AI & ML

masharratt Bundle

Agent interaction capture, logging, analysis with memory tracking + security (Rust). Use to capture/analyze agent interactions, track tool usage and perf metrics, query execution history, or export audit trails for compliance.

masharratt Bundle

Enforces validation pattern compliance across all agent profiles with automated detection and fixing

masharratt Bundle

Generates new agent profiles with consistent structure, automatic validation pattern injection, and test-driven protocols

masharratt Bundle

Automatic, structured persistence of agent outputs to SQLite database. Use when tracking agent outputs across CFN Loop workflows, persisting confidence scores, or querying agent execution history.

masharratt Bundle

Agent process spawning with provider configuration and execution

masharratt Skill

Redis-based agent coordination with pub/sub and waiting mode

ricable Bundle

Browser automation for AI agents with Playwright integration, page snapshots, form filling, and navigation. Use when automating browser interactions, scraping web content, filling forms, or testing web applications from within agent workflows.

ricable Bundle

Advanced extensions for RuVector: embedding generation, admin UI, data export, temporal versioning, and persistence adapters. Use when adding embedding pipelines, visualizing vector data, exporting indexes, or tracking vector changes over time.

ricable Bundle

CLI for local LLM inference with Metal/CUDA acceleration, model management, and benchmarking. Use when running local LLM inference, downloading and managing GGUF models, benchmarking inference performance, serving models via HTTP API, or comparing model outputs across different quantization levels.

ricable Bundle

WASM bindings for browser-based LLM inference with WebGPU acceleration, quantized model loading, and streaming generation. Use when running LLM inference in browsers, deploying language models to edge devices, building offline-capable AI chat, or adding client-side text generation to web applications.

masharratt Bundle

Agent selection based on task classification with fallback support

masharratt Bundle

Type-safe output processing for Loop 2 validators and Loop 3 implementers. Use when parsing agent confidence scores, feedback, or calculating consensus from multiple validators.

masharratt Bundle

Analyzes task descriptions and classifies them into categories for agent selection

alexandrbasis Skill

Prepare session handoff for continuation in a new conversation. Use when 'prepare handoff', 'save progress', 'session handoff', 'I need to stop', 'prepare for next session', 'hand off', 'write handoff', or when the user wants to pause mid-implementation and resume later in a fresh context window.

alexandrbasis Skill

Interactive QA session where the user reports bugs conversationally and the agent files them as tracker issues (GitHub or Linear) one by one or as a dependency-linked breakdown. Explores the codebase in the background for context and domain language. Use when user wants to "do QA", "report bugs", "file issues from a QA pass", or runs through multiple problems at once. NOT for single-bug triage (use /triage-issue) or interactive debug (/dbg).

alexandrbasis Bundle

Use when asked to review code before merge or review a PR, branch, commit range, task path, or current working tree. Trigger on requests like 'review PR', 'review my changes', 'review this branch', 'is this ready to merge', or other pre-merge review requests. Supports task/spec-aware review when task docs exist. NOT for addressing review comments (use /prc).

alexandrbasis Skill

Review and address code review comments on PR. Use when asked to 'address review comments', 'fix PR feedback', 'handle review comments', 'respond to PR comments', or 'address CR comments'. NOT for initiating code review (use /sr), NOT for task-based implementation with CR mode (use /si).

alexandrbasis Skill

Interactive teaching guide for learning while working. Use when asked to 'teach me', 'walk me through', 'explain step by step', 'guide me through', 'show me how', 'learn while doing', 'I want to understand', 'help me learn', 'can you explain how', 'what does this do and why', or when the user expresses desire to understand a topic deeply rather than just get a quick answer. Also trigger when the user wants to learn a new tool, library, pattern, or workflow hands-on — even if they don't use the word "teach". NOT for open-ended brainstorming (use /brainstorm), NOT for quick one-off explanations (just answer directly), NOT for debugging (use /dbg).

alexandrbasis Bundle

Test-driven development with red-green-refactor loop using vertical slices. Use when building features or fixing bugs with TDD, when /si or /si-quick needs canonical TDD discipline, when user mentions "red-green-refactor", "tracer bullets", "test-first", or asks for integration-style tests. Forbids horizontal slicing (all tests then all implementation).

