agentleFS
Sign inStart free
lzx-Billlzx-Bill/Project-Factory-Core/.agents/skills/retrospective/SKILL.md

retrospective

Skill0 starsChanged 4 months agoMITView on GitHub

Use when conducting project phase retrospectives, lessons learned sessions, or after implementation feedback reveals recurring issues. Trigger when user says "project retro", "lessons learned", "what went well", "what could be better", "project review", "phase review", "post-mortem", "项目复盘", "阶段回顾", "经验总结", or when a project phase completes. NOT for Copilot Chat session analysis — use copilot-session-retro for that.

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use dev-story, team-level and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    dev-story

    Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.

    Also in 12 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • CoralGameSkill

    team-narrative

    Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.

    Also in 12 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • +7 more from lilangMax
  • +1 more from CoralGame

The file

Create a free account to mount
Files
SKILL.md

Retrospective

用于项目阶段复盘和经验总结。

When to Use

  • 项目某个阶段完成，需要做复盘
  • 实现反馈揭示了反复出现的问题
  • 用户要求回顾"做得好的"和"可以改进的"
  • 项目遇到重大挫折需要总结
  • 里程碑达成或未达成后的回顾

Input

来源内容
用户消息复盘范围（全部还是某个维度）、参与者反馈
当前项目所有已完成阶段的相关文档、受影响 wiki 页面

Output Schema

文件类型说明
wiki/08-history/decision-log.md决策回顾决策效果评估、是否需要回滚
wiki/06-quality/known-gaps.md缺口追踪本次复盘发现的新缺口
HOME.md状态更新如复盘影响项目方向则更新首页
reports/stage-review/R-NNN.md复盘报告结构化复盘记录

Minimum Viable Output

  • 含做得好的 ≥2 条
  • 含可以改进的 ≥2 条
  • 含下次避免问题的具体行动 ≥2 条

Complete Output

  • 完整 4 象限分析：做得好的/可以改进的/问题根因/行动项
  • 含量化指标（时间偏差、返工次数等）
  • 含对后续阶段的具体建议
  • 含决策回顾（之前的决策效果如何）

Dependencies

类型说明
前置项目有实际执行记录（任务、Prompt 执行结果等）
后置history-sync（复盘结论同步到历史）、home-navigation（首页状态更新）
依赖读取tasks/done.md、reports/acceptance/*.json、HOME.md

Procedure

  1. 确认复盘范围（全部/某个维度/某次迭代）
  2. 收集事实：任务完成情况、返工次数、时间偏差、反馈
  3. 分析根因：区分"做得好的"和"问题"
  4. 形成行动项：具体、可执行、有负责人
  5. 更新已知缺口（known-gaps.md）
  6. 同步到历史记录和首页

4 象限分析模板

# 复盘报告: <阶段名称> — <日期>

## 做得好的 ✅

| # | 事项 | 根因分析 |
|---|------|---------|
| 1 | ... | 因为... |
| 2 | ... | 因为... |

## 可以改进的 🔧

| # | 事项 | 根因分析 |
|---|------|---------|
| 1 | ... | 因为... |
| 2 | ... | 因为... |

## 问题根因 🔴

| # | 问题 | 根因 | 影响 |
|---|------|------|------|
| 1 | ... | ... | ... |

## 行动项 📋

| # | 行动 | 负责人 | 截止日期 | 状态 |
|---|------|--------|---------|------|
| 1 | ... | ... | ... | 待启动 |

复盘报告保存到: reports/stage-review/R-NNN.md

Enriched Behavior

  • 不只做感性的"好/不好"总结，要找根因和模式
  • 可以主动发现反复出现的问题，提出系统性改进建议
  • 行动项要具体可执行，不是"多沟通"这种无效建议
  • 区分个人问题 vs 系统问题，系统问题优先解决

Target Pages

  • <项目根目录>/wiki/06-quality/known-gaps.md（主）
  • <项目根目录>/wiki/08-history/decision-log.md（决策回顾）
  • <项目根目录>/reports/reviews/（复盘报告目录）
  • <项目根目录>/HOME.md（状态更新）

与相近 skill 的区别

Skill关注点时机触发关键词
history-sync变更追踪、决策记录、文档归档任何变更发生时变更日志、决策日志、归档
copilot-session-retroCopilot Chat session 协作分析session 结束后session review、session复盘、对话复盘
retrospective项目阶段复盘、经验总结、行动改进项目阶段完成或重大事件后项目复盘、阶段回顾、经验教训

区分原则：Copilot 对话复盘 → copilot-session-retro；项目阶段复盘 → retrospective

Changelog

日期变更原因
2026-04-30修复：输出路径从 reports/reviews/ 改为 reports/stage-review/（与 express-incubate 结构对齐）路径与实际不符
2026-04-29新增 4 象限分析模板（做得好的/可以改进的/问题根因/行动项）Procedure 缺少格式定义
2026-04-26新建 skill填补 skill 集合中的复盘空白，完善项目闭环

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free