Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Kokxi/qa-test-skills --skill qa-ai-blindspot-compensationgit clone --depth 1 https://github.com/Kokxi/qa-test-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-blindspot-compensation)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-blindspot-compensation"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-blindspot-compensation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-blindspot-compensation"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-blindspot-compensation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.02643 |
| Opus 5 | $0.00064 | $0.01321 |
| Sonnet 5 | $0.00026 | $0.00529 |
| Haiku 4.5 | $0.00013 | $0.00264 |
Grade A, and why
qa-ai-blindspot-compensation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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。
| 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？
- 数据一致性：分布式数据问题是否验证？
- 第三方集成：Mock与真实差异是否对比？
输出格式
## 补盲报告
### 盲区覆盖情况
| 盲区类型 | 原有用例 | 补盲用例 | 覆盖状态 |
|---------|---------|---------|---------|
| 时序依赖 | X条 | X条 | ✓/✗ |
| 并发冲突 | X条 | X条 | ✓/✗ |
| 资源竞争 | X条 | X条 | ✓/✗ |
| 状态累积 | X条 | X条 | ✓/✗ |
| 数据一致性 | X条 | X条 | ✓/✗ |
| 第三方集成 | X条 | X条 | ✓/✗ |
### 补盲用例清单
| 用例编号 | 盲区类型 | 测试标题 | 关联需求 |
|---------|---------|---------|---------|
| BS_XXX_001 | 时序依赖 | [标题] | REQ-XXXX |
补盲工作流
步骤1：识别盲区
对照六大盲区，检查当前测试场景：
- [ ] 时序依赖：有没有操作顺序影响结果的场景？
- [ ] 并发冲突：有没有多人同时操作的场景？
- [ ] 资源竞争：有没有资源可能耗尽的场景？
- [ ] 状态累积：有没有长时间运行的场景？
- [ ] 数据一致性：有没有分布式数据同步的场景？
- [ ] 第三方集成：有没有依赖外部服务的场景？
步骤2：生成补盲场景
对每个识别出的盲区，生成专项测试场景：
时序依赖补盲：
1. 打乱操作顺序，验证结果
2. 测试操作中间状态
3. 验证操作依赖关系
并发冲突补盲：
1. 多用户同时编辑同一数据
2. 同一用户多设备同时操作
3. 并发请求导致数据不一致
资源竞争补盲：
1. 模拟内存不足
2. 模拟连接池耗尽
3. 模拟线程池满
状态累积补盲：
1. 长时间运行测试
2. 会话超时测试
3. 累计操作测试
数据一致性补盲：
1. 跨服务数据同步测试
2. 分布式事务测试
3. 缓存一致性测试
第三方集成补盲：
1. Mock与真实行为对比
2. 第三方异常模拟
3. 第三方降级测试
步骤3：标注补盲场景
为每个补盲场景标注：
- 盲区类型：[时序/并发/资源/状态/数据/第三方]
- 风险等级：高/中/低
- 测试难度：高/中/低
- 建议测试深度：深测/常规/冒烟
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 47583630a8f7
- 12d ago First seen · 226 lines · 129 tokens per session scan A c75ef60e9082
qa-ai-blindspot-compensation is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 10d ago), licensed MIT. It adds 129 tokens to every session and 2,643 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
code-review
Reviews Spec Kit code changes for positive and negative test coverage, regression evidence for bug fixes, and consistent repository terminology. Use when reviewing a diff or pull request. Do not use for implementing changes or posting GitHub review actions.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
octocode-benchmark
Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind judge per question grading two answers X/Y…
octocode-graph-eval
Use when you need a measurable keep/discard loop — goal→KPI, baseline vs target, held-out checks, eval suites, or don't-stop-till-done against a runnable sensor. Not for ordinary ship checks where 'tests passed' is enough.