What makes qa-expert-review notable?

1.1K downloads. Trust evidence available

How should qa-expert-review be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

qa-expert-review

当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。触发场景：专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: final human-style review of AI-generated test cases before shipping, sampling for business validity, scenario completeness, and executability. Skill: qa-expert-review Owner: kokxi Summary: 当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。触发场景：专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: final human-style review of AI-generated test cases before shipping, sampling for business validity, scenario completeness, and executabili

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.8.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.8.0release · observed Sep 29, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-expert-review

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-expert-review/snapshot"

Documentation

CLAWHUB

72,312 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: qa-expert-review
description: >-
  当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。 触发场景：专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: final human-style review of AI-generated test cases before shipping, sampling for business validity, scenario completeness, and executability.
license: MIT
allowed-tools: Read Grep Glob
metadata:
  display-name: "Expert Review"
  version: "1.8.0"
  when-to-use: "用户说\"专家评审\"、\"用例审查\"、\"校正反馈\"、\"评审用例\"、\"检查用例\"、\"终审\"、需要对AI输出进行质量把关、用例上线前需要终审时"
  related-skills: "{\"upstream\":[\"qa-ai-output-critique\",\"qa-ai-blindspot-compensation\"],\"downstream\":[\"qa-test-reporting\",\"qa-retrospective\"]}"
  references: "[\"references/meta-learning.md\"]"
  input-format: "{\"required\":[{\"name\":\"测试用例\",\"type\":\"array\",\"description\":\"AI生成的测试用例列表\"}],\"optional\":[{\"name\":\"需求文档\",\"type\":\"string\",\"description\":\"原始需求文档，用于校验覆盖度\"},{\"name\":\"历史校正数据\",\"type\":\"array\",\"description\":\"历史评审的校正记录，用于模式分析\"}]}"
  output-format: "{\"structure\":[\"覆盖率：标注口径（基于现有需求/输入文档），禁止\\\"全覆盖/100%\\\"绝对化表述；缺失模块标注\\\"未覆盖+原因\\\"\",{\"review_id\":\"REV-XXXX\"},{\"review_summary\":\"评审摘要\"},{\"sampling_rate\":\"抽样比例\"},{\"issues_found\":\"问题列表\"},{\"corrections\":\"校正建议\"},{\"learning_points\":\"学习要点\"},{\"prompt_optimization\":\"Prompt优化建议\"}],\"traceability\":[\"每次评审带唯一ID（REV-XXXX）\",\"关联用例ID（TC_{模块缩写}_{功能缩写}_{序号}，如 TC_API_LOGIN_001）\",\"关联需求ID：REQ-{需求模块缩写}-{序号}\"]}"
  error-recovery-guidance: "{\"on_failure\":\"评审发现系统性问题时回退到输出评审步骤修正\",\"retry_behavior\":\"修正后重新抽样校验\"}"
  categories: "[\"Development\",\"Testing\",\"Quality\"]"
  depth-requirement: "{\"reference_value\":\"根据项目重要性和风险等级调整评审深度：简单x1/中等x2/复杂x3\",\"minimum\":\"至少覆盖功能完整性、边界充分性、异常覆盖性3个维度\"}"
---
> ⚠️ 本技能单独使用效果有限，建议配合完整技能集（12 步工作流）使用。安装：npx skills add Kokxi/qa-test-skills

# 专家评审与元学习

## 核心原则

专家评审不是挑错，而是建立"AI生成→专家校验→持续优化"的正向循环。

## 评审流程

### 第1步：抽样策略

```text
抽样方法：
├─ 随机抽样：10-20%的用例
├─ 分层抽样：P0用例100%覆盖，P1抽样50%，P2抽样20%
├─ 风险抽样：高风险用例100%覆盖
└─ 新功能抽样：新功能用例100%覆盖

抽样公式：
总用例数 < 50 → 全量评审
总用例数 50-200 → 20%抽样
总用例数 > 200 → 10%抽样 + P0全量
```

### 第2步：评审维度

| 维度 | 检查点 | 权重 |
|------|--------|------|
| 完整性 | 是否覆盖所有需求点？ | 30% |
| 准确性 | 测试步骤和预期结果是否正确？ | 25% |
| 可执行性 | 步骤是否清晰可执行？ | 20% |
| 风险覆盖 | 高风险区域是否深测？ | 15% |
| 规范性 | 格式是否符合标准？ | 10% |

