Skills learn
📚

learn

Safe

Capture project insights automatically

Also available from: 0xrdan

Project insights are lost when sessions end. This skill extracts patterns, quirks, and decisions from conversations and persists them to a knowledge base that survives context compaction and new sessions.

Supports: Claude Code(CC)
⚠️ 68 Poor
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "learn". Use /learn to extract insights from our debugging session

Expected outcome:

  • Knowledge Extraction Complete
  • ───────────────────────────────────────
  • Extracted:
  • [Pattern] "API rate limiting with exponential backoff"
  •  
  • Knowledge base now contains:
  • - 5 patterns
  • - 3 quirks
  • - 7 decisions

Security Audit

Safe
v3 • 1/10/2026

Pure prompt-based documentation skill with no code execution. Instructs AI to read/write markdown files in knowledge/learnings directory only. No network, scripts, or command execution. Behavior matches stated purpose.

1
Files scanned
127
Lines analyzed
0
findings
3
Total audits
No security issues found
Audited by: claude View Audit History →

Quality Score

38
Architecture
100
Maintainability
81
Content
30
Community
100
Security
70
Spec Compliance

What You Can Build

Build project memory

Capture team decisions and patterns so future sessions understand project conventions automatically

Train context-aware AI

Help AI assistants understand project-specific quirks and avoid repeated mistakes

Document institutional knowledge

Preserve architectural rationale and design choices for onboarding and long-term maintenance

Try These Prompts

Capture a pattern
Use /learn to extract the pattern from our debugging approach and save it to patterns.md
Document a quirk
Use /learn to document the auth token quirk we discovered in quirks.md
Record a decision
Use /learn to record why we chose SQLite over PostgreSQL in decisions.md
Full extraction
Use /learn to extract all valuable insights from our conversation into the appropriate knowledge files

Best Practices

  • Extract insights at natural stopping points during work sessions
  • Use high confidence for verified insights, medium for inferred patterns
  • Focus on project-specific knowledge, not generic programming concepts

Avoid

  • Extracting obvious or trivial information that adds no value
  • Recording insights without context or rationale
  • Skipping extraction because insights seem "too small" to document

Frequently Asked Questions

What tools does this skill support?
This skill works with Claude and Claude Code. It is designed for the Claude Router system.
How many insights can I extract?
There is no hard limit. The skill processes all extractable insights from the current conversation context.
Can I integrate this with other skills?
Yes. Use /learn-on for continuous extraction, then /learn to persist at session end.
Is my data safe?
Yes. All data stays local in the knowledge/learnings/ directory. No data is sent externally.
Why are my insights not appearing?
Check that knowledge/learnings/ directory exists. Low confidence insights are not used for routing decisions.
How is this different from chat history?
Insights are structured, deduplicated, and survive context compaction. They persist across sessions permanently.

Developer Details

File structure

📄 SKILL.md