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.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →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.
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.
This skill should be used when users want to build LLM-powered applications using LangChain. It provides patterns for initializing any LLM provider (OpenAI, Anthropic, Google, xAI), building agent loops with tools, and implementing structured output. Use this skill when users ask to create chatbots, AI agents, or applications that need LLM integration with tool calling or structured responses.
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.
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
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.
Comprehensive guide to LLM safety and guardrails implementation for AI systems.
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.
Comprehensive guide to securing LLM applications including prompt injection prevention, jailbreak detection, guardrails, and red teaming methodologies
LLMs, prompt engineering, RAG systems, LangChain, and AI application development
Research best practices via MCP Ref/Context7/WebSearch and create documentation (guide/manual/ADR/research). Single research, multiple output types.
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.
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.
Traffic-First opportunity discovery. KILL funnel filters ideas by traffic channel, demand, competition, revenue, interest, MVP-ability. Outputs one idea + one channel recommendation.
CREATE/REPLAN Stories for Epic (5-10 Stories). Delegates ln-001-standards-researcher for standards research. Decompose-First Pattern. Auto-discovers team/Epic.
Orchestrates task operations. Analyzes Story, builds optimal plan (1-6 implementation tasks), delegates to ln-301-task-creator (CREATE/ADD) or ln-302-task-replanner (REPLAN). Auto-discovers team ID.
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.
Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.
Coordinates project structure migration to Clean Architecture
| Atributo | Valor |
LobeVidol - Virtual idol creation platform with MMD dance support, VRM character customization, multi-provider LLM integration, and interactive 3D conversations
Local development environment context management
Local environment management - run SQL queries, set up fake payments, reset test data. Use when the user needs help with local database operations or test data setup.
Expert guide for understanding the Local Skills MCP server repository - its structure, architecture, and implementation. Use when exploring this MCP server's codebase, understanding how Local Skills MCP works internally, or contributing to the project.
Comprehensive guide for using Local Skills MCP - creating skills in the right locations, understanding skill directories, setup, and configuration. Use when creating new skills, deciding where to save skills, setting up the MCP server, or understanding how skill aggregation works.
Local testing setup - start dev server with mock Claude and run tests (unit tests, CLI E2E)
Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools
Execute PowerShell commands on Windows systems with security constraints
Archives completed logs to cloud storage with index management and cleanup
log-auditor
Classifies logs by type (session, test, build) using path patterns and frontmatter analysis
Log problems, bugs, and debugging processes with solutions. Use when encountering issues during development, debugging problems, or documenting solutions for future reference. Maintains DEBUG_LOG.md with structured problem-solution entries.
Orchestrates multi-log workflows with parallel execution for batch operations across many logs
Orchestrates single-log sequential workflows by coordinating operation skills for individual logs
Searches logs by content keywords, patterns, and filters with context extraction
Centralize logs with ELK/EFK and retention policies.
| Atributo | Valor |
Comprehensive guide to preventing PII and secrets from appearing in logs through redaction strategies, safe logging practices, and automated filtering.
Generate creative logo concepts and design directions
logos-reader-architect
Essential knowledge about Logseq DB (database) graphs. Use this skill when working with Logseq DB to ensure accurate understanding of nodes, properties, tags, tasks, and queries. This corrects common misconceptions from file-based Logseq that do NOT apply to DB graphs.
Format any content as a Logseq-compatible outline using nested bullets (no markdown headers, no bold). Works in both Claude Code and Claude Desktop.
Migrate Logseq graphs to Obsidian vaults. Use when the user wants to convert their Logseq notes to Obsidian format, migrate from Logseq, or mentions both Logseq and Obsidian in a migration context. Handles property conversion, admonition blocks, block references, journal renaming, collapsed states, numbered lists, and image syntax. Designed for Claude Code usage from within the user's Logseq graph folder.
Sync Logseq pages tagged with #zotero to Zotero by adding 'in_logseq' tag. Uses batch checking for efficiency. Claude Code only.
> **Version 2.35.0** | PRD to Production | Zero Human Intervention
Create portable AI modules with lazy context loading that work across multiple AI assistants (Claude Code, Cursor, Gemini CLI).
Framework for building AI agents that work effectively across multiple context windows on complex, long-running tasks. Use when building agents for multi-hour/multi-day projects, implementing persistent coding workflows, creating systems that need state management across sessions, or when an agent needs to make incremental progress on large codebases. Provides initializer and coding agent patterns, progress tracking, feature management, and session handoff strategies.