auto-harness-qa
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.
Skill by duoglas
Chalk Labs
Need help deploying auto-harness-qa?
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-qa
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-qa
What's inside
- Skill name
auto-harness-qa- Description
- 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.
- License
- MIT
- Instructions
- 149 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/shk.js
Files (1)
- SKILL.md
SKILL.md (first lines)
# Harness QA
执行 5 层 QA 金字塔的自动化部分(Layer 1-4),生成结构化报告。
## 何时使用
- 完成一个功能或重要代码变更后
- 提交代码前
- 创建 PR 前
- 用户说"跑 QA"或"验证一下"
## 执行流程
### 首选入口:Quality Gate Suite
如果项目存在 `scripts/shk.js`,优先使用结构化准出入口:
```bash
node scripts/shk.js verify --risk medium --write-evidence
```
高风险或发布前改用:
```bash
node scripts/shk.js verify --risk high --write-evidence
node scripts/shk.js verify --risk release --write-evidence
```
该命令会生成:
- `.harness/verify-evidence.json` — `verification-gate.js` 优先读取的机器证据
- `.harness/verify-evidence.md`
- `docs/verification-report.md`
如果 `scripts/shk.js` 不存在,再按下面的手动 Layer 1-4 流程执行。
### Layer 1: Agent Self-Verification
检查当前变更是否有对应测试:
```bash
git diff --name-only | grep -E '\.(ts|js|py|go|rs)$'
# 对每个变更文件,检查是否有对应测试文件
```
如果改的是已有接口、数据格式、模板或 gate,必须同时有正例、负例,以及旧路径或混合新旧输入的兼容用例。medium / high / release 任务至少保留一个负向或边界验证。
### Layer 2: Verification Loop
按顺序执行,任一失败则停止并报告:
```bash
# Phase 1: Build
{{构建命令}}
# Phase 2: Type Check
{{类型检查命令}}
# Phase 3: Lint
{{lint 命令}}
# Phase 4: Test + Coverage
{{测试命令}} --coverage
# Phase 5: Security Scan
grep -rn "sk-\|api_key\|password\|secret" {{源码目录}}/ --include="*.{{ext}}"
# Phase 6: Diff Review
git diff --stat
```
### Layer 3: Spec Compliance Review
如果有 spec 文档:
1. 启动独立 Reviewer Agent
2. 传入 spec + 代码变更
3. 逐项对照检查
4. 输出 PASS/FAIL 清单
### Layer 4: Santa Method(可选,高风险时启用)
1. 启动两个独立 Reviewer Agent
2. 相同 rubric,独立上下文
3. 都通过 → NICE
4. 任一不通过 → 收集 issues → 修复 → 重新双 Review(max 3 轮)
## 输出格式
```
HARNESS QA REPORT
==================
Layer 1 - Self Verification:
Tests exist for changes: [YES/NO]
TDD compliance: [YES/NO/PARTIAL]
Layer 2 - Verification Loop:
Build: [PASS/FAIL]
Types: [PASS/FAIL] (N errors)
Lint: [PASS/FAIL] (N warnings)
Tests: [PASS/FAIL] (X/Y passed, Z% coverage)
Security: [PASS/FAIL] (N issues)
Diff: [N files, +X/-Y lines]
Layer 3 - Spec Compliance:
Verdict: [PASS/FAIL/SKIPPED]
Details: [逐项清单]
Layer 4 - Santa Method:
Verdict: [NICE/NAUGHTY/SKIPPED]
Round: [N/3]
Details: [双 Reviewer 报告]
Overall: [READY / NOT READY]
Issues: [待修复问题列表]
```
报告写入验收证据文件,路径由 `node scripts/shk.js verify --write-evidence` 自动解析——
有当前任务时落 `<tasks_dir>/<TASK-ID>/evidence/verify-evidence.json`,否则落
`.harness/verify-evidence.json`。不要手工拼路径。From duoglas/simple-harness-kit, MIT.
More from duoglas/simple-harness-kit
- 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 - 0.655score
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-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 - 0.654score
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 - 0.654score
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
auto-harness-test-bootstrap
duoglas
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.
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
Signals
- Stars
- 39
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Jul 26, 2026 (3 months ago)
- Last release
- Oct 9, 2026 (26 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-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 - 0.655score
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-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 - 0.654score
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
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-qa 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-qa skill. Agent Mart. https://agentmart.dev/skills/duoglas-auto-harness-qa (last updated 2026-10-24)