Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating real-time voice agents that need to transfer control between specialized agents, implement supervisor escalation, or build complex conversational systems.

Poultry farming domain knowledge for broilers and layers in LivestockAI

Phoenix LiveView UI and real-time feature patterns

Principles for writing simple, maintainable Laravel/Livewire code. Use when writing Livewire components, tests, or Blade views. Focuses on avoiding over-engineering.

Navigate and load project living documentation for context from .specweave/docs/internal/. Use when implementing features and needing project context, referencing ADRs for design decisions, or accessing specs and architecture docs. Provides table of contents for all documentation types.

Launch or resume Living Docs Builder independently. Generates comprehensive enterprise documentation from codebase analysis with AI-powered insights. LSP-enhanced by default for accurate API extraction.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Comprehensive reference for the llama.cpp C API, documenting all non-deprecated functions and common usage patterns.

When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.

LlamaIndex implementation patterns with templates, scripts, and examples for building RAG applications. Use when implementing LlamaIndex, building RAG pipelines, creating vector indices, setting up query engines, implementing chat engines, integrating LlamaCloud, or when user mentions LlamaIndex, RAG, VectorStoreIndex, document indexing, semantic search, or question answering systems.

LlamaIndex Wolfram Alpha tool for computational knowledge queries, math solving, scientific calculations, and agent integration. Triggers: wolfram alpha, computational query, math solver, scientific calculation, WolframAlphaToolSpec.

Expert LLC operations management for ID8Labs LLC (Florida single-member LLC). 9 specialized agents providing PhD-level expertise in compliance, tax strategy, asset protection, and business operations. Triggers on keywords like LLC, taxes, expenses, annual report, EIN, compliance, bookkeeping, deductions, filing, sunbiz, quarterly, S-Corp, retirement, audit, insurance, cash flow, mentor, teach, learn.

Use when user needs LLM system architecture, model deployment, optimization strategies, and production serving infrastructure. Designs scalable large language model applications with focus on performance, cost efficiency, and safety.

Expert LLM architect specializing in large language model architecture, deployment, and optimization. Masters LLM system design, fine-tuning strategies, and production serving with focus on building scalable, efficient, and safe LLM applications.

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

Multi-level caching strategies for LLM applications - semantic caching (Redis), prompt caching (Claude/OpenAI native), cache hierarchies, cost optimization, and Langfuse cost tracking with hierarchical trace rollup for 70-95% cost reduction

Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.

Centralized AI-readable documentation repository with 245+ frameworks and tools. Use to find documentation, add new sources, or update existing docs. Located at ~/github/llm-code-docs.

Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

LLM-powered documentation generation for narrative architecture docs, tutorials, and developer guides. Uses AI consultation to create contextual, human-readable documentation from code analysis and spec data.

Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.

Optimize documentation for AI coding assistants and LLMs. Improves docs for Claude, Copilot, and other AI tools through c7score optimization, llms.txt generation, question-driven restructuring, and automated quality scoring. Use when asked to improve, optimize, or enhance documentation for AI assistants, LLMs, c7score, Context7, or when creating llms.txt files. Also use for documentation quality analysis, README optimization, or ensuring docs follow best practices for LLM retrieval systems.

Extract structured data from construction documents using LLMs. Process RFIs, submittals, contracts, specifications. Convert unstructured PDFs to structured JSON/Excel.

Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators. This skill applies when optimizing request batching to minimize cost while meeting latency thresholds, particularly when dealing with shape compilation costs, padding overhead, and multi-bucket request distributions. Use this skill for tasks involving batch planning, shape selection, generation-length bucketing, and cost-model-driven optimization for neural network inference.

Optimize prompts for better LLM outputs through systematic analysis and refinement

Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a specific task, understand model capabilities, get pricing information, or need help selecting between GPT-4, Claude, Gemini, Llama, or other LLMs. Provides benchmark-based rankings, cost analysis, and use-case-specific recommendations across reasoning, code generation, long context, multimodal, and other capabilities.

