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-retrospectivegit 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-retrospective)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-retrospective"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-retrospective/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-retrospective"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-retrospective.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 | $0.00125 | $0.02378 |
| Opus 5 | $0.00063 | $0.01189 |
| Sonnet 5 | $0.00025 | $0.00476 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
qa-retrospective 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 安全警告:本技能的示例可能涉及发布流程优化和协作流程调整建议。 这些是复盘议题不是直接操作;请勿未经评审即变更团队流程,先达成共识再落地。 本技能仅在 workspace/ 输出评估文件,不持久化、不外传、不跨会话复用。
复盘与经验沉淀
核心原则
复盘的目的是找到系统性的改进点,而不是找谁背锅。
复盘五步法
第1步:收集数据
数据收集:
├─ 缺陷数据
│ ├─ 本迭代新增缺陷数
│ ├─ 缺陷严重程度分布
│ ├─ 缺陷类型分布
│ └─ 缺陷模块分布
│
├─ 漏测数据
│ ├─ 线上缺陷数
│ ├─ 漏测原因分类
│ ├─ 漏测影响评估
│ └─ 漏测修复情况
│
├─ 测试数据
│ ├─ 用例执行率
│ ├─ 用例通过率
│ ├─ 测试覆盖率
│ └─ 测试效率
│
└─ 其他数据
├─ 需求变更次数
├─ 测试延期情况
├─ 线上故障情况
└─ 用户反馈情况
第2步:根因分析(5 Whys)
5 Whys分析法:
问题:线上出现XX Bug
├─ Why 1:为什么测试没发现?
│ └─ 因为测试用例没覆盖这个场景
├─ Why 2:为什么用例没覆盖?
│ └─ 因为需求分析时没考虑到
├─ Why 3:为什么需求分析没考虑到?
│ └─ 因为对这个业务场景不熟悉
├─ Why 4:为什么不熟悉?
│ └─ 因为没有相关的知识沉淀
├─ Why 5:为什么没有知识沉淀?
│ └─ 因为没有复盘和总结机制
根因归类:
├─ 思维盲区:没想到
├─ 信息缺失:不知道
├─ 流程问题:流程不完善
├─ 工具问题:工具不支持
└─ 能力问题:能力不足
第3步:制定改进措施
改进措施设计:
├─ 具体:明确做什么
├─ 可执行:能落地执行
├─ 可衡量:有明确标准
├─ 有负责人:明确责任人
└─ 有时间:明确完成时间
改进措施类型:
├─ 流程改进:优化测试流程
├─ 工具改进:引入/优化工具
├─ 知识沉淀:更新Checklist/模板
├─ 能力提升:培训/学习
└─ 协作改进:优化协作方式
示例:
改进措施:更新登录功能测试Checklist
├─ 具体:增加验证码相关测试点
├─ 负责人:XXX
├─ 完成时间:2024-01-15
├─ 验收标准:Checklist更新并通知团队
└─ 效果验证:下次迭代验证效果
第4步:资产沉淀
资产沉淀类型:
├─ Checklist更新
│ ├─ 新增测试点
│ ├─ 修正错误点
│ └─ 优化检查项
│
├─ 模板更新
│ ├─ 用例模板优化
│ ├─ Bug报告模板优化
│ └─ 测试报告模板优化
│
├─ 知识库更新
│ ├─ 常见问题FAQ
│ ├─ 测试经验总结
│ └─ 最佳实践
│
└─ 流程更新
├─ 测试流程优化
├─ 协作流程优化
└─ 发布流程优化
第5步:跟踪闭环
跟踪机制:
├─ 定期检查:每周/每月检查改进措施执行情况
├─ 效果验证:验证改进措施是否有效
├─ 持续优化:根据效果持续优化
└─ 经验分享:分享改进经验
闭环检查:
├─ 措施是否执行?
├─ 效果是否达到?
├─ 是否需要调整?
└─ 是否可以推广?
复盘报告模板
# 复盘报告
## 1. 基本信息
- 迭代版本:[版本号]
- 复盘时间:[日期]
- 参与人员:[人员列表]
## 2. 数据回顾
- 缺陷数据:[新增X个,严重X个]
- 漏测数据:[线上X个]
- 测试数据:[执行率X%,通过率X%]
## 3. 问题分析
- 主要问题:[问题描述]
- 根因分析:[5 Whys分析]
- 根因归类:[思维/信息/流程/工具/能力]
## 4. 改进措施
- 措施1:[具体措施]
- 措施2:[具体措施]
- 措施3:[具体措施]
## 5. 资产沉淀
- Checklist更新:[更新内容]
- 模板更新:[更新内容]
- 知识库更新:[更新内容]
## 6. 跟踪计划
- 检查时间:[时间]
- 负责人:[人员]
- 验收标准:[标准]
应用场景
迭代结束后复盘:用户登录模块出现了3个线上Bug → 第1步:收集数据(Bug报告、修复记录、测试用例覆盖) → 第2步:5 Whys分析(why漏测?→边界用例未覆盖→why?→测试设计时未识别边界→why?→需求未说明边界) → 第3步:改进措施(增加边界分析环节、补充典型边界checklist) → 第4步:资产沉淀(将边界checklist更新到启发式清单) → 第5步:跟踪计划(下个迭代验证新增checklist的有效性)
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 52aa15289334
- 12d ago First seen · 251 lines · 125 tokens per session scan A d0b1d1b68ca1
qa-retrospective is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 9d ago), licensed MIT. It adds 125 tokens to every session and 2,378 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
add-community-extension
Add a community extension to the Spec Kit catalog from a GitHub issue submission. USE FOR: processing extension submission issues, validating catalog entries, updating catalog.community.json and docs/community/extensions.md, creating PRs. DO NOT USE FOR: creating new extensions from scratch, or first-party extension…
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.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
api-rate-limit-handler
Implement bounded, idempotency-aware API throttling, backoff, and retry handling for 429 and transient 5xx responses.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.