What makes qa-ai-blindspot-compensation notable?

1.2K downloads. Trust evidence available

How should qa-ai-blindspot-compensation 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-ai-blindspot-compensation

AI在生成测试用例时存在六大系统性盲区：时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后，必须用此技能做盲区补盲——因为AI几乎一定会漏掉这些。如果你心里觉得"好像还差点什么但说不上来"，这就是答案。每个盲区维度至少补2-3个场景，总补盲数12-18个。触发场景：还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compensating for known blind spots in AI-generated test cases — timing dependencies, concurrency conflicts, resource contention, state accumulation, data consistency, and third-party integration differences. Skill: qa-ai-blindspot-compensation Owner: kokxi Summary: AI在生成测试用例时存在六大系统性盲区：时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后，必须用此技能做盲区补盲——因为AI几乎一定会漏掉这些。如果你心里觉得"好像还差点什么但说不上来"，这就是答案。每个盲区维度至少补2-3个场景，总补盲数12-18个。触发场景：还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compensating for known blind spots in AI-generated test cases — timing dependencies, concurrency conflicts, resource contention, s

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

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. 1.2K 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: 1.2K 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-ai-blindspot-compensation

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-ai-blindspot-compensation/snapshot"

Documentation

CLAWHUB

87,810 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: qa-ai-blindspot-compensation
description: >-
  AI在生成测试用例时存在六大系统性盲区：时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后，必须用此技能做盲区补盲——因为AI几乎一定会漏掉这些。如果你心里觉得"好像还差点什么但说不上来"，这就是答案。每个盲区维度至少补2-3个场景，总补盲数12-18个。 触发场景：还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compensating for known blind spots in AI-generated test cases — timing dependencies, concurrency conflicts, resource contention, state accumulation, data consistency, and third-party integration differences.
license: MIT
allowed-tools: Read Grep Glob
metadata:
  display-name: "Ai Blindspot Compensation"
  version: "1.8.0"
  when-to-use: "AI输出评审完成后自动激活；用户说\"还有什么没测到\"、\"AI漏了什么\"、\"补盲\"、\"全面覆盖\"、\"是不是不够\"、\"哪还没测\"、\"盲区分析\"、\"遗漏场景\"时"
  related-skills: "{\"upstream\":[\"qa-ai-output-critique\"],\"downstream\":[\"qa-test-skills\",\"qa-expert-review\",\"qa-output-validation\"]}"
  references: "[\"references/blindspot-details.md\"]"
  input-format: "{\"required\":[{\"name\":\"测试用例\",\"type\":\"array\",\"description\":\"AI生成的测试用例列表，包含用例编号、需求ID、风险ID\"},{\"name\":\"需求解构表\",\"type\":\"object\",\"description\":\"来自qa-req-deconstruction，包含需求ID列表\"}],\"optional\":[{\"name\":\"评审报告\",\"type\":\"object\",\"description\":\"来自qa-ai-output-critique的评审结果\"}]}"
  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\\\"\",{\"blindspot_id\":\"BS-XXXX\"},{\"requirement_ids\":[\"REQ-XXXX\"]},{\"original_tc_ids\":[\"TC_{模块缩写}_{功能缩写}_{序号}\"]},{\"blindspot_type\":\"盲区类型\"},{\"new_test_cases\":\"补盲用例列表\"}],\"traceability\":[\"每个补盲用例带唯一ID（BS-XXXX）\",\"关联原始用例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\":\"盲区补盲遗漏维度时回退到评审报告定位遗漏点\",\"retry_behavior\":\"补充遗漏盲区类型后重新生成补盲用例\"}"
  categories: "[\"Development\",\"Testing\",\"AI\"]"
  depth-requirement: "{\"reference_value\":\"根据测试复杂度和风险等级调整补盲深度：简单x1/中等x2/复杂x3\",\"minimum\":\"至少覆盖边界盲区、场景盲区、数据盲区3个维度中的2个\"}"
---
> ⚠️ 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

