Skill directory
Agent skills
Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.
18,175Skills
1,902Publishers
249Official
Rvf Manageruvnet/rufloManage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transfer01Safety Scanruvnet/rufloScan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence. Use when processing untrusted input (user submissions, API payloads, webhook data, tool outputs) before passing it to a model or executing it.01Security Auditruvnet/ruflo>03Security Scanruvnet/rufloRun full security scans on the codebase using Ruflo security tools. Use when reviewing PRs for security regressions, auditing auth/input-handling code, before production deploys, or when the user asks for a security check at quick/standard/deep depth.01Session Persistruvnet/rufloPersist and restore agent sessions across conversations with state snapshots01Skill Builderruvnet/rufloCreate new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.01Sparc Implementruvnet/rufloRun the SPARC Pseudocode and Architecture phases (2 and 3) — write algorithm pseudocode, design module boundaries and API contracts, then implement01Sparc Methodologyruvnet/ruflo>03Sparc Refineruvnet/rufloRun the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate documentation01Sparc Specruvnet/rufloRun the SPARC Specification phase — gather requirements, define acceptance criteria, identify constraints, and store the spec in memory01Stream Chainruvnet/rufloStream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows01Swarm Advancedruvnet/rufloAdvanced swarm orchestration patterns for research, development, testing, and complex distributed workflows01Swarm Initruvnet/rufloInitialize a multi-agent swarm with anti-drift configuration. Use when starting a complex multi-file task that needs 3+ coordinated agents (feature implementation, refactor across modules, security audit). Skip for single-file edits or quick questions.01Swarm Orchestrationruvnet/ruflo>03Tdd Workflowruvnet/rufloTDD London School workflow -- mock-first, outside-in test development01Test Gapsruvnet/rufloDetect missing test coverage and generate test suggestions. Use when the user asks about coverage gaps, untested code, or what tests to write next; also after adding a feature to find what still needs tests.01Trader Backtestruvnet/rufloRun 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)01Trader Cloud Backtestruvnet/rufloRun a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally01Trader Explainruvnet/rufloRegulator-grade feature attribution for any LSTM/Transformer signal — single-entry PageRank ranks the top-K features that drove the prediction (ADR-126 Phase 6, ADR-123 single-entry PR)01Trader Portfolioruvnet/rufloOptimize portfolio allocation using npx neural-trader mean-variance engine with risk constraints and rebalancing plan01Trader Portfolio Cgruvnet/rufloMean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)01Trader Regimeruvnet/rufloDetect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy. Use when the user asks about market conditions, wants to pick a strategy for current conditions, or before running a backtest/signal that should be regime-aware.01Trader Riskruvnet/rufloAssess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status01Trader Signalruvnet/rufloGenerate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction01Trader Trainruvnet/rufloTrain neural models (LSTM, Transformer, N-BEATS) on market data using npx neural-trader with confidence intervals01V3 CLI Modernizationruvnet/rufloCLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.01V3 Core Implementationruvnet/rufloCore module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.01V3 Ddd Architectureruvnet/rufloDomain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.01V3 MCP Optimizationruvnet/rufloMCP 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.01V3 Memory Unificationruvnet/rufloUnify 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).01V3 Performance Optimizationruvnet/rufloAchieve 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.01V3 Security Overhaulruvnet/rufloComplete 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.01V3 Swarm Coordinationruvnet/ruflo15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.01Validate Pluginruvnet/rufloValidate a Claude Code plugin structure, frontmatter, and MCP tool references01Vector Clusterruvnet/rufloCluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)01Vector Embedruvnet/rufloGenerate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index01Vector Hyperbolicruvnet/rufloEmbed hierarchical data via npx ruvector@0.2.25 embed text and project into the Poincare ball in user code (no --model poincare flag in 0.2.25)01Vector Searchruvnet/rufloVector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit quantization for 32× memory reduction01Vector Setupruvnet/rufloFirst-run setup for ruvector@0.2.25 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`01Wasm Agentruvnet/rufloCreate and manage sandboxed WASM agents for isolated code execution01Wasm Galleryruvnet/rufloBrowse, publish, and install WASM agents from the community gallery01Witnessruvnet/rufloSign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.01Worker Benchmarksruvnet/rufloRun comprehensive worker system benchmarks and performance analysis01Worker Integrationruvnet/rufloWorker-Agent integration for intelligent task dispatch and performance tracking01Workflow Automationruvnet/ruflo>01Workflow Createruvnet/rufloAuthor a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)01Workflow Runruvnet/rufloRun a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js orchestration via the Workflow tool01
Skills, installed in one click
Start building freePut a skill to work
Open any project, search the Skills panel in the chat, and the agent picks it up from there.