Communitygithub.com

基準測試優化循環

當用戶要求讓某個東西更快、嘗試多種變體、執行遞迴優化、基準測試延遲/吞吐量/成本,或透過重複測量測試選擇最佳實作時使用。

基準測試優化循環 是什麼?

這個「基準測試優化循環」技能旨在將模糊的性能要求(如「讓它快20倍」或「嘗試50次遞迴優化」)轉化為一個有邊界、可衡量的循環,從而實際改善系統。它支援任何可以執行腳本、程式碼或命令的平台(例如 Claude Code、Cursor、Codex 等)。其核心工作流程包括:先建立必要的基線(操作、正確性門檻、度量指標、當前基線和搜索預算),然後循環進行測量、瓶頸識別、變體生成、測試與驗證,最後提升最快的安全變體。它還提供了變體追蹤表、遞迴搜索的停止條件(如改進在雜訊範圍內、成本超支),以及嚴格的晉升門檻(包括正確性測試、重複驗證、回滾可行性和版本控制)。這個技能對於任何需要系統性優化性能、成本或可靠性的開發者或 AI 代理都非常有用,能確保優化過程是可重複、可驗證且符合預算的。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/benchmark-optimization-loop

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

基準測試優化循環 是做什麼的?

使用此技能將「讓它快20倍」或「嘗試50次遞迴優化」等要求轉換為一個有邊界、可衡量的循環,從而實際改善系統。

必要基線

在開始優化之前,必須先存在以下項目:

  • 正在被優化的操作;
  • 必須保持綠燈的正確性閘門;
  • 度量指標:實際運行時間、p95 延遲、每秒處理行數、每次執行成本、記憶體使用量、錯誤率;
  • 當前的基線;
  • 搜索預算:最大變體數、最大時間、最大花費、最大資料影響。

如果用戶要求的目標不切實際,請保留其雄心,但讓循環保持有邊界且可衡量。

循環

  1. 測量基線。
  2. 根據證據識別瓶頸。
  3. 生成變體,每個變體只測試一個假設。
  4. 使用相同的輸入形狀運行變體。
  5. 拒絕未通過正確性、安全性或可重現性檢查的變體。
  6. 晉升最快的安全變體。
  7. 將勝出路徑編碼為腳本、命令、測試、配置或文件。
  8. 重新運行基線和勝出者以確認改善幅度。

變體追蹤表

像這樣追蹤變體:

變體 | 假設 | 命令 | 時間 | 正確? | 備註
基線 | 當前路徑 | npm run job | 120s | 是 | 穩定
batch-500 | 減少往返次數 | npm run job -- --batch 500 | 42s | 是 | 勝出者
parallel-8 | 更多工作進程 | npm run job -- --workers 8 | 31s | 否 | 速率受限

遞迴搜索

對於遞迴或超參數調整工作:

  • 將每次運行持久化到記錄中;
  • 與先前接受的勝出者比較,而不僅僅是前一次運行;
  • 保留一個保留集或重放檢查;
  • 當改善幅度在雜訊範圍內、正確性測試失敗、成本超出預算,或搜索開始改變比它能解釋的更多變數時停止。

使用「最佳測量安全變體」等詞語,而不是「全局最優」,除非搜索空間確實是窮舉的。

晉升閘門

變體在成為新預設值之前必須滿足:

  • 正確性測試通過;
  • 性能改善幅度被重複驗證或解釋;
  • 回滾方式明確;
  • 變更已編碼在原始碼控制或持久的運行手冊中;
  • 最終摘要包含確切的命令和測量結果。

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.

相關技能