Updated 2mo ago
by SpaceZephyr
build-your-harness
两个配套的 Agent Skill:一个搭 harness,一个给 harness 体检。标准 SKILL.md 格式,Claude Code / Codex / Cursor / OpenClaw 通用,脚本也能直接当 CLI 跑。五层框架 + 可视化报告,破坏性动作一律先出方案等你点头。零依赖。
56 GitHub stars (56)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | −1 |
- 3 skills (3 skills found in its SKILL.md files)
- 9 forks (9 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add SpaceZephyr/build-your-harness
Asks which skills and agents to install. Just one: npx skills add SpaceZephyr/build-your-harness --skill better-your-harness — add -g for every project.
Claude Code
git clone https://github.com/SpaceZephyr/build-your-harnesscp -r "build-your-harness/better-your-harness" ~/.claude/skills/
Copies the better-your-harness skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add SpaceZephyr/build-your-harness
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
better-your-harness
给本地项目做一次 AI Harness 体检,产出可视化 HTML 报告。按五层扫描:安全与卫生(.gitignore、明文密钥、Agent 权限)、上下文质量(AI 可读性、冷启动成本、噪音比、目录结构)、工具装备(Skill/MCP/子Agent,含僵尸 Skill 统计)、记忆(索引健康度)、学习(迭代与复盘)。报告底部列出按严重度排序的待办,每条带一个可一键复制的修复口令,粘给 Claude Code 或 Codex 就能修。当用户说「体检」「harness 分析」「检查我的项目配置」「扫一下这个仓库」「看看我的 Agent 环境有什么问题」「audit」时触发,也适用于用户直接甩来一个本地项目路径要求分析的场景。
better-your-harness/SKILL.md on GitHub (opens in a new tab) -
star-your-harness
帮用户从零搭一个自己的 AI harness 工作目录。先用四个问题做一次简短访谈(你是干什么的、想让 AI 帮你做什么、现在的资料散在哪、放哪儿),然后按职业生成目录骨架,含入口 CLAUDE.md(目录地图 + 行为规则 + 任务路由)、about-me 上下文层、记忆层与索引、协议层与复盘、工具层、.gitignore 和 hooks,最后给出把已有资料搬进来的归类计划。生成的 harness 能直接通过 better-your-harness 的体检。当用户说「帮我搭一个 harness」「我想建自己的 AI 工作目录」「怎么组织我的 AI 协作环境」「从零开始配 Claude Code 的项目结构」「我的资料太乱了想重新组织」「star my harness」时触发。
star-your-harness/SKILL.md on GitHub (opens in a new tab) -
view-your-harness
把一个本地目录变成可浏览的可视化工作台,一屏看清「我有哪些文件」和「我有哪些 Skill 可用」。起一个本地只读服务,浏览器里出目录卡片墙、文件清单、Skill 装备台(带真实调用次数和僵尸标记),支持全局搜索、按类型/时间/体量筛选、点开预览、用系统程序打开或在访达中定位。当用户说「打开工作台」「可视化看一下这个目录」「我有哪些 Skill」「我有哪些文件」「这个文件夹里都有什么」「看板」「dashboard」「浏览我的 harness」时触发,也适用于用户直接甩来一个本地路径要求「看看里面有什么」的场景。
view-your-harness/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.