LLM & Agents

Convert documents (PDF, EPUB, PPTX, DOCX, XLSX, HTML, images) to Markdown/JSON/HTML using marker-pdf with Claude Haiku LLM enhancement for accurate table, math, and form extraction. Use when user needs to extract content from documents, convert PDFs to markdown, or process document files.

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking, and reproducible evidence.

Builds real-time collaborative features with Liveblocks including presence, cursors, storage, comments, and notifications. Use when adding multiplayer experiences, collaborative editing, or live cursors to React applications.

This skill should be used when the user asks to "create a machine class", "configure Proxmox provider", "debug provider registration", "set up CEL storage selectors", "troubleshoot Omni provider", "check provider status", "create a Talos cluster", or needs guidance on Omni + Proxmox infrastructure integration for Talos Kubernetes clusters.

Access official Claude Code documentation including comprehensive guides on hooks, MCP servers, agent skills, slash commands, settings, CLI reference, security, memory, plugins, and troubleshooting. Use when the user asks about Claude Code features, configuration, capabilities, or best practices. ALWAYS use this skill instead of guessing about Claude Code functionality - it contains the authoritative documentation from docs.anthropic.com with automatic updates. Also includes comprehensive skill creation guide with helper scripts when users want to create new skills.

Main TDD workflow command. Finds next test in PLAN.md and executes complete TDD cycle automatically. This is the primary command for TDD development as specified in CLAUDE.md.

Setup vector embeddings and semantic search for document collections. Use for AI-powered similarity search, finding related documents, and preparing knowledge bases for RAG systems.

Multi-tier LLM routing for cost optimization in the BidDeed.AI ecosystem. Routes tasks to appropriate model tier based on complexity, achieving 40-55% FREE tier processing. Use when making API calls, selecting models, implementing chat interfaces, or optimizing AI costs. Tiers: FREE (gemini-2.5-flash 1M context), ULTRA_CHEAP (deepseek-v3.2), CHEAP, STANDARD, PREMIUM (claude-sonnet-4), ULTRA (claude-opus-4.5).

Perform high-recall codebase retrieval using semantic search and symbol indexing. Use when you need to find specific code, understand project structure, or verify architectural patterns before editing.

Complete SDK for controlling Reachy Mini robot - head movement, antennas, camera, audio, motion recording/playback. Covers architecture (daemon/client), deployment modes (USB, wireless, simulation, on-Pi), and app distribution. Also includes advanced application patterns: MovementManager, layered motion, audio-reactive movement, face tracking, LLM tool systems, and OpenAI realtime integration. Use when: (1) Writing code to control Reachy Mini, (2) Moving the robot head or antennas, (3) Accessing camera/video, (4) Playing/recording audio, (5) Recording or playing back motions, (6) Looking at points in image or world space, (7) Understanding robot capabilities, (8) Connecting to real or simulated robot, (9) Building conversational AI apps, (10) Integrating with LLMs/OpenAI, (11) Deploying apps to robot, (12) Any robotics task with Reachy Mini.

Optimizes or analyzes prompts using proven strategies. Use when user provides a prompt for optimization/analysis, or before you generate any prompt content yourself (commands, skills, agents, docs, instructions). Two modes: OPTIMIZE (returns optimized prompt), CONSULT (analysis only). Trigger phrases: 'optimize prompt', 'analyze this prompt', 'make concise'.

Meta-skill that scaffolds, validates, and packages other Agent Skills. Enforces code-first (MCP is the special case) via archetypes and filesystem-based workflows.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Agency and execution. Edit code semantically, invoke LLMs, search the web, query security services, and discover relevant skills.

Active coordinator for building AI-powered side-gigs in 2025. Use when users want to build micro-niche products, validate business ideas, create MVPs, or launch profitable side businesses. This skill orchestrates sub-agents to execute market research, product design, business validation, and launch planning. Triggers include "help me build a side hustle," "validate my business idea," "find market opportunities," "build an AI product," or "launch a side-gig."

Deep expertise for documentation lifecycle orchestration. Quality assessment frameworks, workflow patterns, delegation protocols, and release checklists. Auto-loads for doc-expert agent.

Install agent skills from various sources including local paths, GitHub URLs, or the agent-skills repository. Use when adding new skills to a project or user environment.

Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, fresh Claude) for second opinions when stuck on bugs or making architectural decisions. Use when: debugging attempts have failed, making significant architectural choices, security concerns, or need fresh perspective. Automatically suggests consultation after one failed attempt. Provides synthesis comparing multiple AI perspectives with web research, thinking mode, and repo-aware analysis.

Use when presenting a plan/summary to user and requesting explicit approval before proceeding. Generic approval gate for /audit, /build, /architect, /debug commands. Checks for auto-approve conditions ("do without approval" in prompt).

ChatBotプロジェクトに新しいAI APIを統合するためのスキル。APIクラスの実装パターン、プロキシ設定、ストリーミング実装を提供します。新しいAI APIを追加する時、APIクラスを実装する時、ストリーミング機能を追加する時、サーバープロキシを設定する時に使用してください。