- Home
- Skills
- Product Management
- Dev Team Retrospective Builder
Works with the AI Agents you already use
Dev Team Retrospective Builder
Builds structured improvement experiments with clear owners, success metrics, and review dates.
$9.99
Dev Team Retrospective Builder
Example session with this skill installed
Convert these notes into a retro: Staging was down for 2 days, PRs took forever to get reviewed, the API docs were wrong for the payment story, but we finished the migration on time.
- Read your context and instructions
- Compiled the dev team retrospective
The sprint successfully completed the core migration goal despite significant friction in environments, code review cycles, and documentation accuracy.
Sprint Retrospective: Migration & Infrastructure
| Theme | Evidence from Notes | Impact | Discussion Prompt | Possible Experiment |
|---|---|---|---|---|
| Environment Stability | Staging down for 2 days | Blocked testing and delayed verification | How can we minimize the blast radius of staging outages? | Implement a "local-first" testing mock for core services |
| Review Latency | PRs took a long time | Increased cycle time and context switching | What is the main blocker to starting a review within 4 hours? | Designate a "Review Lead" rotation per day |
| Doc Accuracy | API docs were incorrect | Rework and confusion during payment story | Where did the source of truth fail during refinement? | Require updated spec links before PR approval |
What Went Well
- Goal Alignment: The primary migration was delivered on time despite technical hurdles.
- Resilience: The team maintained delivery velocity even with two days of staging downtime.
Suggested Retrospective Agenda (45 Mins)
- Safety & Context (5m): Review migration success and the staging outage timeline.
- Theme Deep Dive (20m): Focus on Review Latency and Doc Accuracy.
- Experiment Selection (10m): Vote on the Review Lead rotation.
- Action Assignment (10m): Assign owners for doc process updates.
Improvement Experiments
| Experiment | Problem | Change to Try | Owner | Review Point | Success Indicator |
|---|---|---|---|---|---|
| Review Rotation | Slow PR cycles | One dev assigned to prioritize reviews for 4h | [TBD] | Next Retro | PR wait time < 6 hours |
| Spec-First Check | Poor API docs | Add "Docs Updated" checkbox to PR template | [TBD] | End of Sprint | Zero doc-related rework stories |
Next steps
- Share the Theme Map with the team 24 hours before the meeting.
- Nominate owners for the Review Rotation experiment during the session.
- Add the "Spec-First" checklist to your GitHub/GitLab PR template.
Disclaimer: This is a facilitation aid. Results should be validated by the team.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Sprint retrospectives often devolve into vague complaints, blame-shifting, or generic action items like "communicate better." Technical leads struggle to extract actionable experiments from messy Slack notes, incident logs, and verbal feedback.
What it does
- Clusters raw sprint notes, blockers, and incident logs into objective, blameless themes.
- Generates root-cause discussion prompts that focus on process gaps rather than individual mistakes.
- Designs time-boxed meeting agendas tailored to your team's available schedule.
- Builds structured improvement experiments with clear owners, success metrics, and review dates.
- Audits existing retrospective documents to remove blame language and sharpen vague action items.
Why this beats prompting it yourself
Standard LLM prompts often produce generic corporate fluff or overly critical performance critiques. This skill uses a specialized framework to ensure every output is blameless, focuses on small-scale experiments, and produces a structured action register that is actually usable in a tracking tool.
Use cases
- Converting rough bullet points from a chaotic release into a structured learning session.
- Facilitating a neutral, data-driven discussion after a major production incident.
- Cleaning up low-quality retro notes to make them professional for stakeholder reporting.
- Scaffolding a 45-minute agile ceremony for a remote engineering team.
Known limitations
Does not integrate directly with Jira or Linear APIs. Requires manual input of notes and does not replace a human facilitator for high-conflict interpersonal issues.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
Requires manual input of sprint notes. Does not integrate directly with project management APIs. Cannot resolve deep interpersonal team conflicts or provide HR advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
- Software
Python
Permissions
No special permissions declared or detected