compression-progress

npx skills add majiayu000/claude-skill-registry --skill compression-progress-plurigrid-asi-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Compression Progress Skill: Curiosity-Driven Learning **Status**: ✅ Production Ready **Trit**: +1 (PLUS - generator) **Color**: #D82626 (Red) **Principle**: Learning = Compression improvement **Frame**: Compressor improvement rate as reward signal --- ## Overview **Compression Progress** measures the *derivative* of compression ability over time. When a learner compresses data better than before, that improvement is intrinsic reward—the formal theory of curiosity and creativity. 1. **Compressor C(t)**: Current world model 2. **Compression ratio**: |C(data)| / |data| 3. **Progress**: C(t) - C(t-1) improvement 4. **Reward**: Proportional to progress, not absolute compression ## Core Formula ``` r(t) = |C(t-1)(data)| - |C(t)(data)| Curiosity reward = compression improvement rate Boredom = zero progress (already compressed or incompressible) ``` ```python def compression_progress(compressor_old, compressor_new, data) -> float: """Intrinsic reward from model improvement.""" old_bits = len(compressor_old.compress(data)) new_bits = len(compressor_new.compress(data)) return old_bits - new_bits # positive = learned something ``` ## Key Concepts ### 1. Curiosity as Compression Gradient ```

Measure compression progress
just compression-progress before.model after.model data/
Generate curiosity curriculum
just curiosity-curriculum tasks.json
Visualize learning trajectory
just compression-trajectory log.json