auto-qa
在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。
Skill by LeoYeAI
Chalk Labs
Need help deploying auto-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/leoyeai-auto-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, agent-building
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/auto-qa
What's inside
- Skill name
auto-qa- Description
- 在 OpenClaw 平台执行网页自动 QA 测试(自动操作 + 采证 + 报告 + 修复提示包)。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。
- License
- MIT
- Instructions
- 471 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (9)
- SKILL.md
- _meta.json
- state_snapshot_20260220.md · references/
- generic_visual_template.json · scenarios/
- mvp_smoke.json · scenarios/
- registry.json · scenarios/
- wehub_visual_demo.json · scenarios/
- wehub_visual_release.json · scenarios/
- run_autoqa.py · scripts/
SKILL.md (first lines)
# Auto QA (OpenClaw Browser)
用于一期 MVP:
- 自动执行网页关键路径
- 自动采集失败证据(截图、console、network、trace)
- 自动输出 CTO 可读报告与修复任务包
- 自动重试、断点续跑、健康检查与失败分类(环境/产品)
## 实际组件构成(一期 MVP)
1. `场景定义组件`
- 位置:`demo/scenarios/*.json`
- 作用:声明测试步骤、断言条件、期望结果。
- 输入:业务路径(P0 场景)。
- 输出:可执行步骤序列(供执行编排器读取)。
2. `执行编排器`
- 位置:`src/skills/auto-qa/scripts/run_autoqa.py`
- 作用:读取场景并调用 `openclaw browser` 执行动作。
- 输入:场景 JSON、浏览器 profile、run_id。
- 输出:步骤结果、证据文件、汇总报告与修复提示包。
3. `浏览器执行器(OpenClaw 内置能力)`
- 位置:OpenClaw CLI `openclaw browser ...`
- 作用:点击、输入、等待、快照、截图、日志与 trace。
- 输入:编排器下发的步骤参数。
- 输出:结构化 JSON 结果和调试数据。
4. `证据归档组件`
- 位置:`demo/artifacts/run-<run_id>/`
- 作用:按 run 归档步骤明细、截图、console、network、trace。
- 输入:执行过程中的实时证据。
- 输出:可追溯的失败证据包。
5. `报告生成组件`
- 位置:`demo/reports/run-<run_id>/report.json`、`demo/reports/run-<run_id>/report.html`
- 作用:给出通过率、阻断项、Go/No-Go 判定。
- 输入:步骤结果 + 证据统计。
- 输出:机器可读(JSON)与演示可读(HTML)报告。
6. `修复任务包生成组件`
- 位置:`demo/reports/run-<run_id>/fix_plan.json`、`next_window_prompt.md`、`standby_prompt.txt`
- 作用:将"测试失败证据"转成"可直接执行的修复任务"。
- 输入:失败步骤、console、network、trace 路径。
- 输出:根因假设、检查方向、修改方向、验收标准、下一窗口提示词。
7. `稳定性增强组件`
- 位置:`src/skills/auto-qa/scripts/run_autoqa.py`
- 作用:减少"主画面外运行"时的抖动风险,提升演示稳定度。
- 能力:
- 步骤自动重试(默认每步 1 次重试)
- 断点续跑(从失败步骤继续)
- 健康检查(off/on-failure/each-step)
- 失败分类(environment/product/unknown)
8. `门禁断言组件`
- 位置:`src/skills/auto-qa/scripts/run_autoqa.py`
- 作用:将采证数据升级为发布门禁判定,防止"假 GO"。
- 默认规则:
- console `error` -> 违规(critical)
- 同域 network `4xx` -> 违规(critical)
- 同域 network `5xx` -> 违规(blocker)
- 报告输出:
- `gateViolations`
- `gateViolationCountsBySeverity`
- `riskLevel`
- `releaseDecision`(GO / CONDITIONAL_GO / NO_GO)
- `reviewStatus`(consistent / needs_inspection)
- `reviewConclusion`(复核一致 / 复核需进一步检验)
- `reviewFindings`(需进一步检验时的具体项)
9. `Trace 对齐组件`
- 位置:`demo/reports/run-<run_id>/step_trace_map.json`
- 作用:把步骤时间窗与 trace 时间线自动对齐,便于"步骤 -> 证据"快速追溯。
- 输出:每个步骤对应的 trace 事件计数、帧计数、console/API/network 样本。
10. `报告通知组件`
- 位置:`src/skills/auto-qa/scripts/run_autoqa.py`(运行参数触发)
- 作用:自动截取 `report.html` 全页图并发送到聊天频道。
- 规则:
- 传入 `--notify-channel` 时触发。
- 未传 `--notify-target` 时,自动从 `openclaw status --json` 最近会话推断目标(当前频道优先)。
## 一期范围(防跑偏)
- 仅网页 P0 场景(3-5 条关键路径)
- 证据四件套:`screenshot + console + network + trace`
- 交付最小集合:
- `report.json`
- `report.html`
- `fix_plan.json`
- `next_window_prompt.md`
- `standby_prompt.txt`
## 目录约定
```text
demo/
scenarios/
mvp_smoke.json
_generated/ ← agent 智能生成的临时 scenario 存放目录
artifacts/
run-<run_id>/
steps.json
console.json
network.json
health_checks.json
trace.zipFrom LeoYeAI/openclaw-master-skills, MIT.
More from LeoYeAI/openclaw-master-skills
- 0.734score
audit-website
squirrelscan
