| name | asi-agent-orama |
| description | ASI Agent-O-Rama Skill |
| version | 1.0.0 |
Status: ✅ Production Ready Trit: 0 (ERGODIC - coordinator) Integration: Red Planet Labs Rama + ASI patterns
Bridge between Agent-O-Rama (Rama-based agent platform) and ASI (Autonomous Superintelligence) patterns. Enables triadic agent orchestration with GF(3) conservation on Rama's distributed topology.
;; Tree-structured Iterative Decomposition And Recombination
(defn tidar-agent [task seed]
(let [children (splitmix-fork seed 3)]
{:minus (spawn-agent :validate task (nth children 0))
:ergodic (spawn-agent :coordinate task (nth children 1))
:plus (spawn-agent :execute task (nth children 2))}))
(defagentmodule ASIAgentModule [setup topologies]
(<<sources
(source> *asi-tasks :> task)
;; Triadic decomposition
(tidar-forward task :> subtasks)
(batch<- subtasks :> results)
(tidar-backward results :> final)
(aor/result! final)))
just asi-agent-start # Start ASI agent module
just asi-tidar "task" seed # Run TIDAR pipeline
just asi-gf3-verify # Verify GF(3) conservation
Σ(validator, coordinator, executor) = (-1) + (0) + (+1) = 0 (mod 3)
rama-gay-clojure - Rama with deterministic coloringtidar - TIDAR orchestration patternsgay-mcp - Color generation backendbisimulation-game - Skill dispersal with GF(3)Skill Name: asi-agent-orama Type: Agent Platform Bridge Trit: 0 (ERGODIC) GF(3): Conserved via triadic spawn
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
general: 734 citations in bib.duckdbThis 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
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.
Add non-text files to a person's artifacts folder. Use when saving images, documents, or other files related to someone. Trigger words: artifact, save image, add photo, attach file, store document.
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
Personal assistant for daily routines, task management, and productivity
Coordinate Claude Code skills with OpenAI Codex autonomous workflows for end-to-end ATFT-GAT-FAN maintenance.