alexandrbasis Bundle

Configure claudops for a specific repository after copying the workflow or installing the plugin. Use for first setup, requested reconfiguration, or unresolved project placeholders in claudops files.

alexandrbasis Skill

Ship an existing implementation by committing local changes, pushing an open PR, waiting for green CI, and merging it. Use when the user explicitly asks to 'merge the PR', 'ship it', 'merge and close', 'commit push merge', 'finalize this PR', or 'land this branch'. Do not trigger on generic end-of-work language without a resolved PR or branch destination. This flow works with or without a task directory; phase handoff details live in Gate 3. NOT for opening a new PR (use plain `gh pr create`). NOT for addressing review comments (use /prc). NOT for preparing a session handoff to a fresh context (use /ph).

alexandrbasis Skill

Step up one layer of abstraction and produce a map of the relevant modules and their callers — used when you (or the agent) are stuck in one file and losing the bigger picture. Use when user says "zoom out", "give me a map", "I'm lost in this code", or "what calls this".

alexandrbasis Skill

Turn a one-line objective into a bounded staged implementation plan with cold-start briefs. Use when asked to 'blueprint', 'multi-session plan', 'long-term plan', 'construction plan', 'break into sessions', 'plan across sessions', 'multi-step project plan', 'session plan', or when work needs staged handoffs. Produces a plan where each step can be resumed independently by a fresh agent with no prior context.

ricable Bundle

FastGRNN neural router achieving 10us routing latency with circuit breaker, uncertainty estimation, and hot-reload. Use when implementing ultra-low-latency model selection, building AI agent orchestration with intelligent routing, or needing sub-millisecond routing decisions with built-in fault tolerance.

ricable Bundle

AI Manipulation Defense System (AIMDS) with prompt injection detection, jailbreak prevention, PII detection, and self-learning threat analysis. Use when defending against AI manipulation, detecting prompt injection, scanning for PII, or analyzing content safety.

ricable Bundle

Multi-LLM provider system supporting Anthropic, OpenRouter, Gemini, ONNX, and custom providers with model routing and configuration. Use when configuring AI providers, switching models, managing API keys, or setting up multi-provider workflows.

ricable Bundle

CRDT-based autonomous credit economy for distributed compute networks compiled to WASM. Use when building token economies for multi-agent systems, implementing decentralized credit allocation, or managing CRDT-based counters and transfers across distributed nodes.

ricable Bundle

Vector embedding service with ONNX models, HNSW indexing, semantic search, hyperbolic embeddings, and neural substrate integration. Use when generating embeddings, performing semantic search, comparing text similarity, or managing embedding collections.

ricable Bundle

High-performance synthetic data generator for AI/ML training, RAG evaluation, and agentic workflow testing. Use when generating training datasets, creating test data for RAG pipelines, building evaluation benchmarks, or synthesizing realistic agent conversation data.

ricable Bundle

Ultra-fast MicroLoRA weight adaptation in WASM with sub-100us latency for rank-2 LoRA. Use when fine-tuning models at the edge, adapting agent behavior in real-time, or running lightweight parameter-efficient training in browsers without GPU.

ricable Bundle

Ultra-fast WASM neural inference engine with sub-microsecond latency for edge and browser deployments. Use when running neural network inference in WebAssembly, deploying models to edge devices, performing real-time prediction in browsers, or needing minimal-overhead inference for latency-critical applications.

ricable Bundle

Performance profiling, benchmarking, optimization recommendations, bottleneck detection, and metrics tracking. Use when benchmarking performance, profiling applications, identifying bottlenecks, or optimizing agent workflows.

ricable Bundle

WebAssembly attention mechanisms with SIMD-accelerated FlashAttention, MultiHeadAttention, and CrossAttention for browser and edge inference. Use when running attention computations in browsers, deploying transformer layers to edge devices, building client-side attention pipelines, or adding WASM-accelerated attention to web applications.

fierzone Bundle

Modern TypeScript standards for type safety, performance, and maintainability.

fierzone Bundle

Secure coding practices for building safe TypeScript applications.

fierzone Bundle

Standards for creating new High-Density Agent Skills with optimal token economy.