← Back to list

recursive-string-diagrams
by plurigrid
everything is topological chemputer!
⭐ 2🍴 3📅 Jan 20, 2026
SKILL.md
name: recursive-string-diagrams description: recursive-string-diagrams version: 1.0.0
recursive-string-diagrams
Recursive random string diagram generation with white trapezoid as the atomic skill primitive.
Primitives
| Symbol | Name | Meaning |
|---|---|---|
◁═══▷ | White Trapezoid | Skill = morphism with typed ports |
∘ | Compose | Sequential skill chaining |
⊗ | Tensor | Parallel skill execution |
↺ | Trace | Feedback loop / recursion |
GF(3) Trit Assignment
Each white trapezoid carries a trit:
- MINUS (-1): Constraining/validating skill
- ERGODIC (0): Neutral/transforming skill
- PLUS (+1): Generating/expanding skill
Conservation: Σ trits ≡ 0 (mod 3) across diagram
Usage
;; Generate random diagram depth 4
(random-diagram 0 4)
;; Render ASCII
(render-ascii diagram 0)
Example Output
⊗ tensor
↺ trace[1]
◁═══▷ [3→2] ergodic
∘ compose
◁═══▷ [2→2] minus
◁═══▷ [3→3] plus
Semantics (Rama Connection)
| String Diagram | Rama Primitive |
|---|---|
| White Trapezoid | ETL topology |
| Compose (∘) | Depot chain |
| Tensor (⊗) | Parallel PStates |
| Trace (↺) | Recursive query |
DisCoPy Integration
from discopy import Ty, Box, Diagram
# White trapezoid as Box
skill = Box('skill', Ty('in'), Ty('out'))
# Compose
d1 >> d2
# Tensor
d1 @ d2
# Trace
d.trace(n)
Skill Creation Protocol
- Seed: White trapezoid with
[inputs → outputs] - Recurse: Apply random
{∘, ⊗, ↺}up to depth - Color: Assign GF(3) trits, verify conservation
- Render: ASCII or DisCoPy SVG
- Save: Write to
~/.claude/skills/<name>/SKILL.md
Related
discopy- String diagram libraryacsets- Algebraic databasesrama-gay-clojure- Rama + GF(3) colors
Score
Total Score
60/100
Based on repository quality metrics
✓SKILL.md
SKILL.mdファイルが含まれている
+20
✓LICENSE
ライセンスが設定されている
+10
○説明文
100文字以上の説明がある
0/10
○人気
GitHub Stars 100以上
0/15
○最近の活動
3ヶ月以内に更新がある
0/10
○フォーク
10回以上フォークされている
0/5
✓Issue管理
オープンIssueが50未満
+5
✓言語
プログラミング言語が設定されている
+5
○タグ
1つ以上のタグが設定されている
0/5
Reviews
💬
Reviews coming soon