Agent skill

homoiconic-rewriting

Unified homoiconic graph rewriting - λ-calculus, interaction nets, ACSets, CUDA parallelism

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill homoiconic-rewriting-plurigrid-asi-2 --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Version: 1.0.0
Path: skills/ai-ml/homoiconic-rewriting-plurigrid-asi-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Homoiconic Rewriting > *Code = Data = Graph = Parallel Reduction* **Trit**: 0 (ERGODIC - coordinates the stack) ## Core Synthesis ``` ┌─────────────────────────────────────────────────────────────────┐ │ HOMOICONIC REWRITING PIPELINE │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ λ-term ──quote──→ S-exp ──parse──→ INet ──CUDA──→ Result │ │ │ │ │ │ │ │ typed data graph parallel │ │ code (homoiconic) rewriting reduction │ │ │ └─────────────────────────────────────────────────────────────────┘ ``` ## GF(3) Balanced Dependencies | Trit | Skill | Role | |------|-------|------| | +1 | `lambda-calculus` | Term generation | | +1 | `gay-mcp` | Color generation | | 0 | `interaction-nets` | Parallel coordination | | 0 | `lispsyntax-acset` | Data bridge | | -1 | `algebraic-rewriting` | Rule validation | | -1 | `slime-lisp` | Evaluation sink | **Sum**: (+1+1) + (0+0) + (-1-1) = 0 ✓ ## The Homoiconic Property ### Level 1: S-expressions (Lisp) ```clojure ;; Code (+ 1 2) ;; Data (same representation!) '(+ 1 2) ;; Transform code as data (map inc '(+ 1 2)) ; → (1 2 3) ``` ### Level 2: Interaction Nets (Graphs) ``` Code (λ-term): Data (graph): Rewrite (reduction): λx. x

What's inside
Steps it walks through
  1. Core Synthesis
  2. GF(3) Balanced Dependencies
  3. The Homoiconic Property
  4. Level 1: S-expressions (Lisp)
  5. Level 2: Interaction Nets (Graphs)
  6. Level 3: ACSets (Algebraic Databases)
  7. Key Algorithms
  8. 1. λ → Interaction Net Compilation
  9. 2. Parallel Reduction (CUDA-ready)
  10. 3. ACSet Rewriting (DPO)
  11. CUDA Integration (Groote et al.)
  12. GPU Kernel for Active Pair Reduction
  13. Performance (from Eindhoven team)
  14. Typed Decomposition
Ships with 1 file
  • metadata.json
Commands it runs
Parse λ-term to S-expression
echo "(lambda (x) (x x))" | bb -e '(read)'
Compile to interaction net (Bend/HVM)
bend compile program.bend -o program.hvm
Run with GPU parallelism
hvm run program.hvm --cuda
Julia ACSet rewriting
julia -e 'using AlgebraicRewriting; include("rewrite_rules.jl")'
More from claude-skill-registry
All skills →
About this skill
What does the homoiconic-rewriting skill do?

Unified homoiconic graph rewriting - λ-calculus, interaction nets, ACSets, CUDA parallelism

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill homoiconic-rewriting-plurigrid-asi-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going