AI & ML

fierzone Skill

Essential rules for code comments, READMEs, and technical documentation.

fierzone Skill

Universal architectural standards for building robust, scalable, and maintainable systems.

fierzone Bundle

Universal principles for clean, maintainable, and robust code across all environments.

fierzone Skill

Universal mobile UX principles for touch-first interfaces. Enforces touch targets, safe areas, and mobile-specific interaction patterns.

masharratt Bundle

Multi-layer validation and quality gates for CFN Loop workflows. Use when implementing gate checks, consensus validation, or enforcing clean agent exit patterns.

agentient Skill

Vertex AI SDK patterns for configuring Gemini models including generation parameters, safety settings, streaming responses, and function calling. PROACTIVELY activate for: (1) model configuration and temperature settings, (2) safety controls and streaming implementation, (3) Vertex AI endpoint selection and function calling. Triggers: "gemini config", "model parameters", "streaming response"

agentient Skill

Foundational knowledge for creating ADK (Agent Development Kit) agents including environment setup, project structure, and basic agent scaffolding. PROACTIVELY activate for: (1) new ADK agent creation, (2) ADK project setup and environment configuration, (3) AdkApp initialization and understanding core ADK architecture. Triggers: "create adk agent", "new agent", "setup adk"

agentient Skill

Best practices for engineering high-quality system prompts for AI agents with emphasis on XML structure, clarity, few-shot examples, and token efficiency. PROACTIVELY activate for: (1) system prompt creation and optimization, (2) instruction clarity improvement and few-shot example design, (3) XML tag structure implementation and prompt templates. Triggers: "system prompt", "optimize prompt", "prompt engineering"

alexandrbasis Bundle

Run OpenAI Codex CLI for one-shot cross-AI code review or approach validation. Invoke ONLY when the user explicitly asks ('second opinion', 'codex review', 'ask codex', 'run codex', 'cross-AI check'), or when another skill passes an explicit instruction to delegate to codex. Do not invoke proactively on general review requests. Not for interactive conversations.

alexandrbasis Bundle

Run Cursor CLI for one-shot cross-AI code review when a Cursor perspective is explicitly wanted. Invoke ONLY when the user asks ('cursor review', 'ask cursor', 'run cursor'), or another skill explicitly delegates to Cursor. Do not invoke it implicitly for a generic review. Not for interactive conversations.

alexandrbasis Skill

Update documentation for a completed implementation and, when the repository uses one or the user requests it, update its changelog. NOT for creating new product docs (use /product).

alexandrbasis Skill

Investigate a reported bug, find its root cause, and file a tracker issue (GitHub or Linear) with a TDD-based fix plan. Mostly hands-off — minimize questions to the user. Does NOT apply the fix. Use when user reports a bug and wants it tracked, mentions "triage", "file an issue", or "investigate and plan a fix". NOT for interactive debugging (use /dbg) or batch QA sessions (use /qa).

alexandrbasis Bundle

Analyze the structure and quality of the current codebase with evidence-backed metrics, patterns, and recommendations. Use for an explicit code audit, architecture assessment, codebase overview, hotspot/complexity question, module-dependency analysis, or pre-implementation exploration. Do not use for pre-merge review (use /sr), runtime debugging (use /dbg), or external-technology research (use /deep-research).

alexandrbasis Skill

Inspect, install, customize, or troubleshoot the harness-level git safety hook that blocks dangerous git operations (push, branch -D, checkout .) before they execute. Use when the user wants to change which git commands are blocked, verify the guard is wired up, or set it up after a fresh clone.

alexandrbasis Bundle

Run Google Antigravity CLI (agy) for web-grounded research, cross-AI review, or validation when those capabilities are explicitly needed or another skill delegates to agy. One-shot only; do not select it for an ordinary review without an explicit provider choice.

alexandrbasis Skill

Parallelize genuinely independent implementation items when /si or the user asks for parallel work. Use /si directly for one item, dependent work, shared files, or shared mutable state.

alexandrbasis Skill

Internal reference skill — coding standards and patterns for developer agents. Not user-invocable.

alexandrbasis Bundle

Explore codebase and design approaches before implementation. Use when asked 'explore the design', 'how would this fit', 'design exploration', 'what patterns exist for', 'how is X implemented', or when another skill (brainstorm, nf) needs codebase context to ground a design proposal. NOT for code review (use /sr), NOT for static analysis (use /code-analysis).

alexandrbasis Skill

Internal reference skill — shared conventions for all code review agents. Not user-invocable.

