一键导入
sh-retro
Run a retrospective after every 10 completed User Stories. Reflects on recent work, identifies patterns, and generates actionable improvement items.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Run a retrospective after every 10 completed User Stories. Reflects on recent work, identifies patterns, and generates actionable improvement items.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert business analysis with advisory recommendations (no scoring gate)
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
| name | sh-retro |
| description | Run a retrospective after every 10 completed User Stories. Reflects on recent work, identifies patterns, and generates actionable improvement items. |
| disable-model-invocation | true |
Triggered every 10 completed User Stories (tracked in project memory).
Counter tracks US completions only — spikes, bugs, and tooling tasks don't count.
## Retro -- [date] -- after story N
### What worked well
-
### Friction / slowdowns
-
### Bugfix quality (were root causes documented?)
-
### Memory + tooling gaps
-
### Inner loop robustness
-
### Quality gate effectiveness
-
### Actionable items
- [ ] (add to BACKLOG#Ideation or update project rules)
retro_stories_since_last: 0 in project memoryThe retro covers: