Skill rating

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search

SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting

Initialize a new Ruflo project with MCP tools, hooks, and agent configuration. Use when setting up Ruflo in a fresh repo, or when the user says "init ruflo", "set up ruflo", or asks how to bootstrap t

OpenRouter real spend — key limit and usage today/week/month, one request's billed cost by generation id, account credits. Use when asked what OpenRouter charged or whether a key is near its limit. Ne

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

Turn a reviewed goal into a bounded RuFlo AI team, run, and task plan without external side effects.

Verify witness chain integrity and detect provenance gaps

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coo

Run a historical backtest using npx neural-trader with Rust/NAPI engine (8-19x faster) and walk-forward validation; Ed25519-sign the result for paper→live tamper evidence (ADR-126 Phase 4)

Query federation audit logs with compliance filtering

Initialize federation on this node — generate keypair and configure peers

Register a Cognitum Seed device by endpoint and establish agent bridge

Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake

Agent skill for base-template-generator - invoke with $agent-base-template-generator

Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker

Agent skill for topology-optimizer - invoke with $agent-topology-optimizer

Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer

Run health checks on the Ruflo installation and fix common issues

Agent skill for quorum-manager - invoke with $agent-quorum-manager

Generate API documentation from source code with JSDoc and OpenAPI support

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coo

Review RuFlo team results against acceptance criteria using the evidence bundle.

Store and retrieve approved tenant-local team context with RuVector-backed isolation and provenance.

Divide approved work among specialized RuFlo roles and keep task state synchronized.

Report a RuFlo AI team's progress, blockers, task ownership, and remaining planned budget.

Optimize portfolio allocation using npx neural-trader mean-variance engine with risk constraints and rebalancing plan

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Generate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction

Train neural models (LSTM, Transformer, N-BEATS) on market data using npx neural-trader with confidence intervals

Orchestrate firmware rollouts with canary deployment and anomaly-gated advancement

Assess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status

Run Ruflo background workers using Claude Code native /loop scheduling

Create and manage Cognitum Seed device fleets with firmware policies

Stream live swarm events using the Monitor tool for real-time observability

Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.

MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response

AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning se

Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

TDD London School workflow -- mock-first, outside-in test development

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Show AGNTCY/SLIM/CASA integration status — whether upstream AGNTCY packages are installed, which transport (local vs SLIM) is active, and whether CASA enforcement is enabled. Use when the user asks "i

Consumer-side wiring for ADR-097 Phase 3 federation_spend events — per-peer rolling windows + suspension-threshold check

Manage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify <suite.json>` checks suite well-formedness. Bench suites are the fixed

Vector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit quantization for 32× memory reduction

Generate a new song from a creative brief (genre, mood, language, BPM, theme) via the cogmusic MCP create_production tool

Orchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findings