retro
Weekly engineering retrospective with commit analysis and trends. Use when: weekly retros, sprint reviews, monthly engineering reviews.
- License 许可
- Apache-2.0
- 所属仓库
- bravew/Neumar
- 最近更新
- 2026-11-14
- Stars
- ★ 12
- Forks
- 4
01 前言 Front Matter
- icon
- history
- name
- retro
- trigger
- /retro
- version
- 1.0.0
- category
- development
- description
- Weekly engineering retrospective with commit analysis and trends. Use when: weekly retros, sprint reviews, monthly engineering reviews.
03 SKILL.md 正文
When generating output, use the user's preferred language for all headings, labels, and prose.
Overview
A structured engineering retrospective that analyzes recent work, identifies patterns, and generates actionable improvements. Uses git history and project state as evidence.
Phase 1: Data Gathering
Collect evidence before forming opinions:
Git Analysis
- Review commits from the retro period (default: last 7 days)
git log --since="7 days ago" --oneline --stat
- Identify themes — which areas of code changed most?
- Count: commits, files changed, lines added/removed
- Note: any reverts, hotfixes, or emergency changes
Work Analysis
- What was planned vs. what was delivered?
- Were there unexpected tasks that diverted effort?
- Which tasks took longer than expected? Why?
- Which tasks were completed faster than expected? Why?
Phase 2: Retrospective Categories
What Went Well
- Completed deliverables
- Good practices observed in the code
- Effective collaboration moments
- Things that were easier than expected
What Could Be Better
- Recurring pain points
- Technical debt that slowed things down
- Communication gaps
- Process friction
Action Items
For each "could be better" item, propose a specific action:
- What: Concrete improvement
- Who: Who should own this
- When: By when should this be done
- How: First step to take
Phase 3: Trend Analysis
Look for patterns across multiple retros:
- Recurring themes — Is the same issue appearing week after week?
- Improving areas — What's getting better over time?
- New concerns — What appeared for the first time?
- Action item follow-up — Were previous action items completed?
Output Format
## Engineering Retrospective: [date range]
### Summary
- **Commits**: [count]
- **Files changed**: [count]
- **Key areas**: [top 3 areas of activity]
### What Went Well
- [item with evidence]
### What Could Be Better
- [item with evidence]
### Action Items
| # | Action | Owner | Due | Priority |
|---|--------|-------|-----|----------|
| 1 | [action] | [who] | [when] | High/Med/Low |
### Trends
- [trend observation with data]
### Previous Action Items Status
| # | Action | Status |
|---|--------|--------|
| 1 | [from last retro] | ✅ Done / 🔄 In Progress / ❌ Not Started |
Retrospective Principles
- No blame — Focus on systems and processes, not individuals
- Evidence-based — Support observations with data from git/tools
- Forward-looking — Every problem should produce an action item
- Time-boxed — Keep the retro focused and concise
- Follow through — Track action items across retros
04 同仓库更多 Skills
yt-dlp
A robust CLI wrapper for yt-dlp to download videos, playlists, and audio from YouTube and thousands of other sites. Supports format selection, quality control, metadata embedding, and cookie authentication.
weather
Get current weather and forecasts (no API key required).
video-editing
Video Mode editing guidance for agentic storyboard, timeline, caption, audio, render, and publish work through video_* MCP tools.
video-edit
Conversational video editing workflow for cuts, transcript-based edits, overlays, captions, subtitle burn-in, and render planning with ffmpeg. Use when the user asks to edit video by instruction, cut silence or words, add subtitles, add overlays, transcribe video, or render a final clip.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
ship
Full shipping workflow: test, review, version, changelog, and PR creation. Use when: preparing to ship code, creating releases, merging PRs.