docs/zh-CN/skills/agent-eval/SKILL.md
编码代理(Claude Code、Aider、Codex等)在自定义任务上的直接比较,包含通过率、成本、时间和一致性指标
npx skillsauth add affaan-m/everything-claude-code agent-evalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
一个轻量级 CLI 工具,用于在可复现的任务上对编码代理进行头对头比较。每个“哪个编码代理最好?”的比较都基于感觉——本工具将其系统化。
# pinned to v0.1.0 — latest stable commit
pip install git+https://github.com/joaquinhuigomez/agent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b
以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功:
name: add-retry-logic
description: Add exponential backoff retry to the HTTP client
repo: ./my-project
files:
- src/http_client.py
prompt: |
Add retry logic with exponential backoff to all HTTP requests.
Max 3 retries. Initial delay 1s, max delay 30s.
judge:
- type: pytest
command: pytest tests/test_http_client.py -v
- type: grep
pattern: "exponential_backoff|retry"
files: src/http_client.py
commit: "abc1234" # pin to specific commit for reproducibility
每个代理运行都获得自己的 git 工作树——无需 Docker。这提供了可复现的隔离,使得代理之间不会相互干扰或损坏基础仓库。
| 指标 | 衡量内容 | |--------|-----------------| | 通过率 | 代理生成的代码是否通过了判断? | | 成本 | 每个任务的 API 花费(如果可用) | | 时间 | 完成所需的挂钟秒数 | | 一致性 | 跨重复运行的通过率(例如,3/3 = 100%) |
创建一个 tasks/ 目录,其中包含 YAML 文件,每个任务一个文件:
mkdir tasks
# Write task definitions (see template above)
针对你的任务执行代理:
agent-eval run --task tasks/add-retry-logic.yaml --agent claude-code --agent aider --runs 3
每次运行:
生成比较报告:
agent-eval report --format table
Task: add-retry-logic (3 runs each)
┌──────────────┬───────────┬────────┬────────┬─────────────┐
│ Agent │ Pass Rate │ Cost │ Time │ Consistency │
├──────────────┼───────────┼────────┼────────┼─────────────┤
│ claude-code │ 3/3 │ $0.12 │ 45s │ 100% │
│ aider │ 2/3 │ $0.08 │ 38s │ 67% │
└──────────────┴───────────┴────────┴────────┴─────────────┘
judge:
- type: pytest
command: pytest tests/ -v
- type: command
command: npm run build
judge:
- type: grep
pattern: "class.*Retry"
files: src/**/*.py
judge:
- type: llm
prompt: |
Does this implementation correctly handle exponential backoff?
Check for: max retries, increasing delays, jitter.
data-ai
Run team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.
data-ai
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
development
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
tools
React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.