# AI 盲区补偿

## 核心原则

AI有系统性的盲区，专家知道在哪些维度上主动补盲。

**关键指标**：每个盲区至少补充2-3个测试场景，六大盲区 × 每个2-3个场景 = 至少12-18个补盲用例。

## AI 六大已知盲区

> 每个盲区的典型场景、检查清单、补盲问法详见 [`references/blindspot-details.md`](references/blindspot-details.md)。

| 盲区 | AI的典型盲点 | 补盲方向 |
|------|-------------|---------|
| 时序依赖 | 不思考"操作顺序变更"的影响 | 打乱顺序、测试中间状态、验证依赖 |
| 并发冲突 | 不思考"多人同时操作" | 多用户并发、多设备操作、锁机制 |
| 资源竞争 | 不思考"资源耗尽" | 内存/连接/线程/磁盘不足 |
| 状态累积 | 不思考"长时间运行后漂移" | 会话超时、累计操作、缓存过期 |
| 数据一致性 | 不思考"分布式数据问题" | 跨服务同步、分布式事务、主从一致 |
| 第三方集成 | 不思考"Mock与真实差异" | 第三方异常/超时/变更/降级 |

> **国内业务常见实例**（补盲时优先对照）：

| 盲区 | 国内业务实例 |
|------|-------------|
| 时序依赖 | 秒杀活动中"先加购物车后下单"与"直接下单"顺序不同，库存扣减结果差异 |
| 并发冲突 | 双11多用户同时抢同一商品，超卖问题；多人同时编辑同一订单 |
| 资源竞争 | 支付网关连接池耗尽、日志磁盘写满、数据库连接数超限 |
| 状态累积 | 用户会话长期不退出导致 Token 过期/权限漂移；长连接内存泄漏 |
| 数据一致性 | 订单跨服务（订单服务+库存服务+支付服务）分布式事务；主从延迟读 |
| 第三方集成 | 微信支付/支付宝回调超时重试、短信服务商变更、地图/天气第三方异常降级 |

### 补盲检查清单
- [ ] 时序依赖：操作顺序变更是否影响结果？
- [ ] 并发冲突：多人同时操作是否测试？
- [ ] 资源竞争：资源耗尽场景是否覆盖？
- [ ] 状态累积：长时间运行是否测试？
- [ ] 数

_meta.json

{
  "ownerId": "kn71y9b23csfx0ykgm55d5m9x5891zt8",
  "slug": "qa-ai-blindspot-compensation",
  "version": "1.8.0",
  "publishedAt": 1790655892734
}

references/blindspot-details.md

# 六大盲区详解

> 本文档是 `qa-ai-blindspot-compensation` 的参考文件。执行补盲时，按以下六个维度逐一排查。

---

## 盲区1：时序依赖（必检）
**问题**：AI不擅长思考"操作顺序变更"的影响

```
典型场景：
- 操作A必须在操作B之前执行
- 操作A执行后需要等待才能执行操作B
- 操作A和操作B的执行顺序会影响结果

补盲检查清单：
- [ ] 操作顺序变更是否影响结果？
- [ ] 操作中间状态是否处理？
- [ ] 操作依赖关系是否验证？
- [ ] 并发操作的时序是否测试？

补盲问法：
"请检查这些场景中，操作顺序变更会影响结果的情况"
"如果用户不按预期顺序操作，会发生什么？"
"哪些场景有时序依赖？"
```

---

## 盲区2：并发冲突（必检）
**问题**：AI不擅长思考"多人同时操作"的场景

```
典型场景：
- 多人同时编辑同一数据
- 同一用户多设备同时操作
- 并发请求导致数据不一致

补盲检查清单：
- [ ] 多人同时操作是否测试？
- [ ] 多设备同时操作是否测试？
- [ ] 并发请求是否导致数据不一致？
- [ ] 锁机制是否验证？

补盲问法：
"请分析并发场景：多用户同时操作会怎样？"
"如果用户在多个设备同时登录会怎样？"
"并发请求会导致什么问题？"
```

