AI & ML

ricable Bundle

Fast Artificial Neural Network Library - FANN bindings for Node.js with network creation, training, and inference. Use when building neural networks with FANN, training models with backpropagation, running inference on trained networks, or integrating native FANN into Node.js pipelines.

ricable Bundle

AI Manipulation Defense System with prompt injection detection, adversarial input scanning, PII detection, and threat analysis. Use when protecting AI applications from prompt injection attacks, scanning inputs for manipulation, detecting PII in prompts, implementing security middleware for LLM pipelines, or hardening agent systems against adversarial inputs.

ricable Bundle

Neural swarm orchestration with WebAssembly-accelerated agent coordination, topology management, and distributed task execution. Use when orchestrating multi-agent swarms, coordinating distributed AI workloads, managing swarm topologies (mesh, hierarchical, ring), running parallel agent tasks, or building self-organizing agent systems.

ricable Bundle

Enterprise AI agent orchestration with 60+ agent types, swarm coordination, self-learning hooks, vector memory, and MCP integration. Use when initializing projects, managing agents, running swarms, or orchestrating multi-agent workflows with Claude Flow.

ricable Bundle

AI agent orchestration platform with 66 specialized agents, MCP tool integration, multi-provider LLM support, and federation. Use when running AI agents with task descriptions, configuring MCP servers, managing agent federations, proxying Claude Code or Cursor, or spawning QUIC transport for low-latency agent communication.

ricable Bundle

SPARC methodology project scaffolding CLI with interactive wizards, MCP server configuration, and AIGI integration. Use when creating new SPARC-structured projects, adding components to existing projects, configuring MCP servers for AI tools, running the interactive setup wizard, or scaffolding minimal Roo mode frameworks.

ricable Bundle

RuVector CLI with self-learning hooks, HNSW vector search, and agent routing. Use when the user needs to manage vector databases from the command line, configure self-learning hooks, route tasks to agents, run benchmarks, or orchestrate RuVector operations via terminal commands.

masharratt Bundle

Introspects Supabase DB, updates project db-query skill with current schema. Run after any migration to keep agent context accurate.

masharratt Bundle

Data persistence for CFN Loop: SQLite storage, Redis coordination, auto memory persistence. Use when storing/retrieving CFN state, coordinating via Redis, or persisting agent memory.

masharratt Skill

Pull the global CFN tool-initiation failure log and investigate why tools failed to start. Use when log-tool-init-failure.sh has recorded failures (missing scripts, not-executable, agent spawn no-output, skill not found, MAX_ITERATIONS exhausted) and you need to diagnose root cause. Summarizes by tool/category/project, then walks each cluster to a fix.

masharratt Bundle

CFN Loop orchestration: gate checks, validation, consensus, Product Owner decisions. Use when orchestrating multi-agent workflows, managing iteration cycles, or coordinating Loop 2/Loop 3 dependencies.

ricable Bundle

Edge AI swarms for browsers with P2P networking, vector search, and neural networks. Use when the user needs browser-based AI swarms, peer-to-peer vector search, client-side neural network inference, decentralized agent coordination, or edge-deployed AI workloads without server infrastructure.

ricable Bundle

Self-Optimizing Neural Architecture with runtime-adaptive LoRA, EWC++ consolidation, and ReasoningBank. Use when building self-improving AI agents, implementing online learning, adapting models at runtime without retraining, or preventing catastrophic forgetting in continual learning systems.

ricable Bundle

Multi-agent research swarm CLI with GOAP planning, HNSW vector search, AgentDB self-learning, and goal decomposition. Use when running multi-perspective research tasks, managing HNSW vector indexes, performing goal-based research with GOALIE decomposition, benchmarking ReasoningBank performance, or orchestrating parallel research swarms.

ricable Bundle

AI agent coordination for Jujutsu VCS with quantum-ready architecture, QuantumDAG consensus, and AgentDB learning. Use when managing Jujutsu repositories with AI agents, resolving merge conflicts automatically, running AI-powered code reviews on jj changes, or coordinating multi-agent VCS workflows.

ricable Bundle

Claude Flow CLI tool for enterprise AI agent orchestration - agents, swarms, memory, tasks, sessions, hooks, and MCP server management. Use when running claude-flow commands, spawning agents, managing swarms, or configuring the orchestration system.

ricable Bundle

MCP (Model Context Protocol) server for Claude Flow - stdio/http/websocket transports, tool registry, connection pooling. Use when starting or managing the MCP server, listing tools, or integrating MCP into applications.

ricable Bundle

Semantic router with HNSW SIMD-accelerated intent matching for AI agent task routing. Use when the user needs semantic intent routing, vector-based route matching, AI agent task dispatch, utterance classification, or building intent-based APIs with sub-millisecond routing decisions.

