.claude-plugin/asi/SKILL.md
# Topological Superintelligence (TSI) Compositional AI framework using GF(3) triadic balance and category-theoretic foundations. ## Core Principle Every operation balances trits {-1, 0, +1}: ``` inject(+1) + bridge(0) + emit(-1) ≡ 0 (mod 3) ``` ## Tripartite Agent Architecture | Agent | Trit | Role | Color | |-------|------|------|-------| | PLUS | +1 | Generation, creation, synthesis | #FF6B6B | | ERGODIC | 0 | Coordination, balance, infrastructure | #4ECDC4 | | MINUS | -1 | Verification,
npx skillsauth add plurigrid/asi .claude-plugin/asiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Compositional AI framework using GF(3) triadic balance and category-theoretic foundations.
Every operation balances trits {-1, 0, +1}:
inject(+1) + bridge(0) + emit(-1) ≡ 0 (mod 3)
| Agent | Trit | Role | Color | |-------|------|------|-------| | PLUS | +1 | Generation, creation, synthesis | #FF6B6B | | ERGODIC | 0 | Coordination, balance, infrastructure | #4ECDC4 | | MINUS | -1 | Verification, validation, analysis | #45B7D1 |
gay-mcp - Deterministic color generation with SplitMix64triad-interleave - Balanced schedule interleavingworld-hopping - Badiou-inspired world navigationcrdt-vterm - Collaborative terminal sharingagent-o-rama - Learning and pattern extractionskill-dispatch - GF(3) triadic task routingunwiring-arena - Autopoietic closureacsets-algebraic-databases - Category-theoretic dataautopoiesis - Self-modifying agent configurationcognitive-surrogate - Cognitive modelingentropy-sequencer - Information gain optimizationbisimulation-game - Attacker/Defender verificationspi-parallel-verify - Strong Parallelism Invariancebafishka - Shell operations verificationinfluence-propagation - Network analysisThe bicomodule framework:
c (Control/Semantics) ← High-level reasoning
↕ σ (effect handler)
m (Interface/State) ← Middle layer
↕ ε (counit), δ (comult)
d (Data/Matter) ← Low-level execution
Key law: ε ∘ δ = id (interpretability criterion)
Install via Claude Code marketplace:
claude plugin marketplace add plurigrid/asi
claude plugin install plurigrid@asi
Canonical seed: 0xf061ebbc2ca74d78
Same seed produces identical sequences across all implementations (15+ languages verified).
development
BDD-Driven Mathematical Content Verification Skill Combines Behavior-Driven Development with mathematical formula extraction, verification, and transformation using: - Cucumber/Gherkin for specification - RSpec for implementation verification - mathpix-gem for LaTeX/mathematical content extraction - Pattern matching on syntax trees for formula validation Enables iterative discovery and verification of mathematical properties through executable specifications.
tools
Meta-skill that generates domain-specific AI skills from tool documentation
development
Code Query with AI-enhanced deterministic analysis via SplitMix ternary classification
development
Directed Yoneda lemma as directed path induction. Riehl-Shulman's key insight for synthetic ∞-categories.