auto-harness-test-bootstrap
为缺少测试的已有项目渐进式补充多层自动化测试覆盖。Use when project has low or no test coverage and needs automated test generation.
Skill by duoglas
Chalk Labs
Need help deploying auto-harness-test-bootstrap?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/duoglas-auto-harness-test-bootstrap
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/auto-harness-test-bootstrap
What's inside
- Skill name
auto-harness-test-bootstrap- Description
- 为缺少测试的已有项目渐进式补充多层自动化测试覆盖。Use when project has low or no test coverage and needs automated test generation.
- License
- MIT
- Instructions
- 204 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Harness Test Bootstrap
为缺少测试的已有项目建立多层自动化测试覆盖。AI 分析代码、生成测试、运行验证、迭代补充——用户只做验收。
这不是单纯“补几个测试文件”。SHK 在目标工程里的职责是完整链路:
1. **测试生成**:根据 spec、工程类型和风险,为目标工程生成单测、API E2E、浏览器 E2E 或组合测试。
2. **有效测试验证**:检查测试是否覆盖需求、风险、流量路径、断言、正向、负向/边界和 mutation/fault 证据。
3. **交付准出**:只有 spec、test effectiveness、E2E sufficiency 和基础 gate 都 READY,AI 才能说可以交付。
## 何时使用
- 项目测试覆盖率低或为零
- 团队长期依赖人工测试,想转自动化
- 用户说"补测试"、"加测试覆盖"、"建立测试体系"
## 核心原则
1. **AI 写测试,人验收** — 用户不需要自己写任何测试代码
2. **渐进式,不一步到位** — 先高风险模块,再逐步扩展
3. **先搭基础设施,再生成测试** — 没有测试框架就先装
4. **测试现有行为,不是理想行为** — 先锁定当前行为,再讨论要不要改
5. **新应用没有 E2E 时,AI 要生成第一套** — 不能只报告“缺 E2E”就停下
6. **E2E PASS 不等于充分** — fake、空脚本、只 smoke、坏代码也能 PASS 的 E2E 都不能交付
## 执行流程
### Phase 1:分析(AI 自动完成)
AI 扫描项目,输出分析报告:
如果是新应用工程或 UI/API 相关任务,先跑后端识别器:
```bash
node scripts/shk.js spec status --risk medium --format json
node scripts/shk.js e2e inspect --format json
node scripts/shk.js e2e bootstrap --risk medium --format json
```
这两个命令是给 AI 读的,不是让用户背命令。AI 要根据输出判断:
- 这是 Web、fullstack、API service,还是未知项目;
- 本地启动命令是什么;
- 有没有 Playwright / Cypress / API E2E;
- 没有 E2E 时,该生成 Playwright、Cypress 还是 API E2E;
- 如果无法判断,只问用户一个具体问题。
- 如果缺少 `.harness/iteration-spec.json`,AI 要先补一份短 spec:需求、方案、风险、测试计划、流量路径、验收标准。
```
测试分析报告
============
技术栈: [自动识别]
现有测试: [框架/覆盖率/数量,如果有]
建议测试框架: [根据技术栈推荐]
模块风险评估:
高风险: src/auth/(认证逻辑,无测试)
高风险: src/api/(对外接口,无测试)
中风险: src/utils/(工具函数,部分测试)
低风险: src/components/(展示组件)
建议优先级:
1. src/auth/ — 先补单元测试
2. src/api/ — 补集成测试
3. 关键页面 — 补 E2E 测试
```
→ **暂停,等用户确认优先级。**
### Phase 2:搭建测试基础设施
如果项目没有测试框架,AI 自动搭建:
- 安装测试依赖(根据技术栈自动选择)
- 创建配置文件
- 写一个 smoke test 验证环境可用
- 配置覆盖率报告
→ 运行 smoke test 确认环境 OK。
如果项目没有 E2E,AI 必须进入 E2E bootstrap:
- Web/fullstack 默认生成 Playwright;
- 已有 Cypress 则沿用 Cypress;
- API-only 生成 API E2E,不强行上浏览器;
- 必须写 `.harness/task-quality-contract.json`;
- 第一版至少有 1 个正向路径、1 个负向/阻断路径、真实断言和结构化 evidence。
### Phase 3:按优先级生成测试
对每个模块,按 3 步循环:
```
Step 1: AI 读代码,理解现有行为
Step 2: 生成测试(覆盖正常路径 + 边界 + 错误处理)
Step 3: 运行测试
→ 全部通过 → 记录覆盖率,进入下一个模块
→ 有失败 → 分析原因:
- 测试写错了 → AI 修测试
- 发现真实 bug → 记录到 constraints.md(不自动修,等用户决定)
```
### Phase 4:多层测试覆盖
根据项目类型,逐层补充:
**Layer 1 — 单元测试(最先补)**
```
目标: 所有公开函数/方法
方法: AI 读函数签名和实现 → 生成测试 → 运行
覆盖: 正常输入、边界值、空值、异常输入
```
**Layer 2 — 集成测试(API/数据库项目)**
```
目标: API 端点、数据库操作、服务间调用
方法: AI 分析路由/ORM → 生成请求级测试
覆盖: 正常请求、参数校验、权限、错误码
```From duoglas/simple-harness-kit, MIT.