alexandrbasis Skill

Build or update a DDD-style ubiquitous language glossary when the user explicitly asks to define domain terms, build/update the project glossary, or harden terminology. For /nf, /product, or /ct context-reading calls, load and report the glossary; for authorized post-grill updates, merge and write it. Do not write for a load-only or explanatory request. NOT for architectural vocabulary (use /architecture-language).

alexandrbasis Bundle

Canonical architectural vocabulary — module, interface, seam, adapter, depth, leverage, locality. Use when reviewing architecture, deepening shallow modules, designing interfaces, or evaluating refactor candidates. NOT a domain glossary (use /ubiquitous-language for that).

alexandrbasis Bundle

Explore a codebase for architectural deepening opportunities: refactors that turn shallow modules into deeper ones with better testability and locality. Use when the user explicitly asks for architecture improvement, refactoring opportunities, or coupled-module analysis. Do not use for pre-merge review (use /sr) or spec gaps (use /ct). Read-only; it does not write code.

fierzone Bundle

Motion design principles for mobile apps. Covers timing curves, transitions, gestures, and performance-conscious animations.

ricable Bundle

High-performance Spiking Neural Network engine with SIMD optimization, multiple neuron models, and STDP learning. Use when building neuromorphic computing applications, simulating brain-like networks, or running energy-efficient inference with spiking neurons.

ricable Bundle

Native TeammateTool integration plugin bridging Claude Code v2.1.19+ multi-agent capabilities with Claude Flow swarm coordination. Use when configuring teammate-based agent teams, bridging Claude Code native teams with Claude Flow, or setting up multi-agent collaboration.

ricable Bundle

Mathematical AI interpretability via Category Theory, Homotopy Type Theory, Spectral Analysis, Causal Inference, Quantum Topology, and Sheaf Cohomology in WebAssembly. Use when analyzing neural network interpretability in browsers, computing spectral properties of model layers, performing causal inference on AI decisions, or building mathematical AI auditing tools.

ricable Bundle

High-performance WASM attention mechanisms for transformers and LLMs - MultiHead, Flash, and Hyperbolic attention. Use when running transformer inference in browsers, adding attention layers to edge ML pipelines, or accelerating LLM token processing with WebAssembly.

ricable Bundle

Distributed agent coordination framework with shared vector memory, task routing, and claude-flow integration. Use when orchestrating multi-agent workflows with vector search, connecting AI agents to RuVector indexes, building agentic RAG pipelines, or dispatching tasks across agent pools with capability-based routing.

ricable Bundle

Quality engineering plugin with 51 specialized agents across 12 DDD bounded contexts for comprehensive testing and validation. Use when running quality engineering workflows, orchestrating test agent swarms, performing domain-driven quality analysis, or automating QA across bounded contexts.

ricable Bundle

Portable WASM embedding generation using ONNX Runtime with SIMD acceleration and parallel workers. Use when generating text embeddings in browsers without a server, running embedding models at the edge, or building offline-capable semantic search applications.

ricable Bundle

Unified WASM bindings for 18+ attention mechanisms including DAG, Graph, Mamba SSM, Flash, and Sparse attention. Use when running diverse attention patterns in browsers, comparing attention architectures, or building custom transformer variants with mixed attention types.

ricable Bundle

Mathematical AI interpretability plugin with sheaf cohomology, spectral analysis, causal inference, and quantum topology. Use when validating coherence across agent outputs, verifying consensus, detecting hallucinations, or analyzing mathematical structure of multi-agent reasoning.

ricable Bundle

AI-powered performance optimization plugin with bottleneck detection, memory analysis, and configuration tuning. Use when profiling application performance, identifying bottlenecks, analyzing memory usage, tuning agent or system configurations, or optimizing resource allocation.

agentient Skill

Transform prompts into optimized, production-ready versions. PROACTIVELY activate for: (1) prompt engineering, (2) prompt improvement, (3) making prompts more effective, (4) prompt debugging. Triggers: "optimize prompt", "improve prompt", "better prompt", "fix prompt", "prompt engineering", "refine prompt", "enhance prompt"

agentient Skill

Multi-agent orchestration patterns including coordinator agents, LlmAgent vs WorkflowAgent selection, agent-as-tool pattern, and inter-agent communication via session state. PROACTIVELY activate for: (1) multi-agent systems and agent coordination, (2) sub-agent delegation and agent-as-tool implementation, (3) workflow orchestration with LlmAgent and WorkflowAgent. Triggers: "multi-agent", "orchestration", "agent team"

agentient Skill

Generate multi-LLM research design with optimized prompts for each model. PROACTIVELY activate for: (1) research planning, (2) competitive analysis, (3) market research, (4) technology evaluation, (5) strategic research. Triggers: "research brief", "research design", "research plan", "competitive analysis", "market research", "multi-model research"