用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/mturac/everything-openai-codex --skill agent-eval命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Use this skill to monitor and verify a deployed URL or public OSS launch surface after releases — checks HTTP endpoints, SSE streams, static assets, console errors, performance regressions, PR queue health, maintainer feedback, and listing-review blockers after deploys, merges, submissions, or dependency upgrades. Smoke / canary / post-deploy / PR-watch verification.
Build reputation-safe open-source marketing from verifiable project evidence, not hype, spam, or repeated public pings. Use for launch copy, directory targeting, community posts, proof packets, and maintainer-facing positioning.
Turn public launch, directory, community, or list rejections into repo fixes and better proof without arguing, spamming, or resubmitting blindly. Use after Hacker News, Product Hunt, GitHub list PR, marketplace, or community rejection.
基于 SOC 职业分类
正在显示 SKILL.md
| name | agent-eval |
| description | 编码代理(OpenAI Codex、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 |
| origin | ecc |
| tools | Read, Write, Edit, Bash, Grep, Glob |
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 codex --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 │
├──────────────┼───────────┼────────┼────────┼─────────────┤
│ codex │ 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.