Audit websites for SEO, performance, security, technical, content, and 15 other issue cateories with 230+ rules using the squirrelscan CLI.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.734score
arista-device-health
network-security-skills-suite
Arista EOS device health check and triage procedure.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.733score
analyticscli-ts-sdk
wotaso
Use when integrating or upgrading the AnalyticsCLI TypeScript SDK in web, TypeScript, React Native, or Expo apps.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.731score
ai-headshot-generation
eachlabs
Generate professional AI headshots from casual photos using each::sense AI.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.731score
acl-rule-analysis
network-security-skills-suite
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule…
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.729score
agentic-street
agentic-street
Earn yield on USDC by investing in AI-managed DeFi funds, or launch your own fund and build a public track record on Base.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.728score
aureus-arena
aureus-arena
Build and operate autonomous AI agents that compete in Aureus Arena, a fully on-chain Colonel Blotto game on Solana.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.728score
agent-bom
msaad00
Open security platform for agentic infrastructure — broad scanning plus MCP discovery, CVEs, blast radius, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowflake)…
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.727score
aster-futures
Aster
Aster Futures request using the Aster API.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.725score
anvevoice
AnveVoice
Add AI voice assistants to your website.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.724score
anima
animaapp
Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.719score
xaut-trade
aurehub
Buy or sell XAUT (Tether Gold) on Ethereum.
SkillCFreshness: C★ 2.2KClaude Code +9
Signals
- Stars
- 2,168
- Forks
- 325
- Open issues
- 13
- Last commit (this folder)
- Jun 8, 2026 (4 months ago)
- Last release
- Jul 20, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Website
- myclaw.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LeoYeAI
- 0.552score
aavegotchi-gbm-skill
LeoYeAI
View, create, cancel, bid, and claim Aavegotchi GBM auctions on Base mainnet (8453).
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.552score
aqara-open-api
LeoYeAI
Query and control Aqara/Lumi Studio smart home devices and manage spaces via the Aqara Open Platform API (HTTP JSON).
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.552score
aawp
LeoYeAI
AAWP (AI Agent Wallet Protocol) — the only crypto wallet protocol built exclusively for AI Agents on EVM-compatible blockchains.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.552score
ai-task-hub
LeoYeAI
AI task hub for image analysis, background removal, speech-to-text, text-to-speech, markdown conversion, and async execute/poll/presentation orchestration.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.552score
animation-shader
LeoYeAI
READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap…
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.552score
adaptive-learning-playbook
LeoYeAI
World-Class Adaptability & Learning Playbook.
SkillCFreshness: C★ 2.2KClaude 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-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-qa skill. Agent Mart. https://agentmart.dev/skills/leoyeai-auto-qa (last updated 2026-10-24)