ruvnet

Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical…

Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime

Discover and run bounded remote dynamic workflows with Ruflo mod policy, worker inspection and independent acceptance gates

Creates, assigns, and updates tasks in an AI team run so work has one owner and one deliverable each. Use when the user asks to break down, assign, claim, block, or complete tasks in a run. Changes recorded task state only.

Plans and creates an AI team for a goal, with roles, a run that carries a unit budget, and bounded tasks. Use when the user asks to start, set up or staff a team, or to split a larger goal across roles. Records coordination state only; nothing is executed.

Pauses, resumes, or completes an AI team, or marks a run complete, while keeping its evidence. Use when the user asks to pause, stop, resume, wrap up, or close a team or run. Changes coordination state only and deletes nothing.

Reports an AI team's progress, blockers, task ownership, and recorded budget. Use when the user asks for status, what is blocked, who owns what, or how much of the budget is recorded as used. Read-only.

Stores approved context for one AI team and searches it later, with provenance. Use when the user asks to remember a decision, constraint, or fact for the team, or to recall what the team already knows. Memory is separate for each team and tenant.

Reach RuView sensing hardware from the machine it is attached to — ESP32 CSI nodes (serial + UDP stream), 60 GHz MR60BHA2 / 24 GHz LD2410 mmWave radars, RPLIDAR and iPhone LiDAR — and from other machines over SSH, read-only.

Build, flash, and provision an ESP32-S3/C6 CSI node for RuView — firmware variant choice, cross-platform checksum-verified esptool flashing, NVS/WiFi/channel/MAC-filter overrides, boot-log evidence.

Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

Turn a feature request into a minimal, file-level implementation plan before any code.

Map a Homecore capability to reviewed source, tests, ADRs, and limitations.

Review Home Assistant migration as untrusted versioned input and no-clobber output.

Review Homecore server startup, restore, authentication, feature, and provider configuration.

Draft a bounded legacy-style YAML role configuration with explicit permissions and compatibility limits. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Compare supplied religious passages with explicit translation, historical and interpretive boundaries. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Format supplied prose with configurable word-prefix emphasis while preserving its text. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Turn a customer problem into distinct ideas, a small prototype and a measurable learning test. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Prepare Bubble API queries and workflow change requests without collecting tokens or claiming execution. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Develop an evidence based business plan spanning customers, product, operating costs, hiring and governance. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Compare supplied availability and draft a meeting proposal without accessing calendars or sending invitations. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

Translate a sanitized cURL request into an explicit API contract draft and integration requirements. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

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

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

Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.

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 times.

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 implementation.

Walk the causal graph in AgentDB to explain why two memories are connected, or trace a root cause. Use when the user asks "why did X happen", "what led to Y", or after an incident.

Record a causal relationship between two memories in AgentDB — "X caused Y", "A supersedes B", "patch-foo depends-on patch-bar". Use when the user is documenting cause/effect, dependencies, supersessions, or after-action analysis.

Store memories in tier-aware hierarchical memory — working / short-term / long-term — and recall with tier filters. Use for working-set context that should fade, vs facts that should persist, vs patterns that should be searchable forever.

Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server. Use when the user is starting a new project that needs vector memory, or asks to "set up agentdb" / "init agentdb".

Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb stats", or after long-running sessions to confirm state.

Execute Cypher queries against AgentDB's graph backend. Use when the user wants to write a custom traversal that the standard tools don't cover, or when explaining graph state.

Search and manage hyperedges — n-ary relationships between memories. Use for swarm membership, multi-cause incidents, or any "this involves all of (A, B, C, D)" relationship that doesn't fit a binary edge.

K-hop traversal from a starting node in AgentDB's graph. Use to explore neighborhoods, find reachable nodes, or visualize a memory's "context".

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable `npm install @metaharness/kernel@X.Y.Z` next step. Exits 2…

Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/* example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research,…

GCP Secret Manager integration: validate setup, fetch values, or confirm an NPM_TOKEN is non-revoked via `npm whoami`. Used for publish-time token rotation without long-lived keys in CI.

Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest,…

Publish a generated harness to npm — runs the smoke test, signs the witness manifest, and dispatches `npm publish --provenance` from your tagged release.

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for…

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

Create and run custom background analysis workers with composable phases. Use when you need automated code analysis, security scanning, pattern learning, or API documentation generation.

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

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

Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

Discover and integrate RuV Stack projects when the user asks where to begin with ruvnet, which RuV tools fit a goal, or how the stack fits together.

Generate or evolve a repository-specific CLI, MCP and skills harness using MetaHarness, with bounded evaluation and explicit release authority.

Connect to x.ruv.io, read federation channels and claims, or coordinate authorized work across Ruflo hosts with explicit identity and publishing boundaries.

Choose and validate RuVector or AgentDB memory for an agent application, including provenance, isolation, retention and workload-specific retrieval benchmarks.

Self-learning pre/post-task hooks and model/task routing from the Ruflo CLI, on a ruOS desktop. Use to add coordination, formatting, and learning around Claude Code operations, or to route work by complexity/cost.

Store and semantically search agent memory with ONNX vector embeddings on a ruOS desktop, using the Ruflo CLI. Use to persist patterns/decisions across sessions and recall them by meaning rather than exact key.

Spin up a coordinated multi-agent swarm (hierarchical or mesh topology) to work a complex, multi-file task on a ruOS desktop. Use when a task needs 3+ agents working in parallel with anti-drift coordination; skip for single-file edits.

Persistent, adaptive vector memory for agents on a ruOS desktop — a Rust-native vector database with local semantic embeddings, HNSW retrieval, and graph relationships. Use to remember and recall across sessions with no database server or API key.

Diagnose Open Claude Code installation, provider authentication, skill discovery, and CLI failures. Use when OCC fails to start, returns errors, or cannot find an installed skill.

Run Open Claude Code (OCC) for coding tasks and verify its CLI installation. Use when asked to use OCC, select its provider, or perform a bounded coding task through its CLI.

Verify Open Claude Code package integrity, release tests, and automation evidence. Use when asked whether an OCC release is published, tested, or fully automated.

Safely resume an interrupted or handed-off SPARC run from its verified persisted state without duplicating mutations or skipping unfinished gates.

Audit an existing SPARC run without changing it when the user asks for gate readiness, trace integrity, evidence coverage, or an independent delivery review.

Run an engineering goal through the gated SPARC phases when the user wants a new implementation, integration, redesign, or other substantial delivery workflow.

Audit RuField tests, trust boundaries, privacy projections, and evidence promotion. Use for conformance review, security regression review, release validation, or checking whether field accuracy claims have support.

Run and explain the RuField deterministic synthetic benchmark and local sensing dashboard. Use for a RuField demo, quickstart, benchmark baseline, or viewer smoke test.

Validate RuField CSI or ultrasonic recording replay and its fusion boundary. Use for captured CSI JSONL, BatVu ultrasonic replay, replay adapter integration, or replay regression diagnosis.