learning
Skill1 starsChanged 8 months agoMITView on GitHub
Structured retrospective and lesson extraction. Use when reflecting on completed work or projects. Triggered by "learning", "retrospective", "what did we learn?", "reflection", or "what to apply next time".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- HsuanYuLee/polaristheir own version, first seen Nov 12, 2026
- DaraBoth/skilljmskilltheir own version, first seen Nov 8, 2026
- akumidv/ai_akmontheir own version, first seen Nov 1, 2026
- unisone/claude-learnertheir own version, first seen Oct 9, 2026
- marco-souza/skillstheir own version, first seen Jun 13, 2026
- zinan92/skills-repotheir own version, first seen Mar 15, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- alxyrgin/secondbrain_ai★ 17same name
- DaraBoth/skilljmskill★ 8same name
- HsuanYuLee/polaris★ 5same name
- marco-souza/skills★ 3same name
- amoraleda/skills★ 2same name
- akumidv/ai_akmon★ 1same name
- unisone/claude-learner★ 1same name
- zinan92/skills-repo★ 1same name
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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- evaluateSkill
- notebookSkill
- plan-projectSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
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 24
Use open questions to help the user elaborate on details.
- Very specific: line 28
If NOTEBOOK_PATH is set, search for past lessons related to the retrospective target:
- Distinctive: line 31
Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Very specific: line 38
Create a team with the following teammates using their agent definitions from .claude/agents/:
“Common” is measured: kept by at least 6 in 10 of the 5 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
Learning Skill
A workflow that creates an Agent Team of Researcher and Analyst to perform structured retrospectives through evidence-based analysis and discussion.
Workflow
Step 1: Understand the Retrospective Target
Accurately understand the retrospective target presented by the user. Clarify:
- Subject (project, sprint, decision, event, etc.)
- Time period (from when to when)
- Stakeholders & context
- Original goals & expectations
Use open questions to help the user elaborate on details.
Step 2: Retrieve Past Notebook Context
If NOTEBOOK_PATH is set, search for past lessons related to the retrospective target:
- Grep
$NOTEBOOK_PATH/learnings/and$NOTEBOOK_PATH/research/for keywords from the target (searching title, tags, and body) - Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Include the retrieved content as context when creating the team
Skip this step if zero matches or NOTEBOOK_PATH is not set.
Step 3: Create Agent Team
Create a team with the following teammates using their agent definitions from .claude/agents/:
Teammates:
researcher— gathers evidence, data, and context about what happenedanalyst— performs structured retrospective analysis
Team instructions:
Retrospective target: [Subject]
Time period: [Period]
Original goals: [Goals and expectations]
[Past Notebook context if found]
Collaboration protocol:
1. Researcher gathers evidence: project history, outcomes, metrics, related context from Notebook and codebase
2. Analyst performs initial retrospective analysis (what went well, what didn't, patterns, key learnings)
3. Researcher challenges the analysis — verifies claims against evidence, surfaces overlooked factors
4. Analyst refines the analysis based on Researcher's input, deepens root cause analysis
5. Continue iterating until both agree the lessons are well-evidenced and actionable (aim for 2-3 rounds)
Rules:
- Output language: Use the language specified by OUTPUT_LANGUAGE env var. If not set, match the user's language (default: English)
- If NOTEBOOK_PATH is set: Researcher saves evidence summary to $NOTEBOOK_PATH/research/, Analyst saves retrospective to $NOTEBOOK_PATH/learnings/
- Each agent writes its own deliverables with structured frontmatter (Analyst must use type: learning)Step 4: Final Output
## Retrospective: [Subject]
### Discussion Summary
[How the retrospective analysis evolved through team discussion]
### Time Period & Context
[Overview]
---
### What Went Well
1. **[Item]**: [Description]
- Evidence: [Supporting data from Researcher]
2. ...
### What Didn't Go Well
1. **[Item]**: [Description]
- Root cause: ...
- Evidence: [Supporting data from Researcher]
2. ...
### Patterns
- [Recurring trends observed, validated by evidence]
### What to Do Differently
| Action | Priority | Notes |
|--------|----------|-------|
| ... | High | ... |
### Key Learnings
1. **[Lesson Title]**: [Generalized learning]
2. ...
3. ...
---
### Notebook Save
- [Save status and location]Output Format
Present the following to the user:
- Brief summary of the team discussion process
- What went well / What didn't go well (with evidence)
- Discovered patterns
- Specific improvement actions (with priority)
- Key lessons (3)
- Notebook save status
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.

