AGENT SKILL

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

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: --incident for 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:

  1. Copy to clipboard
  2. Save to .context/retros/<date>-<slug>.md
  3. Both

04 同仓库更多 Skills

drn
drn/dots

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.

邮件与沟通
★ 23
drn
drn/dots

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.

Skill与智能体开发
★ 23
drn
drn/dots

plannotator-annotate

Open Plannotator's annotation UI for a markdown file, converted HTML file, URL, or folder and then respond to the returned annotations.

★ 23
drn
drn/dots

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.

Skill与智能体开发
★ 23
drn
drn/dots

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".

★ 23
drn
drn/dots

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.

★ 23