Expert in building production-grade streaming interfaces for LLM responses that feel instant and responsive.

Generate and update HTML dashboards for LLM usage (Claude, Gemini, Kiro, VS code, Cline, etc). Use when the user wants to visualize their AI coding assistant usage statistics, view metrics in a web interface, or analyze historical trends.

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping.

Generate an llms.txt file for any project or website following the llmstxt.org specification. Use when asked to create llms.txt, generate LLM-friendly documentation, make a project AI-readable, or prepare documentation for language models.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Research standards/patterns via MCP Ref. Generates Standards Research for Story Technical Notes subsection. Reusable worker.

Top orchestrator for complete doc system. Delegates to ln-110 coordinator (project docs via 5 L3 workers) + ln-120-150 workers. Phase 4: global cleanup. Idempotent.

Coordinates project documentation creation. Gathers context once, detects project type, delegates to 5 L3 workers (ln-111-115). L2 Coordinator invoked by ln-100.

Creates 2 backend docs (api_spec.md, database_schema.md). L3 Worker invoked CONDITIONALLY when hasBackend or hasDatabase detected.

Creates test documentation (testing-strategy.md + tests/README.md). Establishes testing philosophy and Story-Level Test Task Pattern. L2 Worker in ln-100-documents-pipeline workflow.

Builds interactive HTML presentation with 6 tabs (Overview, Requirements, Architecture/C4, Tech Spec, Roadmap, Guides). Creates presentation/README.md hub. L2 Worker under ln-100-documents-pipeline.

CREATE/REPLAN Stories for Epic (5-10 Stories). Delegates ln-001-standards-researcher for standards research. Decompose-First Pattern. Auto-discovers team/Epic.

Validates Stories/Tasks with GO/NO-GO verdict, Readiness Score (1-10), Penalty Points, and Anti-Hallucination verification. Auto-fixes to reach 0 points, delegates to ln-002 for docs. Use when reviewing Stories before execution or when user requests validation.

L3 Worker. Reviews task implementation for quality, code standards, test coverage. Creates [BUG] tasks for side-effect issues found outside task scope. Sets task Done or To Rework. Usually invoked by ln-400 with isolated context, can also review a specific task on user request.

Fixes tasks in To Rework and returns them to To Review. Applies reviewer feedback only for the selected task.

Runs a single Story final test task (label "tests") through implementation/execution to To Review.

Story-level quality orchestrator with 4-level Gate (PASS/CONCERNS/FAIL/WAIVED) and Quality Score. Pass 1: code quality -> regression -> manual testing. Pass 2: verify tests/coverage -> calculate NFR scores -> mark Story Done. Use when user requests quality gate for Story or when ln-400 delegates quality check.

Worker that checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Validates architectural decisions via MCP Ref: (1) Optimality - is chosen approach the best? (2) Compliance - does it follow best practices? (3) Performance - algorithms, configs, bottlenecks. Reports issues with SEC-, PERF-, MNT-, ARCH-, BP-, OPT- prefixes.

Orchestrates test planning pipeline (research → manual → auto tests). Coordinates ln-511, ln-512, ln-513. Invoked by ln-500-story-quality-gate.

Researches real-world problems, competitor solutions, and customer complaints before test planning. Posts findings as Linear comment for ln-512 and ln-513.

Performs manual testing of Story AC via executable bash scripts saved to tests/manual/. Creates reusable test suites per Story. Worker for ln-510.

Plans automated tests (E2E/Integration/Unit) using Risk-Based Testing after manual testing. Calculates priorities, delegates to ln-301-task-creator. Worker for ln-510.

Audit project documentation quality across 8 categories (Hierarchy, SSOT, Compactness, Requirements, Actuality, Legacy, Stack Adaptation, Semantic Content). Delegates to ln-601 for deep semantic verification of project documents. Use when documentation needs quality review, after major doc updates, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.