metrics
# ... make changes ...
/benchmark compare # compares against baseline
Output:
| Metric | Before | After | Delta | Verdict |
|--------|--------|-------|-------|---------|
| LCP | 1.2s | 1.4s | +200ms | WARNING: WARN |
| Bundle | 180KB | 175KB | -5KB | ✓ BETTER |
| Build | 12s | 14s | +2s | WARNING: WARN |
Stores baselines in .benchmarks/ (project root) as JSON. Git-tracked so the team shares baselines.
/benchmark compare on every PR