Learning Capture

Overview

This skill enables continual learning by recognizing valuable patterns during work and capturing them as new skills. It focuses on high-ROI captures: patterns that will save significant context window tokens through frequent reuse.

Recognition Framework

Monitor for these five types of learning moments:

1. Novel Problem-Solving Approaches

Trigger: Develop a creative, non-obvious solution to a complex problem that could apply to similar future problems.

Strong signals:

• Solution required multi-step reasoning or novel tool combinations
• Approach is generalizable beyond this specific instance
• User expresses satisfaction with the results
• Similar problem type likely to recur

2. Repeated Patterns

Trigger: User requests similar tasks 2-3 times and a consistent approach emerges.

Strong signals:

• Pattern has repeated 2+ times with consistent structure
• User asks "can you do the same thing as before?"
• Task type is clearly ongoing (e.g., weekly reports, monthly communications)
• Each instance requires re-explaining the approach

3. Domain-Specific Knowledge

Trigger: User explains company processes, terminology, schemas, or standards that span multiple conversations.

Strong signals:

• Information accumulates across 2+ conversations
• Knowledge is stable (won't change weekly)
• User frequently asks questions in this domain
• Re-explaining costs 1000+ tokens each time

4. Effective Reasoning Patterns

Trigger: Discover a particular way of structuring thinking that consistently produces better results.

Strong signals:

• Pattern applies to a category of problems, not just one instance
• Results are notably better than simpler approaches
• Structure is teachable and reproducible
• Problem category recurs frequently

5. Workflow Optimizations

Trigger: Figure out an efficient way to chain tools or steps together that produces comprehensive results.

Strong signals:

• Workflo...