代理技能：在任何仓库中建立OpenAI的线束工程方法论。可使用Copilot、Codex、Claude、Cursor。
概览
一个代理技能，可以在任何仓库中建立OpenAI的线束工程方法论。可与任何AI编码代理合作——Copilot、Codex、Claude、Cursor或其他。 将任何仓库转变为以代理为先的工程环境： - — ~100行渐进披露地图（非百科全书）—— — 机械强制的依赖边界 - — 测试运行器、工具、架构边界测试 - — lint、类型检查、测试、构建每个PR - — 代码库的规范DO/DONT模式 - — 每周自动扫描反模式漂移 - — 在违规到达CI前捕捉 任何堆栈都能用。
概述（AI 翻译）
一个代理技能，可以在任何仓库中建立OpenAI的线束工程方法论。可与任何AI编码代理合作——Copilot、Codex、Claude、Cursor或其他。
它的作用
将任何仓库转变为以代理为先的工程环境：
- AGENTS.md — ~100行渐进披露地图（非百科全书）
- 架构层——机械强制的依赖边界
- 测试基础设施 — 测试运行工具、工具、架构边界测试
- CI 流水线 — 在每个 PR 上进行 lint、类型检查、测试、构建
- 黄金原则 — 代码库的规范DO/DOT模式
- 垃圾回收 — 每周自动扫描反模式漂移
- 预提交钩子 — 在违规到达CI前发现
支持的堆栈
适用于任何堆叠。该技能会自动检测并适应：
| 堆叠 | 测试跑者 | 加注者 |
|---|---|---|
| React/Vue/Svelte（Vite） | Vitest | ESLint |
| Next.js/Nuxt | Vitest/Jest | ESLint |
| Node.js/Express | Vitest/Jest | ESLint |
| Python/Django/FastAPI | pytest | Ruff |
| 走 | 去测试 | 戈兰奇林特 |
| 锈蚀 | 货物测试 | 剪辑 |
| 鲁比/轨道 | RSpec | 鲁博警察 |
安装
本页由 AI 翻译，技术细节请以原文为准。
README
harness-engineering
An agent skill that sets up OpenAI’s harness engineering methodology in any repository. Works with any AI coding agent — Copilot, Codex, Claude, Cursor, or others.
What It Does
Transforms any repo into an agent-first engineering environment:
- AGENTS.md — ~100-line progressive disclosure map (not an encyclopedia)
- Architecture layers — mechanically enforced dependency boundaries
- Testing infrastructure — test runner, utilities, architecture boundary tests
- CI pipeline — lint, typecheck, test, build on every PR
- Golden principles — canonical DO/DON’T patterns for the codebase
- Garbage collection — weekly automated scans for anti-pattern drift
- Pre-commit hooks — catch violations before they reach CI
Supported Stacks
Works with any stack. The skill auto-detects and adapts:
| Stack | Test Runner | Linter |
|---|---|---|
| React/Vue/Svelte (Vite) | Vitest | ESLint |
| Next.js/Nuxt | Vitest/Jest | ESLint |
| Node.js/Express | Vitest/Jest | ESLint |
| Python/Django/FastAPI | pytest | Ruff |
| Go | go test | golangci-lint |
| Rust | cargo test | clippy |
| Ruby/Rails | RSpec | RuboCop |
Install
npx skills add charlesanim/harness-engineering
Or to install globally (user-level, available in all repos):
npx skills add charlesanim/harness-engineering -g
Usage
Once installed, just ask your agent:
“Set up harness engineering in this repo”
Or any of these triggers:
- “Make the repo agent-ready”
- “Add architectural boundaries”
- “Set up testing and CI”
- “Adopt agent-first engineering”
What is Harness Engineering?
Coined by OpenAI after shipping ~1 million lines of agent-generated code in 5 months with zero manually-written code. The core insight: don’t write better prompts — design better environments.
8 Principles:
- Engineers become environment designers
- Give agents a map, not an encyclopedia
- If agents can’t see it, it doesn’t exist
- Enforce architecture mechanically, not through instructions
- Boring technology wins
- Entropy management is garbage collection
- Throughput changes merge philosophy
- Agent-to-agent code review
Read the original: openai.com/index/harness-engineering
License
MIT
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add charlesanim/harness-engineering