agent operations skill risk: low
Sprint Retrospective Facilitator
Guides a structured sprint retrospective by selecting formats such as Start/Stop/Continue, 4Ls, or Sailboat, analyzing raw feedback and sprint performance data, grouping themes, an…
SKILL 1 file
SKILL.md
--- name: retro description: "Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros." --- ## Sprint Retrospective Facilitator Run a structured retrospective that surfaces insights and produces actionable improvements. ### Context You are facilitating a retrospective for **$ARGUMENTS**. If the user provides files (sprint data, velocity charts, team feedback, or previous retro notes), read them first. ### Instructions 1. **Choose a retro format** based on context (or let the user pick): **Format A — Start / Stop / Continue**: - **Start**: What should we begin doing? - **Stop**: What should we stop doing? - **Continue**: What's working well that we should keep? **Format B — 4Ls (Liked / Learned / Lacked / Longed For)**: - **Liked**: What did the team enjoy? - **Learned**: What new knowledge was gained? - **Lacked**: What was missing? - **Longed For**: What do we wish we had? **Format C — Sailboat**: - **Wind (propels us)**: What's driving us forward? - **Anchor (holds us back)**: What's slowing us down? - **Rocks (risks)**: What dangers lie ahead? - **Island (goal)**: Where are we trying to get to? 2. **If the user provides raw feedback** (e.g., sticky notes, survey responses, Slack messages): - Group similar items into themes - Identify the most frequently mentioned topics - Note sentiment patterns (frustration, energy, confusion) 3. **Analyze the sprint performance**: - Sprint goal: achieved or not? - Velocity vs. commitment (over-committed? under-committed?) - Blockers encountered and how they were resolved - Collaboration patterns (what worked, what didn't) 4. **Generate prioritized action items**: | Priority | Action Item | Owner | Deadline | Success Metric | |---|---|---|---|---| | 1 | [Specific, actionable improvement] | [Name/Role] | [Date] | [How we'll know it worked] | - Limit to 2-3 action items (more won't get done) - Each must be specific, assignable, and measurable - Reference previous retro actions if available — were they completed? 5. **Create the retro summary**: ``` ## Sprint [X] Retrospective — [Date] ### Sprint Performance - Goal: [Achieved / Partially / Missed] - Committed: [X pts] | Completed: [Y pts] ### Key Themes 1. [Theme] — [summary] ### Action Items 1. [Action] — [Owner] — [By date] ### Carry-over from Last Retro - [Previous action] — [Status: Done / In Progress / Not Started] ``` Save as markdown. Keep the tone constructive — the goal is improvement, not blame.
INPUTS
- $ARGUMENTS REQUIRED
sprint or team context for the retrospective
REQUIRED CONTEXT
- $ARGUMENTS (sprint context)
OPTIONAL CONTEXT
- files (sprint data, velocity charts, team feedback, previous retro notes)
- raw feedback (sticky notes, survey responses, Slack messages)
ROLES & RULES
Role assignments
- Sprint Retrospective Facilitator
- You are facilitating a retrospective for **$ARGUMENTS**.
- If the user provides files, read them first.
- Group similar items into themes.
- Identify the most frequently mentioned topics.
- Note sentiment patterns.
- Limit to 2-3 action items.
- Each must be specific, assignable, and measurable.
- Reference previous retro actions if available.
- Save as markdown.
- Keep the tone constructive.
EXPECTED OUTPUT
- Format
- markdown
- Schema
- markdown_sections · Sprint Performance, Key Themes, Action Items, Carry-over from Last Retro
- Constraints
- use one of the three specified retro formats
- limit to 2-3 action items
- include table for action items with priority, owner, deadline and success metric
- keep tone constructive
- save as markdown
- reference previous retro actions if available
SUCCESS CRITERIA
- Surfaces insights and produces actionable improvements.
- Limit to 2-3 action items.
- Each action item must be specific, assignable, and measurable.
CAVEATS
- Dependencies
- Requires $ARGUMENTS context.
- Requires uploaded files if provided.
- Requires previous retro actions if available.
- Missing context
- How $ARGUMENTS is supplied or formatted
- Ambiguities
- Format choice rule ('based on context') is not fully specified
QUALITY
- OVERALL
- 0.85
- CLARITY
- 0.90
- SPECIFICITY
- 0.80
- REUSABILITY
- 0.85
- COMPLETENESS
- 0.85
IMPROVEMENT SUGGESTIONS
- Add explicit decision criteria or default for choosing among the three retro formats
- Specify how to handle the case when no files or raw feedback are provided
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Local Documentation Online Sync Automatoragentoperations
- HashiCorp Packer Golden Image Expertagentoperations
- ML Experiment GPU Deployment Workflowagentoperations
- Codex Training Metrics Monitoragentoperations
- Context Optimization Techniques Guideagentoperations
- Issue Triage State Machineagentoperations
- ML Experiment Results Monitoragentoperations
- DOCX Document Creation Editing Guideagentoperations
- Repo Agent Skills Configuration Setupagentoperations
- Git Worktree Isolated Workspace Setupagentoperations
- Agent Context Compression Strategiesagentoperations
- Parallel Agent Dispatcher for Independent Tasksagentoperations
- Scientific Computing Resource Detectoragentoperations
- PPTX File Handling Skill Guideagentoperations
- Interactive QA GitHub Issue Fileragentoperations
- Agent Skill Writing Guideagentoperations
- Brilliant Directories Rube MCP Automation Guideagentoperations
- Istio Linkerd Service Mesh Expertagentoperations
- Machine Learning Experiment Monitoragentoperations
- Benchling Python SDK Integrationagentoperations
- Blackbaud Automation via Rube MCPagentoperations
- DigitalOcean Automation via Rube MCPagentoperations
- Service Mesh Architecture Expertagentoperations
- WandB Training Metrics Health Checkeragentoperations
- Bubble Automation via Rube MCPagentoperations