More from duoglas/simple-harness-kit
- 0.655score
auto-harness-review
duoglas
执行交付前 5 项复盘检查,确保流程合规和质量达标。Use when about to deliver work to users, before final handoff, or when completing a development cycle.
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
harness-start
duoglas
启动 Harness 任务(交互式收集需求,自动带上全部流程约束)。Use when starting a new feature, task, or any development work in a Harness-enabled project.
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
git-commit
duoglas
AI 智能生成 commit message 并分批提交。读取 active preset 的 subject 格式、type 枚举、分支规则、业务词归一表,自动适配 generic / example-company / 公司自定义 preset。**不自动 push** —— push 时机交回 shk 的…
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
auto-harness-loop-fix
duoglas
在 AI 工具内执行受控自动修复 loop。Use when tests, E2E, quality gate, or verification fails and the user expects the agent to fix and rerun instead of only reporting…
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
auto-harness-learn
duoglas
分析 session 观察数据,提取行为模式生成 instinct,给出改进建议和 Token 优化提议。Use when user says "分析学习数据"、"看看有什么模式"、"harness learn"。
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
auto-harness-santa
duoglas
执行 Santa Method 双独立对抗验证。Use when reviewing high-risk changes, production deployments, or complex logic before shipping.
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
harness-feedback
duoglas
执行 F1-F5 结构化反馈处理流程,从问题中提炼规则并写入约束系统。Use when receiving bug reports, user feedback, review findings, or test failures.
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
harness-off
duoglas
临时关闭 Harness 模式(本会话)。Use when you need to use other skills or do non-development tasks without Harness 6-stage loop.
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
harness-on
duoglas
重新启用 Harness 模式。Use when you want to resume Harness 6-stage loop after /harness-off.
SkillAFreshness: A★ 39Claude Code +9 - 0.651score
harness-init
duoglas
为当前项目初始化完整的 Harness Engineering 配置(Rules、Hooks、Constraints、QA 标准)。Use when bootstrapping a new project or adding harness to an existing project.
SkillAFreshness: A★ 39Claude Code +9 - 0.650score
auto-harness-qa
duoglas
执行 5 层 QA 金字塔检查,生成量化验证报告。Use when completing a feature, before committing, or before creating a PR.
SkillAFreshness: A★ 39Claude Code +9
Signals
- Stars
- 39
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Jun 5, 2026 (5 months ago)
- Last release
- Oct 9, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/duoglas/simple-harness-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from duoglas
- 0.655score
auto-harness-review
duoglas
执行交付前 5 项复盘检查,确保流程合规和质量达标。Use when about to deliver work to users, before final handoff, or when completing a development cycle.
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
harness-start
duoglas
启动 Harness 任务(交互式收集需求,自动带上全部流程约束)。Use when starting a new feature, task, or any development work in a Harness-enabled project.
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
git-commit
duoglas
AI 智能生成 commit message 并分批提交。读取 active preset 的 subject 格式、type 枚举、分支规则、业务词归一表,自动适配 generic / example-company / 公司自定义 preset。**不自动 push** —— push 时机交回 shk 的…
SkillAFreshness: A★ 39Claude Code +9 - 0.655score
auto-harness-loop-fix
duoglas
在 AI 工具内执行受控自动修复 loop。Use when tests, E2E, quality gate, or verification fails and the user expects the agent to fix and rerun instead of only reporting…
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
auto-harness-learn
duoglas
分析 session 观察数据,提取行为模式生成 instinct,给出改进建议和 Token 优化提议。Use when user says "分析学习数据"、"看看有什么模式"、"harness learn"。
SkillAFreshness: A★ 39Claude Code +9 - 0.654score
auto-harness-santa
duoglas
执行 Santa Method 双独立对抗验证。Use when reviewing high-risk changes, production deployments, or complex logic before shipping.
SkillAFreshness: A★ 39Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get auto-harness-test-bootstrap running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
auto-harness-test-bootstrap skill. Agent Mart. https://agentmart.dev/skills/duoglas-auto-harness-test-bootstrap (last updated 2026-10-24)