retrospective
Skill0 starsChanged 9 months agoMITView on GitHub
Conduct structured post-sprint retrospectives for continuous improvement and learning harvest. Use after major releases, significant milestones, or when projects feel stuck. Trigger phrases: 'do a retrospective', 'what did we learn', 'reflect on this release', 'harvest the learnings', 'what went well and what was hard'.
69 other projects use a version of this.
Adopted by
Most recently taken up by
- Adelie-Squad/solosquadtheir own version, first seen Nov 8, 2026
- sbfnk/skillstheir own version, first seen Nov 8, 2026
- AndyB840506/skillstheir own version, first seen Nov 8, 2026
- paureis/pau-skillstheir own version, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- simonasrazm/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use dev-story, team-level and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkilldev-story
Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.
Also in 12 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 12 projects that use this
CoralGameSkillteam-narrative
Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.
Also in 12 projects that use this
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
- +7 more from lilangMax
- +1 more from CoralGame
Other versions69 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 69
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- alibaba/MNN★ 16ksame name
- glebis/claude-skills★ 410same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- blacklanternsecurity/red-run★ 296same name
- striderZA/OpenCodeGameStudios★ 118same name
- The01Geek/prflow★ 99same name
- PAIR-code/deliberate-lab★ 97same name
- AsiaOstrich/universal-dev-standards★ 84same name
- tranhieutt/software_development_department★ 71same name
59 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- agent-teachingSkill
- cf-pages-trespies-deploySkill
- compression-ritualSkill
- context-ingestionSkill
- decision-propagationSkill
- documentation-auditSkill
- era-architectureSkill
- file-managementSkill
- frontend-from-backendSkill
- handoff-protocolSkill
- health-auditSkill
- house-poc-builderSkill
- implementation-promptSkill
- iterative-scoutingSkill
- mcp-cloudflare-builderSkill
- mcp-server-builderSkill
- memory-gardenSkill
- multi-surface-strategySkill
- parallel-tracksSkill
- patient-learning-protocolSkill
- planning-with-filesSkill
- poc-tool-forgeSkill
- pre-implementation-checklistSkill
- process-extractionSkill
- product-positioningSkill
- project-explorationSkill
- release-specificationSkill
- repo-context-syncSkill
- repo-statusSkill
- research-modesSkill
- research-synthesisSkill
- seed-extractionSkill
- seed-librarySkill
- seed-to-skill-converterSkill
- semantic-clustersSkill
- skill-audit-upgradeSkill
- skill-creationSkill
- skill-maintenanceSkill
- spec-constellation-to-prompt-suiteSkill
- static-tool-verifySkill
- status-templateSkill
- status-writingSkill
- strategic-scoutSkill
- strategic-to-tactical-workflowSkill
- web-research-externalSkill
- workflow-routerSkill
- workspace-navigationSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 58 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
When a trigger event occurs, state the intention to conduct a retrospective.
- Very specific: line 47
Create a new markdown file in the relevant project's docs/retrospectives/ directory (e.g., …
- Distinctive: line 61
Identify Patterns: Look for recurring themes across the different answers.
- Distinctive: line 63
Create Seeds for the Memory Garden: If a lesson is particularly profound or reusable, distill it into a Dojo Seed.
- Distinctive: line 67
Commit the completed retrospective document to the repository.
- Distinctive: line 131
Be Specific and Concrete: Avoid vague statements. Use specific examples.
- Distinctive: line 132
End with Action: Every retrospective should result in at least one concrete action item for the next sprint.
- Distinctive: line 139
When running inside the Dojo Genesis plugin:
- Very specific: line 143
Save: all outputs using dojo_save_artifact with appropriate artifact types:
“Common” is measured: kept by at least 6 in 10 of the 58 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Retrospective Skill
OpenClaw Integration: This skill is invoked by the Dojo Genesis plugin via
/dojo retroor/dojo run retrospective. The agent receives project context automatically via thebefore_agent_starthook. Usedojo_get_contextfor full state,dojo_save_artifactto persist outputs, anddojo_update_stateto record phase transitions and decisions.
Version: 1.0 Created: 2026-02-04 Author: Manus AI Purpose: To provide a structured, repeatable process for conducting sprint retrospectives, harvesting learnings, and feeding them back into our collaborative practice.
I. The Philosophy of the Harvest
A retrospective is not a post-mortem. It is not about blame or judgment. It is a harvest. After a season of hard work, we pause to gather the fruits of our labor—not just the features we shipped, but the wisdom we gained in the process. It is a practice of gratitude, honesty, and a commitment to continuous learning.
