harness
Skill2 starsChanged 2 days agoMITView on GitHub
Harness Engineering 项目管理入口(接入 / 升级 / 接手 / 计划 / 验证 / 评审 / 发布 / 交接 / 反馈 kit 问题)。未接入的仓库先走 adopt:定位 kit → 只读盘点 → dry-run → init;已接入先运行 python3 tools/harness.py status。触发:用 harness-kit 接入或改造存量项目、接手项目、建计划、完成前验证、发布前检查、交接、升级 kit、反馈 kit 缺陷或文档不一致。
36 other projects use a version of this.
Adopted by
Most recently taken up by
- manhquydev/flow-skilltheir own version, first seen Nov 13, 2026
- hanzhangzzz/agent-skills-zhtheir own version, first seen Oct 29, 2026
- anlmalabs/skillstheir own version, first seen Oct 25, 2026
- gutomec/nirvana-os-enginetheir own version, first seen Oct 13, 2026
- es6kr/skillstheir own version, first seen Oct 13, 2026
- manuelcozar55/setup-claude-codetheir own version, first seen Oct 13, 2026
Used with
Projects with it also use retro, verify and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AWSSkillretro
Conduct a retrospective on a coding session.
Also in 3 projects that use this
Microsoft AzureSkillverify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 4 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
SentrySkillskill-creator
Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.
Also in 3 projects that use this
Other versions36 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 36
- revfactory/harness★ 9.1ksame name
- cexll/myclaude★ 2.8ksame name
- Simpleyyt/ai-manus★ 1.6ksame name
- BankrBot/skills★ 1.2ksame name
- BankrBot/openclaw-skills★ 1.2ksame name
- bam-bam-2/solo-skills★ 366same name
- serejaris/personal-corp-os★ 244same name
- serejaris/ris-claude-code★ 243same name
- SensorsIot/Embedded-AI-Harness★ 235same name
- skillsynchq/txcript★ 208same name
26 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
harness · 项目入口
0. 先定位 kit,再看状态
- kit 位置(按顺序,找到即停,不要猜):
- 用户级安装记录:
~/.agents/skills/.harness-kit-skill.json的kitRoot; - 仓库内或父目录的
harness-kit/VERSION; - 都没有:问用户一次 kit 路径。
- 用户级安装记录:
- 版本核对:读
<kit>/VERSION;低于 front matter 的min_version时提示升级 kit 并重装 skill(<kit>/scripts/harness-skill install --scope user --force),不自行改仓库。 - 已接入(仓库有
tools/harness.py):运行python3 tools/harness.py status --json,按输出路由。 - 未接入(没有
tools/harness.py):走references/adopt.md;不要伪造make/ 门禁输出。
宿主支持斜杠调用时(DSH / Qoder CN / Claude Code 的输入框有「技能」补全),用
/harness显式加载本 skill;也按 description 自动触发。本 skill 是默认入口。只有不支持 skills 的宿主才用提示词兜底:
<kit>/scripts/harness-prompt copy <场景>(或docs/agent-prompts.md)。两者冲突时以本 skill + kit 文档为准。
1. 按意图路由
| 意图 | 动作 |
| 接入新项目 / 改造存量项目 | references/adopt.md |
| 接手 / 继续 / 做到哪了 | status + references/status.md |
| 提需求 / 建计划 / 需求验收 | references/plan.md(start 或 intake) |
| 实现 / 修 bug / 重构 / 依赖升级 | references/build.md |
| 完成前验证 / 证据 / 三值判定 | references/verify.md(verify) |
| Code Review / PR 前自检 / 对抗评审 | references/review.md |
| 发布 / 安全检查 / 性能 | references/release.md(release --check) |
| 交接 / 换 Agent / 多 Agent 分工 | references/collaborate.md(handoff) |
| 升级 harness-kit | references/upgrade.md |
| 反馈 kit 缺陷 / 文档不一致 / 需要新能力 | references/feedback.md |
2. 硬约束(不可协商)
- 作用域:只改计划
scope.allow覆盖的文件;越界先停下更新计划并说明。 - 证据:没有证据不写“已完成/已验证”;未运行写“未验证 + 手动步骤”。test-count PASS 需要可重算 artifact(JUnit XML),证据 JSON 与 artifact 都必须 git 入库;归档证据不参与判定。
- 归档:
_archive计划/证据是历史快照,不是当前状态;没有 active 计划时先读 status/handoff 的归档回读,再决定新建计划。 - 门禁:
make check/harness.py verify红了先修根因;不删除、不弱化、不绕过门禁。 - 反馈上游:kit 自身缺陷/文档不一致先按
references/feedback.md交回上游(https://github.com/DavidTeam2008/harness-engineering-kit/issues);不改宿主tools/或 kit 模板来绕过(升级会覆盖)。 - 问人:push、发布、删除、改规则/门禁、
--force覆盖前先问。 - 单一状态源:计划与证据是仓库文件;不把进度只留在对话里。
- 不装 skill 也能工作:skill 只是入口;所有事实与流程都在仓库文件和 kit 文档里。
3. 输出协议(固定五段)
- 结论(做了什么/当前判断)
- 证据(命令 + 退出码 + evidence id;没有就写未验证)
- 未验证项
- 下一步(1 条可执行动作)
- 需要人决策的点
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

