agentCLAWHUBUnverified
qa-retrospective
当一个迭代结束、一个项目完成、或者发生线上事故需要事后分析时使用此技能。通过系统性的回顾会议和数据复盘，把个人和团队的经验教训转化为可复用的组织资产。不要沦为"说说好话走个形式"——有效的复盘需要有数据支撑（缺陷趋势/漏测分析/效率数据）、有根因分析（为什么出问题）和有 action items（下次怎么做不一样）。输出复盘报告和改进项追踪表。 触发场景：测试复盘、迭代复盘、项目复盘、经验沉淀、漏测分析、回顾总结、事后分析、反复出现同类问题需要根因改进时。 Use when the user asks about: test retrospectives and post-incident review — defect trends, escaped-defect analysis, efficiency data, and turning lessons into reusable assets. Skill: qa-retrospective Owner: kokxi Summary: 当一个迭代结束、一个项目完成、或者发生线上事故需要事后分析时使用此技能。通过系统性的回顾会议和数据复盘，把个人和团队的经验教训转化为可复用的组织资产。不要沦为"说说好话走个形式"——有效的复盘需要有数据支撑（缺陷趋势/漏测分析/效率数据）、有根因分析（为什么出问题）和有 action items（下次怎么做不一样）。输出复盘报告和改进项追踪表。 触发场景：测试复盘、迭代复盘、项目复盘、经验沉淀、漏测分析、回顾总结、事后分析、反复出现同类问题需要根因改进时。 Use when the user asks about: test retrospectives and post-incident review — defect trends, escaped-defect analysis, efficiency data, and turni
OpenClaw
Rank
62
Safety
84
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-retrospective- 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-retrospective/snapshot"
Documentation
CLAWHUB
63,957 characters of source documentation, loaded on request.
Extracted files
4 files captured from the source.
SKILL.md
---
name: qa-retrospective
description: >-
当一个迭代结束、一个项目完成、或者发生线上事故需要事后分析时使用此技能。通过系统性的回顾会议和数据复盘，把个人和团队的经验教训转化为可复用的组织资产。不要沦为"说说好话走个形式"——有效的复盘需要有数据支撑（缺陷趋势/漏测分析/效率数据）、有根因分析（为什么出问题）和有 action items（下次怎么做不一样）。输出复盘报告和改进项追踪表。 触发场景：测试复盘、迭代复盘、项目复盘、经验沉淀、漏测分析、回顾总结、事后分析、反复出现同类问题需要根因改进时。 Use when the user asks about: test retrospectives and post-incident review — defect trends, escaped-defect analysis, efficiency data, and turning lessons into reusable assets.
license: MIT
allowed-tools: Read Grep Glob
metadata:
display-name: "Retrospective"
version: "1.8.0"
when-to-use: "用户说\"测试复盘\"、\"迭代复盘\"、\"项目复盘\"、\"经验沉淀\"、\"漏测分析\"、\"回顾总结\"、\"事后分析\"、需要复盘总结经验、反复出现同类问题需要根因改进时"
related-skills: "{\"upstream\":[\"qa-bug-root-cause-analysis\",\"qa-quality-metrics\",\"qa-bug-lifecycle\"],\"downstream\":[\"qa-heuristic-checklist\",\"qa-team-coaching\",\"qa-test-leadership\"]}"
references: "[\"references/five-steps.md\"]"
input-format: "{\"required\":[{\"name\":\"迭代数据\",\"type\":\"object\",\"description\":\"迭代的测试和缺陷数据\"},{\"name\":\"团队反馈\",\"type\":\"array\",\"description\":\"团队成员反馈和意见\"}],\"optional\":[{\"name\":\"历史回顾\",\"type\":\"object\",\"description\":\"历史回顾记录\"}]}"
output-format: "{\"traceability\":[\"每次复盘带唯一ID（RETRO-XXXX）\"],\"structure\":[{\"retrospective_report\":\"复盘报告\"},{\"what_went_well\":\"做得好的事项\"},{\"improvement_areas\":\"改进领域\"},{\"action_items\":\"行动项清单\"},{\"follow_up_plan\":\"跟踪计划\"}]}"
error-recovery-guidance: "{\"on_failure\":\"复盘数据不充分时回退到质量度量收集更多数据\",\"retry_behavior\":\"补齐数据后重新复盘\"}"
categories: "[\"Development\",\"Team\"]"
depth-requirement: "{\"reference_value\":\"根据迭代数据调整复盘深度：简单×1/中等×2/复杂×3\",\"minimum\":\"至少包含数据支撑、根因分析、action items 3要素\"}"
---
> ⚠️ 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
> **⚠️ 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。
## 加载时机
| 什么时候读 | 读哪个 |
|-----------|--------|
| 需要五步法的方法细节时，取对应小节 | [`references/five-steps.md`](references/five-steps.md) |
> `复盘五步法`的完整内容已下沉至 `references/five-steps.md`，避免每次触发都占用上下文。
## 复盘报告模板
```markdown
# 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）
**用户说"这个问题又发生了"**
→ 触发复盘：系统性的根因分析，避免同类问题再次发生
## 自检清单
复盘完成后检查：
- [ ] 数据收集是否完整？
- [ ] 根因分析是否深入？
- [ ] 改进措施是否具体？
- [ ] 资产沉淀是否完成？
- [ ] 跟踪计划是否制定？
- [ ] 经验是否分享？
## 检查清单
- [ ] 数据是否支撑结论？
- [ ] 根因是否分析？
- [ ] action items是否可执行？
- [ ] 责任人和时限是否明确？
- [ ] 追踪机制是否建立？_meta.json
{
"ownerId": "kn71y9b23csfx0ykgm55d5m9x5891zt8",
"slug": "qa-retrospective",
"version": "1.8.0",
"publishedAt": 1790656072424