ricable Bundle

Self-learning LLM orchestration with SONA adaptive learning, HNSW memory, and FastGRNN routing. Use when orchestrating LLM calls across providers, implementing self-learning prompt pipelines, managing multi-model routing, or building adaptive AI agents with recursive retrieval and SIMD inference.

clawdsolana Skill

Formally verified skill attestation service on Solana - creates onchain attestations for skills verified via QEDGen formal verification, integrates with Metaplex agents, and manages agent wallet vault integration

clawdsolana Bundle

Create non-custodial Solana wallets for AI agents with e-commerce, Jupiter swaps, faucet funding, and agent-to-agent payments

clawdsolana Bundle

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

rjmurillo Bundle

Run a 5-layer interview to elicit how a team actually works (rhythms, decisions, dependencies, institutional knowledge, friction) and emit a structured operating model. Use when you say "elicit operating model", "interview team operating model", "how does this team actually work", or "validate operating model". Do NOT use for code analysis (use the analyst agent), external audience narratives (use the explainer agent), or retrospectives (use the retrospective agent).

rjmurillo Skill

Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and boundary-layer audits where automated judgment is safe. Do NOT use for mapping team operating rhythms or decision flows; use work-operating-model instead.

rjmurillo Bundle

Catalog of every configuration axis in this repo, env vars, commit markers, frontmatter keys, QA skip verdicts, and escape hatches, each with its enforcement point and abuse story, plus the checklist for adding a new flag safely. Use when you say `what does a skip flag do`, `list escape hatches`, `can I skip this gate`, `add a config flag`. Do NOT use for hook runtime behavior (use `agent-harness-reference`) or change gating policy (use `ai-agents-change-control`).

ricable Bundle

AI commerce payment infrastructure with AP2 and ACP dual-protocol support for autonomous agent transactions. Use when building AI agent payment systems, implementing autonomous commerce workflows, authorizing agent-to-agent transactions, managing payment wallets, or integrating payment rails into agentic applications.

ricable Bundle

Event-driven lifecycle hooks with ReasoningBank learning, agent routing, pretraining, model routing, coverage analysis, and 12 background workers. Use when setting up self-learning workflows, routing tasks to agents, pretraining from repositories, or managing hook-based automation.

ricable Bundle

Multi-agent swarm coordination with 4 topologies, hive-mind consensus, scaling, and hierarchical mesh orchestration. Use when initializing swarms, coordinating multiple agents, managing hive-mind consensus, or scaling agent clusters.

ricable Bundle

MCP server exposing 87+ neural trading tools for AI agent integration. Use when connecting trading capabilities to Claude or other AI agents via MCP, exposing market data and strategy tools through Model Context Protocol, or building agent-driven trading automation.

ricable Bundle

WebAssembly Graph Neural Network layers for browser and edge inference with GraphConv, GATLayer, SAGEConv, and GINConv. Use when running GNN inference in browsers, deploying graph models to edge devices, building client-side knowledge graph embeddings, or adding WASM-accelerated graph learning to web applications.

ricable Bundle

Claims-based authorization with role management, policy enforcement, and permission control for agent workflows. Use when managing permissions, checking authorization, granting or revoking claims, or configuring role-based access control.

ricable Bundle

Memory management with AgentDB unification, HNSW indexing, vector search, and hybrid SQLite+AgentDB backend. Use when storing, searching, or managing agent memory, configuring memory backends, or performing semantic search across knowledge bases.

ricable Bundle

Ultra-low latency neural trading engine with Rust bindings for Node.js. Use when building algorithmic trading systems, implementing neural trading strategies, backtesting portfolio models, processing real-time market data feeds, or integrating quantitative finance into AI agent pipelines.

ricable Bundle

High-performance attention mechanisms for Node.js including MultiHeadAttention, FlashAttention, and CrossAttention. Use when implementing transformer-style attention layers, building custom attention pipelines, performing efficient large-context attention with Flash algorithm, or integrating attention into agent coordination.

masharratt Skill

FAST code generation via mcp__cerebras-mcp__write tool using Z.ai glm-4.6. Use for rapid test generation, boilerplate creation, and bulk code tasks in main chat. Prompt must be SHORTER than output. Ideal for tests, CRUD, migrations, and repetitive patterns.

masharratt Bundle

Two-phase Rust/TypeScript compilation error fixer: Cerebras LLM bulk processing + agent cleanup. Use when you have 20+ compilation errors needing fast bulk reduction, or errors are mostly mechanical (type mismatches, missing imports, syntax).