Continuous Learning

Continuous Learning

Pattern Extraction Framework

After every significant coding session, extract and categorize learnings into three buckets:

1. Corrections - Mistakes caught during review or by the user
2. Successful Approaches - Patterns that worked well and should be repeated
3. Anti-Patterns - Approaches that caused problems and should be avoided

Learning Entry Format

pattern:
  id: "LEARN-2025-0042"
  category: "error-handling"
  type: "correction"         # correction | success | anti-pattern
  confidence: 0.85           # 0.0 to 1.0
  language: "typescript"
  context: "API error responses"
  observation: "Returning raw error messages from database exceptions exposes internals"
  lesson: "Always map database errors to application-level error codes before returning"
  example:
    before: "catch (e) { res.status(500).json({ error: e.message }) }"
    after: "catch (e) { logger.error(e); res.status(500).json({ error: 'INTERNAL_ERROR' }) }"
  frequency: 3               # times this pattern has been observed
  last_seen: "2025-06-15"

Confidence Scoring

| Score | Meaning | Action | |-------|---------|--------| | 0.95+ | Verified across multiple projects | Apply automatically | | 0.80-0.94 | Confirmed in this codebase | Apply and mention | | 0.60-0.79 | Observed but not fully validated | Suggest with caveat | | 0.40-0.59 | Hypothesis based on limited data | Ask before applying | | 0.85) - Apply automatically

• DEPRECATED - Once valid, now superseded by a better approach

Integration with Memory Files

Store learnings in the project's memory file (CLAUDE.md or equivalent):

• High-confidence learnings (>0.85) go in the main instructions section
• Medium-confidence (0.60-0.84) go in a dedicated "Learnings" section
• Low-confidence (<0.60) stay in session notes until validated
• Deprecated patterns move to an archive section with reason for deprecation

Review and prune the knowledge base monthly. Remove entries that have not been referenced in 90 days and have confidence below 0.70.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: rohitg00
• Source: rohitg00/awesome-claude-code-toolkit
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.