retro
Run a structured retrospective or post-incident review with optional knowledge base capture. Use for running retrospectives, postmortems, or incident reviews.
- License 许可
- MIT
- 所属仓库
- drn/dots
- 最近更新
- 2026-11-12
- Stars
- ★ 23
- Forks
- 4
01 前言 Front Matter
- name
- retro
- description
- Run a structured retrospective or post-incident review with optional knowledge base capture. Use for running retrospectives, postmortems, or incident reviews.
02 资源文件 3
- 参考文档evals/evals.json7.7 KB
- 参考文档references/sample-size-guide.md6.6 KB
- 参考文档references/test-templates.md6.4 KB
03 SKILL.md 正文
Retrospective
Structured retrospective for projects, sprints, or incidents. Captures learnings and optionally persists them to the knowledge base.
Arguments
$ARGUMENTS- Optional:--incidentfor post-incident template, or a topic/project name
Context
- Recent commits: !
git log --oneline -20 2>/dev/null | head -20 - Merged PRs: !
gh pr list --state merged --limit 10 2>/dev/null | head -10 - Knowledge base: !
cat context/knowledge/index.md 2>/dev/null | head -30 - Current branch: !
git branch --show-current
Instructions
Step 1: Choose template
IF --incident is in $ARGUMENTS, use the Incident template.
OTHERWISE, use the Standard template.
Step 2: Gather context
Review the recent commits and merged PRs from the context above. Summarize the scope of work that this retro covers. If the user provided a topic, focus on that.
Step 3: Present and collaborate
Standard Template
## Retrospective: <topic or date>
### What Went Well
- <positive outcomes, wins, good patterns>
### What Did Not Go Well
- <pain points, friction, mistakes>
### Action Items
- [ ] <concrete next step with owner if applicable>
### Key Learnings
- <insights to carry forward>
Incident Template
## Post-Incident Review: <incident name>
### Timeline
| Time | Event |
|------|-------|
| | <what happened> |
### Impact
- **Users affected:**
- **Duration:**
- **Severity:**
### Root Cause
<what actually caused the issue>
### What Went Well
- <effective response actions>
### What Did Not Go Well
- <gaps in detection, response, or prevention>
### Action Items
- [ ] <concrete remediation with owner and deadline>
### Follow-ups
- [ ] <longer-term improvements>
Present the template pre-filled with whatever you can infer from the git context. Ask the user to fill in, correct, or expand each section. Iterate until the user is satisfied.
Step 4: Knowledge capture (optional)
IF a knowledge base exists (check context above for context/knowledge/index.md):
- Propose adding key learnings as a new topic or updating an existing topic
- Only add durable, reusable insights — not session-specific details
- Follow the format in
/knowledge(bold entity names, standalone facts, date-stamp volatile info)
IF no knowledge base exists, skip this step entirely. Do not suggest creating one.
Step 5: Save
Offer to:
- Copy to clipboard
- Save to
.context/retros/<date>-<slug>.md - Both
04 同仓库更多 Skills
batch-pr-review
Review a batch of pull requests together, describe every change in plain language, and build a private Claude artifact that eases human review, with a severity-tagged and verified findings list. Use when asked to review several PRs, a stack of PRs, PRs listed in a Slack thread or message, or to summarize a batch of PRs for a reviewer.
plannotator-setup-goal
Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final /goal prompt.
plannotator-annotate
Open Plannotator's annotation UI for a markdown file, converted HTML file, URL, or folder and then respond to the returned annotations.
write-skill
Create or improve a Claude Code skill/slash command with best practices for structure, dynamic context, and safety. Use for creating new skills, improving existing ones, or learning skill authoring.
wrapup
End-of-session checklist that detects loose ends — uncommitted changes, unmerged branches, learnings to capture, handoffs needed — and routes to the right skills. Use for session closeout, wrapping up, end of day, or "anything else to capture".
tts
Read text aloud using text-to-speech. Use when the user says "speak to me", "read to me", "read this aloud", "say this", "speak the summary", or asks to hear something spoken.