}references/five-steps.md
# 复盘五步法详解
> 本文是 `qa-retrospective` 的**五步法详解**。需要方法细节或推进要点时读本文；
只需要复盘报告模板时不必读。
---
### 第1步：收集数据
```text
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）
```text
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
```text
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
```text
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
```text
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？
```skill-card.md
## Description: Guides QA teams through data-backed test and incident retrospectives, root-cause analysis, and actionable follow-up plans. 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 teams use this skill after iterations, projects, or incidents to analyze defect and testing data, identify root causes, and track measurable improvements. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The optional unpinned skill-set install command may add skills beyond this artifact. Mitigation: Review the package source and use a pinned trusted version before running the command. Risk: Retrospective recommendations could change team or release processes without adequate review. Mitigation: Review proposals with the team and agree on changes before implementing them. ## Reference(s): - [ClawHub skill release](https://clawhub.ai/kokxi/skills/qa-retrospective) - [Five-step retrospective method](references/five-steps.md) ## Skill Output: **Output Type(s):** [Markdown, Guidance] **Output Format:** [Markdown retrospective report and action-item tracking plan] **Output Parameters:** [1D] **Other Properties Related to Output:** [Includes a RETRO-XXXX identifier, supporting metrics, root-cause analysis, owners, acceptance criteria, and follow-up checks.] ## Skill Version(s): 1.8.0 (source: frontmatter and ClawHub release evidence) ## 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.
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/kokxi/skills/qa-retrospective",
"sourceUrl": "https://clawhub.ai/kokxi/skills/qa-retrospective",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T05:51:18.906Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-retrospective/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-retrospective/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T05:51:18.906Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.1K downloads",
"href": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceUrl": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T05:51:18.906Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.8.0",
"href": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceUrl": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-09-29T04:27:52.424Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-retrospective/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-retrospective/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.8.0",
"description": "Version 1.8.0 introduces reference extraction and metadata restructuring. - Extracted detailed \"复盘五步法\" (Five Steps) content to a new file: references/five-steps.md - Removed redundant file: skill-card.md - Simplified and reorganized SKILL.md for clarity; most method content now referenced instead of inline - Added a metadata section to SKILL.md, formalizing version, references, format, and usage details - Updated descriptions and structure for improved usability and context efficiency",
"href": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceUrl": "https://clawhub.ai/kokxi/qa-retrospective",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-09-29T04:27:52.424Z",
"isPublic": true
}
]
}Record generated Oct 11, 2026.