Best use case
triangle-metrics is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Triangle Metrics Skill
Teams using triangle-metrics 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/triangle-metrics/SKILL.md --create-dirs "https://raw.githubusercontent.com/plurigrid/asi/main/plugins/asi/skills/triangle-metrics/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/triangle-metrics/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How triangle-metrics Compares
| Feature / Agent | triangle-metrics | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Triangle Metrics Skill
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
# Triangle Metrics Skill
**Trit**: 0 (ERGODIC - synthesizer/coordinator)
**Purpose**: Unify all triangle inequality skills into a coherent metric space
---
## Cross-Referenced Skills
| Skill | Guarantee | Integration Point |
|-------|-----------|-------------------|
| **glass-hopping** | ≪ order transitivity | `TriangleInequality` Narya type |
| **world-hopping** | Dijkstra pruning | `d13 <= d12 + d23` constraint |
| **glass-bead-game** | Propagator constraint | `world_distance` comparisons |
| **epistemic-arbitrage** | Knowledge transfer bound | `d(A,C) ≤ d(A,B) + d(B,C)` |
| **l-space** | Navigation metric | `:triangle_inequality` traversal |
| **open-games** | Play/coplay equilibrium | `equilibrium ⟺ d(a,c) ≤ d(a,b) + d(b,c)` |
---
## Unified Interface
```julia
# Abstract metric interface all skills implement
abstract type TriangleMetric end
struct WorldDistance <: TriangleMetric
d12::Float64
d23::Float64
d13::Float64
end
function triangle_valid(m::WorldDistance)::Bool
m.d13 ≤ m.d12 + m.d23
end
# Skill-specific implementations
struct GlassHoppingMetric <: TriangleMetric
h12::Bridge # W₁ ≪ W₂
h23::Bridge # W₂ ≪ W₃
# Transitivity guarantees h13
end
struct OpenGamesMetric <: TriangleMetric
play::Strategy # Forward distance
coplay::Strategy # Backward distance
# Equilibrium ⟺ triangle satisfied
end
```
---
## Mutual Awareness Protocol
When any triangle skill is invoked:
1. **Check**: Query other loaded triangle skills
2. **Validate**: Ensure distances are consistent across all
3. **Propagate**: Share metric updates to siblings
4. **Witness**: Generate Narya proof if all agree
```narya
-- Unified triangle witness
def UnifiedTriangle
(glass : GlassHopping.Bridge)
(world : WorldHopping.Path)
(game : OpenGames.Equilibrium)
: TriangleValidated
```
---
## DuckLake Integration
```sql
-- Query triangle-validated interactions
SELECT a.id, a.trit, a.triangle_valid,
b.id as next_id, b.trit as next_trit,
c.id as third_id, c.trit as third_trit,
ABS(c.trit - a.trit) as d13,
ABS(b.trit - a.trit) + ABS(c.trit - b.trit) as d12_plus_d23
FROM activity_log a
JOIN activity_log b ON b.timestamp > a.timestamp
JOIN activity_log c ON c.timestamp > b.timestamp
WHERE d13 <= d12_plus_d23; -- Triangle inequality
```
---
## GF(3) Conservation
The unified metric preserves GF(3):
```
Σ(skill trits) = glass-hopping(0) + world-hopping(0) +
glass-bead-game(0) + epistemic-arbitrage(0) +
l-space(0) + open-games(0) +
triangle-metrics(0) = 0 ✓
```
---
## Usage
```bash
# Validate all triangle constraints
just triangle-validate
# Generate unified Narya witness
just triangle-witness
# Query cross-skill distances
just triangle-query
```
**Integration**: Load alongside any triangle skill for automatic mutual awareness.
## 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
We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.