local-compositionality-gadget

Local Compositionality Gadget

16 stars

Best use case

local-compositionality-gadget is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Local Compositionality Gadget

Teams using local-compositionality-gadget should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/local-compositionality-gadget/SKILL.md --create-dirs "https://raw.githubusercontent.com/plurigrid/asi/main/plugins/asi/skills/local-compositionality-gadget/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/local-compositionality-gadget/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How local-compositionality-gadget Compares

Feature / Agentlocal-compositionality-gadgetStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Local Compositionality Gadget

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Local Compositionality Gadget

ERGODIC local update step gadget via Blume-Capel dynamics with GF(3) conservation.

## Trit: 0 (ERGODIC)

This gadget serves as the neutral coordinator in triadic systems.

## Core Concept

Combines:
1. **Blume-Capel dynamics** for spin-1 {-1, 0, +1} state transitions
2. **Three-Gadget rewriting** (RED/BLUE/GREEN) from `crdt_egraph`
3. **ERGODIC update** as the neutral coordinator role

## GF(3) Conservation by Construction

**Key Insight**: Trits are generated in triplets that algebraically sum to zero.

Given two random trits t₁, t₂, the third is computed as:
```
t₃ = -(t₁ + t₂) mod 3
```

This guarantees: `t₁ + t₂ + t₃ ≡ 0 (mod 3)` for every triplet.

## Gadget Patterns

| Gadget | Trit | Pattern | Polarity |
|--------|------|---------|----------|
| BLUE | -1 | `a ⊕ (b ⊕ c) → (a ⊕ b) ⊕ c` | Negative |
| GREEN | 0 | `a ≡ a` | Neutral |
| RED | +1 | `(a ⊕ b) ⊕ c → a ⊕ (b ⊕ c)` | Positive |

## 4-Phase Saturation

1. **Backfill** (step mod 4 = 0) - BLUE gadgets decompose structure
2. **Verify** (step mod 4 = 1) - GREEN identity rules for verification  
3. **Live** (step mod 4 = 2) - RED associative rules to compose
4. **Reconcile** (step mod 4 = 3) - Final GF(3) conservation check

## Usage

```bash
# Run 9 local update steps with seed 0x42D (1069 decimal)
bb scripts/local_compositionality_gadget.bb --seed 1069 --steps 9

# Run with hex seed
bb scripts/local_compositionality_gadget.bb --seed 0x42D --steps 9

# Run 27 steps (9 complete triplets)
bb scripts/local_compositionality_gadget.bb --seed 12345 --steps 27
```

## GF(3) Conservation Guarantee

**ALWAYS** conserved: `∑ gadget_trits ≡ 0 (mod 3)`

Enforced by triplet structure: For every 3 steps, sum = 0.

When steps isn't a multiple of 3, the partial triplet still sums to 0 (mod 3)
because each complete triplet contributes 0 to the running sum.

## Blume-Capel Parameters

| Parameter | Value | Meaning |
|-----------|-------|---------|
| J | 1.0 | Exchange coupling |
| Δ | 0.0 | Tricritical point |
| Spectral Gap | 1/4 | Rapid mixing guarantee |

## Tested Seeds

All seeds produce GF(3)-conserved outputs:
- Seed 1: ✓ (Σ=3 ≡ 0)
- Seed 42: ✓ (Σ=0 ≡ 0)
- Seed 1069: ✓ (Σ=3 ≡ 0)
- Seed 9999: ✓ (Σ=0 ≡ 0)



## Scientific Skill Interleaving

This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:

### Graph Theory
- **networkx** [○] via bicomodule
  - Universal graph hub

### Bibliography References

- `general`: 734 citations in bib.duckdb

## Cat# Integration

This skill maps to **Cat# = Comod(P)** as a bicomodule in the equipment structure:

```
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
```

### GF(3) Naturality

The skill participates in triads satisfying:
```
(-1) + (0) + (+1) ≡ 0 (mod 3)
```

This ensures compositional coherence in the Cat# equipment structure.

Related Skills

tailscale-localsend

16
from plurigrid/asi

Tailscale + LocalSend Peer Discovery

spectral-locale-debugging

16
from plurigrid/asi

Debug and simulate ghostly phenomena using ordered locale theory and trifurcated interactions

ordered-locale

16
from plurigrid/asi

Ordered Locale Skill

ordered-locale-fanout

16
from plurigrid/asi

UPDATED: Now uses proper ordered-locale (Heunen-van der Schaaf 2024). Cocone construction over triadic ordered locale with open cone condition.

localsend-analysis

16
from plurigrid/asi

Analyze LocalSend repos with tree-sitter tags, gh GraphQL contributor snapshots, and protocol safety notes.

local-finetune

16
from plurigrid/asi

local-finetune

localsend-mcp

16
from plurigrid/asi

P2P file transfer with mutual discovery, voice announcements, and redundant connection methods

Feedforward Learning Local

16
from plurigrid/asi

**Category:** Phase 3 Core - Alternative Learning Paradigms

specter-navigator-gadget

16
from plurigrid/asi

Unified Specter/Navigator/3-MATCH architecture with bidirectional path compilation

jepsen-testing

16
from plurigrid/asi

Jepsen-style correctness testing for distributed systems under faults (partitions, crashes, clock skew) using concurrent operation histories and formal checkers (linearizability/serializability and Elle-style anomalies). Use when designing, implementing, or running Jepsen tests, or interpreting histories/violations.

Deterministic Color Generation via Metadata Hashing

16
from plurigrid/asi

**Status**: ✅ Production Ready

cyton-dongle

16
from plurigrid/asi

Connect and stream from OpenBCI Cyton/Daisy via USB dongle, including first-time radio channel pairing