Communitygithub.com

Benchmark – Leistungsbasislinie & Regressionserkennung

Mit dieser Fähigkeit können Sie Leistungsbasislinien messen, Regressionen vor/nach PRs erkennen und Stack-Alternativen vergleichen.

Was ist Benchmark – Leistungsbasislinie & Regressionserkennung?

Diese AI-Agent-Fähigkeit ermöglicht es Entwicklern, Leistungstests direkt aus dem Entwicklungsworkflow heraus durchzuführen – ohne manuelle Benchmarks oder externe Tools. Sie unterstützt vier Modi: Seitenleistung (über echte Core Web Vitals wie LCP, CLS, INP), API-Leistung (p50/p95/p99 Latenz unter Last), Build-Leistung (Kaltstart, HMR, Tests) sowie Vorher/Nachher-Vergleiche für Änderungen. Die Ergebnisse werden als JSON-Baselines im Ordner `.ecc/benchmarks/` gespeichert und sind Git-versioniert, sodass das Team gemeinsame Basislinien teilen kann. Die Fähigkeit ist ideal für CI/CD-Pipelines, wo sie automatisch nach jedem PR einen Vergleich durchführen kann. Sie lässt sich mit anderen Fähigkeiten wie `/canary-watch` für Post-Deploy-Monitoring oder `/browser-qa` für die vollständige Auslieferungs-Checkliste kombinieren. Das Tool hilft, Leistungsregressionen frühzeitig zu erkennen, bevor sie in Produktion gelangen, und ermöglicht datengestützte Entscheidungen bei der Wahl von Technologie-Stacks.

Funktioniert mit~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/benchmark
Original anzeigen→Alle Skills durchsuchen

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Dokumentation

Was macht Benchmark – Leistungsbasislinie & Regressionserkennung?

Wann verwenden

  • Vor und nach einem PR zur Messung der Leistungsauswirkungen
  • Einrichten von Leistungsbasislinien für ein Projekt
  • Wenn Benutzer melden „es fühlt sich langsam an“
  • Vor einer Veröffentlichung – stellen Sie sicher, dass die Leistungsziele erreicht werden
  • Vergleichen Ihres Stacks mit Alternativen

So funktioniert es

Modus 1: Seitenleistung

Misst echte Browser-Metriken über Browser MCP:

1. Navigiere zu jeder Ziel-URL
2. Miss die Core Web Vitals:
   - LCP (Largest Contentful Paint) – Ziel < 2,5s
   - CLS (Cumulative Layout Shift) – Ziel < 0,1
   - INP (Interaction to Next Paint) – Ziel < 200ms
   - FCP (First Contentful Paint) – Ziel < 1,8s
   - TTFB (Time to First Byte) – Ziel < 800ms
3. Miss die Ressourcengrößen:
   - Gesamtseitengewicht (Ziel < 1 MB)
   - JS-Bündelgröße (Ziel < 200 KB gzip)
   - CSS-Größe
   - Bildgewicht
   - Gewicht von Drittanbieter-Skripten
4. Zähle Netzwerkanfragen
5. Prüfe auf render-blockierende Ressourcen

Modus 2: API-Leistung

Benchmarkt API-Endpunkte:

1. Rufe jeden Endpunkt 100 Mal auf
2. Miss: p50, p95, p99 Latenz
3. Verfolge: Antwortgröße, Statuscodes
4. Teste unter Last: 10 gleichzeitige Anfragen
5. Vergleiche mit SLA-Zielen

Modus 3: Build-Leistung

Misst die Entwicklungs-Rückkopplungsschleife:

1. Kalte Build-Zeit
2. Hot Reload-Zeit (HMR)
3. Testsuite-Dauer
4. TypeScript-Prüfzeit
5. Lint-Zeit
6. Docker-Build-Zeit

Modus 4: Vorher/Nachher-Vergleich

Führe vor und nach einer Änderung durch, um die Auswirkungen zu messen:

/benchmark baseline    # speichert aktuelle Metriken
# ... Änderungen vornehmen ...
/benchmark compare     # vergleicht mit der Basislinie

Ausgabe:

| Metrik  | Vorher | Nachher | Differenz | Ergebnis       |
|---------|--------|---------|-----------|----------------|
| LCP     | 1,2s   | 1,4s    | +200ms    | WARNUNG: WARN  |
| Bündel  | 180KB  | 175KB   | -5KB      | ✓ BESSER       |
| Build   | 12s    | 14s     | +2s       | WARNUNG: WARN  |

Ausgabe

Speichert Basislinien in .ecc/benchmarks/ als JSON. Git-versioniert, sodass das Team gemeinsame Basislinien teilt.

Integration

  • CI: /benchmark compare bei jedem PR ausführen
  • Kombinieren mit /canary-watch für Post-Deploy-Monitoring
  • Kombinieren mit /browser-qa für vollständige Auslieferungs-Checkliste

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳：このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Verwandte Skills

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community