Skip to content
Agentmart
Submit a tool

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

IndexedMIT★ 2,168
Write a review

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.

Book a call

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.

We use your email only for this newsletter. Privacy

About

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。

Use cases: testing, agent-building

No 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.zip

From LeoYeAI/openclaw-master-skills, MIT.

More from LeoYeAI/openclaw-master-skills

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

More from LeoYeAI

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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying auto-qa?

CallGet help
Cite this page

auto-qa skill. Agent Mart. https://agentmart.dev/skills/leoyeai-auto-qa (last updated 2026-10-24)