Skip to main content
Agent skill

Sprint Retrospective

Run a sprint retrospective — gather data, analyze incidents, propose action items. Any agent can facilitate.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Sprint Retrospective when an AI agent needs a reusable SKILL.md workflow for this job: Run a sprint retrospective — gather data, analyze incidents, propose action items. Any agent can facilitate.

When not to use it

Skip Sprint Retrospective when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/sprint-retrospective
# Save SKILL.md to ~/.claude/skills/sprint-retrospective/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/sprint-retrospective/SKILL.md. For a shared project, commit the folder at .claude/skills/sprint-retrospective/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Sprint Retrospective skill for this task: Use Sprint Retrospective when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

68/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
71/100
Practical detail
68/100
Source evidence
58/100
Source signals
72/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Sprint Retrospective

Reviews the sprint and proposes process improvements.

## Step 1: Gather data

```bash # Sprint doc cat plan/issues/sprints/{N}/sprint.md

# Diary entries from this sprint cat plan/diary.md

# Git history for the sprint git log --oneline --since="YYYY-MM-DD"

# Recently completed issues rg -n '^status: done$' plan/issues/*.md | tail -20

# Task completion times (if available) # Check TaskList or sprint doc task table ```

## Step 2: Identify incidents

For each merge/task, assess: - **Cycle time**: how long from claim to merge? - **Friction**: rebase failures, conflict resolution, idle waiting? - **Quality**: regressions? Tests skipped? Checklist steps missed? - **Communication**: too many messages? Wrong recipients? Ignored messages?

## Step 3: Categorize

**What went well** — with evidence: - Which processes worked as designed? - Which fixes landed cleanly? - What saved time vs previous sprints?

**What didn't go well** — with root cause: - Each incident: what happened, why, impact - Systemic patterns across incidents

## Step 4: Propose action items

For each problem, propose a specific change to a specific file:

| # | Change | File | Priority | |---|--------|------|----------| | A1 | {what to change} | {which file} | HIGH/MEDIUM/LOW |

Each action item should be: - **Specific**: exact file and section to edit - **Testable**: how do we know it worked next sprint? - **Small**: one rule change, not a process overhaul

## Step 5: Write retrospective

Write to `plan/issues/sprints/{N}/sprint.md`:

```markdown # Sprint {N} Retrospective

**Date**: YYYY-MM-DD **Baseline**: {start numbers} **Final**: {end numbers}

## What went well - (with evidence)

## What didn't go well ### Incident 1: {title} **What happened**: ... **Root cause**: ... **Impact**: ... **Action item**: ...

## Action items summary | # | Change | File | Priority | ...

## Proposed file edits (exact diffs for each action item) ```

## Step 6: Review with team

Share the retro with tech lead and user. Don't apply edits unilaterally — propose and wait for approval.

## Output

Message tech lead: `"Sprint-{N} retro complete. {X} incidents, {Y} action items. Review at plan/issues/sprints/{N}/sprint.md"`

Intended uses

  • Use Sprint Retrospective when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.