---

## 盲区3：资源竞争（必检）
**问题**：AI不擅长思考"资源耗尽"的场景

```
典型场景：
- 内存泄漏导致服务崩溃
- 数据库连接池耗尽
- 线程池满导致请求排队
- 磁盘空间不足

补盲检查清单：
- [ ] 内存泄漏是否测试？
- [ ] 连接池耗尽是否测试？
- [ ] 线程池满是否测试？
- [ ] 磁盘空间不足是否测试？

补盲问法：
"请分析资源耗尽场景：内存/连接/线程/磁盘不足时会怎样？"
"长时间运行后会出现什么资源问题？"
"高并发下资源会怎么变化？"
```

---

## 盲区4：状态累积（必检）
**问题**：AI不擅长思考"长时间运行后的状态漂移"

```
典型场景：
- 会话超时后的状态处理
- 长时间操作中间状态丢失
- 累计操作导致的数据膨胀
- 缓存过期后的数据一致性

补盲检查清单：
- [ ] 会话超时是否测试？
- [ ] 长时间运行是否测试？
- [ ] 累计操作是否测试？
- [ ] 缓存过期是否测试？

补盲问法：
"请分析状态累积场景：长时间运行会出什么问题？"
"会话超时后会发生什么？"
"累计操作会影响什么？"
```

---

## 盲区5：数据一致性（必检）
**问题**：AI不擅长思考"分布式场景"的数据问题

```
典型场景：
- 跨服务数据同步延迟
- 分布式事务失败回滚
- 主从数据库不一致
- 缓存与数据库不一致

补盲检查清单：
- [ ] 跨服务数据同步是否测试？
- [ ] 分布式事务是否测试？
- [ ] 主从数据库一致性是否测试？
- [ ] 缓存与数据库一致性是否测试？

补盲问法：
"请分析分布式场景：数据一致性会出什么问题？"
"跨服务调用失败会怎样？"
"缓存与数据库不一致会怎样？"
```

---

## 盲区6：第三方集成（必检）
**问题**：AI不擅长思考"Mock与真实行为的差异"

```
典型场景：
- Mock响应与真实响应不同
- 第三方服务超时/异常
- 第三方接口变更
- 第三方服务降级/熔断

补盲检查清单：
- [ ] Mock与真实行为是否对比？
- [ ] 第三方异常是否测试？
- [ ] 第三方接口变更是否考虑？
- [ ] 第三方降级是否测试？

补盲问法：
"请分析第三方集成场景：Mock与真实行为有什么差异？"
"第三方服务异常会怎样？"
"第三方接口变更会影响什么？"
```

skill-card.md

## Description:

Reviews AI-generated test cases against six common blind-spot categories and proposes traceable additional test scenarios.

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 developers use this Chinese-language checklist after reviewing AI-generated test cases to identify missing timing, concurrency, resource, state, data-consistency, and third-party integration scenarios. The skill suggests risk-ranked supplemental cases linked to requirements and original tests.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Reviewing unintended local files may expose unrelated or sensitive information.

Mitigation: Limit file reads to the requirements and test cases selected for review.

Risk: The optional command to install a companion skill would add code from a separately sourced package.

Mitigation: Do not run the optional installation command unless its package and source have been independently trusted.

Risk: A checklist-based coverage report can overstate completeness when requirements or test inputs are missing.

Mitigation: State the coverage basis, mark missing modules as uncovered with reasons, and avoid claims of full or 100% coverage.

## Reference(s):

- [ClawHub skill release](https://clawhub.ai/kokxi/skills/qa-ai-blindspot-compensation)
- [Six blind-spot categories and checklists](artifact/references/blindspot-details.md)

## Skill Output:

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

**Output Format:** [Markdown blind-spot report with coverage and supplemental test-case tables]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Supplemental cases include blind-spot category, risk level, and links to requirement and original test IDs; coverage is scoped to supplied materials.]

## Skill Version(s):

1.8.0 (source: skill frontmatter and ClawHub release)

## 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 1d 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.