This skill turns the informal act of looking back into a formal ritual, ensuring that the valuable lessons from each sprint are not lost, but are instead integrated into our shared memory and future workflows.
II. When to Use This Skill
- After a major release: (e.g., after Dojo Genesis v0.0.25 is fully shipped)
- After a significant milestone: (e.g., after completing a major refactor)
- When a project feels stuck or has encountered significant friction.
- At regular intervals (e.g., monthly) to maintain a cadence of reflection.
III. The Retrospective Workflow
Step 1: Initiate the Retrospective
When a trigger event occurs, state the intention to conduct a retrospective. Frame it as a positive and necessary part of the workflow.
Example: "Now that v0.0.25 is shipped, let's conduct a retrospective to harvest the learnings from this sprint. I'll use the Retrospective skill to guide us."
Step 2: Create the Retrospective Document
Create a new markdown file in the relevant project's docs/retrospectives/ directory (e.g., /home/ubuntu/dojo-genesis/docs/retrospectives/v0.0.25_retrospective.md). Use the template provided in Section IV of this skill.
Step 3: Answer the Three Core Questions
Collaboratively, answer the three core questions of the retrospective. This should be a brainstorming phase. Capture all thoughts without judgment.
- What went well? (What should we amplify?)
- What was hard? (What were the sources of friction or difficulty?)
- What would we do differently next time? (What are the concrete, actionable changes we can make?)
Step 4: Synthesize and Extract Learnings
Analyze the answers to the three questions and synthesize them into key themes and actionable insights. This is the most critical step.
- Identify Patterns: Look for recurring themes across the different answers.
- Distill Actionable Insights: For each theme, identify a concrete action that can be taken to improve the workflow.
- Create Seeds for the Memory Garden: If a lesson is particularly profound or reusable, distill it into a Dojo Seed.
Step 5: Commit and Share
Commit the completed retrospective document to the repository. Share the key findings and action items to ensure they are integrated into the next sprint's planning.
IV. Retrospective Document Template
# Retrospective: [Sprint/Release Name]
**Date:** [Date]
**Participants:** [e.g., Cruz, Manus]
**Context:** A reflection on the [Sprint/Release Name] sprint, which focused on [brief description of the sprint's goals].
---
## 1. The Three Core Questions
### What Went Well?
- *[Observation 1]*
- *[Observation 2]*
- *[Observation 3]*
### What Was Hard?
- *[Friction Point 1]*
- *[Friction Point 2]*
- *[Friction Point 3]*
### What Would We Do Differently Next Time?
- *[Actionable Suggestion 1]*
- *[Actionable Suggestion 2]*
- *[Actionable Suggestion 3]*
---
## 2. Key Themes & Insights
| Theme | Analysis | Action Item |
| :--- | :--- | :--- |
| **[Theme 1]** | [A summary of the observations related to this theme.] | [A concrete action to be taken in the next sprint.] |
| **[Theme 2]** | [A summary of the observations related to this theme.] | [A concrete action to be taken in the next sprint.] |
| **[Theme 3]** | [A summary of the observations related to this theme.] | [A concrete action to be taken in the next sprint.] |
---
## 3. Seeds for the Memory Garden
- **Seed:** [Seed Name] — *Why it matters:* [Explanation] — *Revisit trigger:* [When to remember this lesson]
---
## 4. Closing
[A brief closing statement summarizing the key takeaway from the retrospective and expressing gratitude for the practice.]V. Best Practices
- Be Honest and Gentle: The goal is learning, not blame.
- Focus on Process, Not People: Analyze the workflow, not the individuals.
- Be Specific and Concrete: Avoid vague statements. Use specific examples.
- End with Action: Every retrospective should result in at least one concrete action item for the next sprint.
- Keep it Lightweight: The process should feel energizing, not burdensome.
OpenClaw Tool Integration
When running inside the Dojo Genesis plugin:
- Start by calling
dojo_get_contextto retrieve full project state, history, and artifacts - During the skill execution, follow the workflow steps as documented above
- Save all outputs using
dojo_save_artifactwith appropriate artifact types:scout→ type: "scout-report"spec→ type: "specification"tracks→ type: "track-decomposition"commission→ type: "implementation-prompt"retro→ type: "retrospective"
- Update state by calling
dojo_update_stateto:- Record the skill execution in activity history
- Advance the project phase if appropriate
- Log any decisions made during the skill run
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