### 第3步：校正标记

```text
校正标记格式：
├─ [C-001] 问题类型：描述问题
├─ [C-002] 问题类型：描述问题
└─ ...

问题类型：
├─ MISSING：缺失场景
├─ WRONG：步骤/预期错误
├─ VAGUE：描述模糊
├─ REDUNDANT：冗余用例
├─ RISK：风险覆盖不足
└─ FORMAT：格式不规范
```

### 第4步：输出评审报告

```markdown
# 专家评审报告

## 评审摘要
- 评审ID：REV-XXXX
- 评审日期：YYYY-MM-DD
- 评审专家：[姓名]
- 用例总数：XX条
- 抽样数量：XX条（抽样比例XX%）

## 评审结果
| 维度 | 评分 | 问题数 |
|------|------|--------|
| 完整性 | X/10 | X个 |
| 准确性 | X/10 | X个 |
| 可执行性 | X/10 | X个 |
| 风险覆盖 | X/10 | X个 |
| 规范性 | X/10 | X个 |
| 综合评分 | X/10 | - |

## 问题清单
| 用例编号 | 问题类型 | 问题描述 | 校正建议 |
|---------|---------|---------|---------|
| TC_XXX_001 | MISSING | 缺少并发场景 | 补充并发测试用例 |
| TC_X

_meta.json

{
  "ownerId": "kn71y9b23csfx0ykgm55d5m9x5891zt8",
  "slug": "qa-expert-review",
  "version": "1.8.0",
  "publishedAt": 1790655995102
}

references/meta-learning.md

# 评审反馈元学习机制详解

> 本文是 `qa-expert-review` 的**评审反馈元学习机制详解**。把评审反馈沉淀为可复用资产时读本文；
其余部分留在 SKILL.md，不必读本文。

---


### 校正数据收集

```text
收集内容：
├─ 问题类型分布
├─ 高频问题模式
├─ 专家校正建议
├─ 用例质量趋势
└─ 改进效果跟踪

存储格式：
{
  "review_id": "REV-001",
  "date": "2024-01-01",
  "issues": [
    {
      "type": "MISSING",
      "count": 5,
      "pattern": "缺少并发场景",
      "correction": "补充并发测试"
    }
  ],
  "learning_points": [...]
}
```

### 模式识别

```text
识别方法：
├─ 问题聚类：识别相似问题
├─ 趋势分析：问题数量变化
├─ 根因分析：为什么会出现这个问题
└─ 改进验证：改进措施是否有效

输出：
├─ 高频问题TOP5
├─ 问题趋势图
├─ 改进建议
└─ 效果评估
```

### Prompt优化

```text
优化流程：
1. 分析校正数据
2. 识别Prompt不足
3. 生成优化建议
4. 测试优化效果
5. 持续迭代

优化示例：
原Prompt："生成登录模块的测试用例"
优化后："生成登录模块的测试用例，需覆盖：
1. 正常登录流程
2. 异常场景（密码错误、账号锁定）
3. 边界条件（密码长度、特殊字符）
4. 并发场景（多设备同时登录）
5. 安全场景（SQL注入、XSS）"
```

skill-card.md

## Description:

Guides a final, risk-aware review of AI-generated test cases for business validity, scenario coverage, and executability before release.

This skill is ready for commercial/non-commercial use.

## Publisher:

[kokxi](https://clawhub.ai/user/kokxi)

### License/Terms of Use:

MIT-0

## Use Case:

QA engineers and reviewers use this skill to sample and assess AI-generated test cases, document defects and corrections, and feed recurring findings into future test-case generation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Installing the suggested broader skill set could run code from an unverified source.

Mitigation: Verify the Kokxi/qa-test-skills source and prefer a pinned version or trusted commit before running the suggested npx command.

Risk: Sampling can miss important gaps in AI-generated test cases.

Mitigation: Review all highest-priority and high-risk cases, trace coverage to available requirements, and repeat review after correcting systematic gaps.

## Reference(s):

- [Meta-learning reference](references/meta-learning.md)
- [ClawHub skill release](https://clawhub.ai/kokxi/skills/qa-expert-review)

## Skill Output:

**Output Type(s):** [Text, Markdown, Guidance]

**Output Format:** [Markdown review report with scores, issue table, corrections, and improvement recommendations]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes review and test-case IDs, sampling rate, requirements traceability, and prompt-optimization suggestions.]

## Skill Version(s):

1.8.0 (source: skill frontmatter and ClawHub release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.