create-retrospective
Use when writing a sprint retrospective from team feedback and metrics.
Skill by igmarin
Chalk Labs
Need help deploying create-retrospective?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/igmarin-create-retrospective
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/create-retrospective
What's inside
- Skill name
create-retrospective- Description
- Use when writing a sprint retrospective from team feedback and metrics. Trigger words: retrospective, retro, sprint review, what went well, what didn't, lessons learned, improvement items.
- License
- MIT
- Metadata
- version: 1.0.0 · user-invocable: true
- Instructions
- 44 lines in SKILL.md · view on GitHub
Files (2)
- RETROSPECTIVE_TEMPLATE.md
- SKILL.md
SKILL.md (first lines)
# Creating a Sprint Retrospective Generate a structured retrospective focused on learning and actionable improvements. ## Quick Reference - **Input:** Sprint data (goal, completed/not completed), team feedback, metrics. - **Output:** Retrospective document with action items. - **Sections:** What Went Well, What Didn't, Action Items, Metrics, Kudos. - **Rule:** Every "what didn't" needs an action item with an owner. ## HARD-GATE ```text DO NOT fabricate feedback — only include input the team actually provided. DO NOT skip action items — every "what didn't" must have at least one action. DO assign an owner and timeline to every action item. ``` ## Core Process 1. **Gather** — sprint data (goal met? completed/not completed tickets), team feedback, relevant metrics. 2. **Categorize**: - **What Went Well** — wins, effective practices, things to continue. - **What Didn't** — blockers, bottlenecks, process issues, surprises. - **Kudos** — shout-outs and recognition. 3. **Identify themes** — group related feedback into themes rather than listing raw comments. 4. **Draft action items** — specific, owned, time-bound. Use the template in [RETROSPECTIVE_TEMPLATE.md](./RETROSPECTIVE_TEMPLATE.md) if available; otherwise use the minimal template below. 5. **Review** — verify every "what didn't" maps to an action item. ## Output Style Use **[RETROSPECTIVE_TEMPLATE.md](./RETROSPECTIVE_TEMPLATE.md)** when bundled. Section order: header → What Went Well → What Didn't → Action Items → Metrics → Kudos. Use English unless the user requests otherwise. Every "what didn't" maps to an action item with Owner, Timeline, and Linked Issue. ## Integration | Skill | When to chain | |-------|---------------| | **plan-sprint** | Review the sprint plan vs what was actually delivered | | **generate-status-report** | Include retrospective insights in the next status report | | `work-router` with `project-manager` intent | Focus the retrospective on delivery follow-through; it does not select a separate persona |
From igmarin/agnostic-planning-skills, MIT.
More from igmarin/agnostic-planning-skills
- 0.555score
requirements-clarifier
igmarin
Use when a request is vague and needs scope, user stories, or acceptance criteria.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
estimate-tasks
igmarin
Use when estimating effort, sizing tasks, or assigning story points.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
work-router
igmarin
Route a work request to one skill in the active project profile.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
llm-judgment-layer
igmarin
Use when adding an LLM judgment or recommendation layer to an application — adaptive difficulty, content ranking, daily mixes, personalization.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
review-prd
igmarin
Use when reviewing a PRD for completeness, testability, clarity, or feasibility.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
identify-risks
igmarin
Use when scanning a plan for risks or building a risk register.
SkillAFreshness: A★ 1Claude Code +9 - 0.555score
judgment-gate
igmarin
Use when a plan, backlog, or design needs a defensible go/no-go or ranking and vibes are not enough.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
task-complexity-classifier
igmarin
Classify task complexity using Jev (TypeSafe AI) to help any AI agent decide how to handle a task.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
plan-tickets
igmarin
Draft tracker-ready work items from a plan or PRD.
SkillAFreshness: A★ 1Claude Code +9 - 0.531score
create-prd
igmarin
Use when the user wants a PRD, product requirements, a feature spec, or a written scope.
SkillAFreshness: A★ 1Claude Code +9 - 0.522score
github-issue
igmarin
Use when creating, updating, or closing GitHub issues, or moving them on a project board when explicitly requested.
SkillBFreshness: B★ 1Claude Code +9 - 0.517score
prioritize-backlog
igmarin
Use when prioritizing a backlog, ranking features, or applying RICE, MoSCoW, value-vs-effort, or WSJF.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from igmarin
- 0.619score
implement-hotwire
igmarin
Use when adding Turbo Frames, Turbo Streams, or Stimulus controllers.
SkillAFreshness: A★ 28Claude Code +9 - 0.619score
optimize-performance
igmarin
Use when investigating N+1s, slow queries, caching, or query plans in Rails.
SkillAFreshness: A★ 28Claude Code +9 - 0.619score
extract-engine
igmarin
Use when extracting a host-app feature into a Rails engine.
SkillAFreshness: A★ 28Claude Code +9 - 0.619score
implement-authorization
igmarin
Use when adding or reviewing Rails authorization with Pundit, CanCanCan, or policy objects.
SkillAFreshness: A★ 28Claude Code +9 - 0.619score
create-engine
igmarin
Use when scaffolding a new Rails engine.
SkillAFreshness: A★ 28Claude Code +9 - 0.619score
seed-database
igmarin
Use when choosing seeds, fixtures, or factories for Rails dev/test data.
SkillAFreshness: A★ 28Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get create-retrospective running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
create-retrospective skill. Agent Mart. https://agentmart.dev/skills/igmarin-create-retrospective (last updated 2026-10-24)