retro

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits.

23 stars

Best use case

retro is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits.

Teams using retro should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/retro/SKILL.md --create-dirs "https://raw.githubusercontent.com/christophacham/agent-skills-library/main/skills/game-dev/retro/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/retro/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How retro Compares

Feature / AgentretroStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Start-Stop-Continue Retrospective

Run a focused retrospective identifying what to Start, Stop, and Continue.

## Instructions

Analyze the subject (project, period, process) and generate specific, actionable items for each category. Focus on behaviors and practices, not people.

### Output Format

**Subject**: What period or topic are we reflecting on?
**Timeframe**: What period does this cover?

---

## START
*New practices or behaviors to begin*

| What to Start | Why | Owner | When |
|--------------|-----|-------|------|
| [Specific action] | [Benefit expected] | [Who] | [Start date] |
| [Specific action] | [Benefit expected] | [Who] | [Start date] |
| [Specific action] | [Benefit expected] | [Who] | [Start date] |

---

## STOP
*Current practices to eliminate*

| What to Stop | Why | Owner | When |
|--------------|-----|-------|------|
| [Specific thing to stop] | [Problem it causes] | [Who] | [End date] |
| [Specific thing to stop] | [Problem it causes] | [Who] | [End date] |
| [Specific thing to stop] | [Problem it causes] | [Who] | [End date] |

---

## CONTINUE
*Things that are working well*

| What to Continue | Why It Works | How to Protect It |
|-----------------|--------------|-------------------|
| [Working practice] | [Value it provides] | [How to ensure it continues] |
| [Working practice] | [Value it provides] | [How to ensure it continues] |
| [Working practice] | [Value it provides] | [How to ensure it continues] |

---

**Top Priority**
The single most impactful change from this retro:
> [Action] — because [reason]

**Check-in**
When will we review if these changes are working?
> [Date or trigger]

## Guidelines

- Be specific: "Start daily standups" not "communicate more"
- Be behavioral: Focus on actions, not attitudes
- Balance: Aim for 3-5 items per category
- Celebrate Continues: Don't skip this section—recognize what's working
- Assign owners: Unowned actions don't happen
- One priority: If everything is important, nothing is

$ARGUMENTS

Related Skills

cost-optimization

23
from christophacham/agent-skills-library

Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing c...

copilot-usage-metrics

23
from christophacham/agent-skills-library

Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.

copilot-sdk

23
from christophacham/agent-skills-library

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

copilot-instructions-blueprint-generator

23
from christophacham/agent-skills-library

Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.

copilot-docs

23
from christophacham/agent-skills-library

Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instructions, copilot-instructions.md, GitHub Copilot config.

conventional-commit

23
from christophacham/agent-skills-library

Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.

contagious

23
from christophacham/agent-skills-library

Engineer word-of-mouth and virality using the STEPPS framework (Social Currency, Triggers, Emotion, Public, Practical Value, Stories). Use when the user mentions "go viral", "word of mouth", "shareable content", "social currency", or "why people share". Covers environmental triggers and high-arousal emotional content. For sticky messaging, see made-to-stick. For persuasion tactics, see influence-psychology.

constant-time-analysis

23
from christophacham/agent-skills-library

Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret-dependent branches, or constant-time programming questions in C, C++, Go, Rust, Swift, Java, Kotlin, C#, PHP, JavaScript, TypeScript, Python, or Ruby.

connect

23
from christophacham/agent-skills-library

Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.

connect-apps

23
from christophacham/agent-skills-library

Connect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.

conductor-revert

23
from christophacham/agent-skills-library

Git-aware undo by logical work unit (track, phase, or task)

git:compare-worktrees

23
from christophacham/agent-skills-library

Compare files and directories between git worktrees or worktree and current branch