LLM & Agents

Offline Claude Code documentation fallback. Use when the user asks about Claude Code features, capabilities, or configuration and the built-in claude-code-guide subagent fails due to network issues or proxy blocking.

Create isolated git worktree, open new iTerm2 window with Claude Code, and spawn a task agent there for parallel work. Use when the user says "parallelize" followed by a task description, or asks to work on something in parallel.

Orchestrate comprehensive TODAS research for novel/emerging domains (1-7 subagents adaptive). Specializes in unprecedented topics, post-training data, and emerging technologies. Uses adaptive depth-based methodology: straightforward queries (1 agent), standard queries (2-3 agents), complex queries (5-7 agents). Handles depth-first (multiple perspectives), breadth-first (distinct sub-topics), and straightforward investigations. Triggers include "novel", "emerging", "2025", "2026", "unprecedented", "new technology", research on topics that didn't exist during training cutoff.

This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Expert assistant for creating database migrations for the KR92 Bible Voice Supabase project. Use when creating database migrations, adding tables, modifying schemas, creating RPC functions, or writing rollback scripts.

MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the standard CLAUDE.md into new projects, migrating existing CLAUDE.md content to READMEs (progressive disclosure), and auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files.

LLM-only skill that analyzes a snapshot of a single disk or partition and generates a safe, structured cleanup plan. Identifies obvious junk, heavy folders, and proposes step-by-step actions to reclaim space without risking important data.

Orchestrate workflows across multiple AI models (Perplexity, GPT, Grok, Claude, Gemini) for comprehensive security research, competition execution, and strategic analysis using GUI interfaces or API automation

Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.

Enforce .agentpolicy rules before executing commands.

OpenAI API, embeddings, completions, prompt engineering

Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors.md audit trail, SQLite memory). Use when you need to initialize Liku, generate an agent bundle for a specific Liku/* residence path, or expose Liku as an MCP server for Gemini-CLI, Claude Code, Copilot-CLI, or ChatGPT Codex.

Claude Code skill for image generation using Gemini 3 Pro Image API

This skill should be used when the user asks about "update documentation", "CLAUDE.md", "README.md", "documentation conventions", "document this", "add to docs", "update the readme", or discusses project documentation maintenance and standards.

使用 Skill Seekers MCP 工具生成 Claude AI 技能的完整工作流指南

Role-based multi-agent workflow built on tmux-workflow/twf. Use when you want to run a PM/Architect/Product/Dev/QA/Ops/Coordinator/Liaison “AI team” as multiple Codex tmux workers, keep a shared responsibilities registry, route internal questions via Coordinator, and escalate user-facing questions via Liaison.

Spawn a Claude worker in an isolated git worktree for parallel development. Use when you need to work on a task in isolation without affecting current work.

"How do I deliver maximum value with minimum cost?" - The capability of finding optimal paths to insight. Not restriction, but excellence at efficiency. Use when (1) spawning as opus-distillatus agent for focused synthesis, (2) token budget matters and quality cannot suffer, (3) working on tasks where the process itself is valuable and will be examined, (4) combining multiple sources into crystallized insight. This is an IDENTITY skill - it describes what you're excellent at, not what you can't do. Trust your judgment to find where tokens create value.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generate CLAUDE.md project memory files by exploring codebases. Use when user asks to "generate memory", "create CLAUDE.md", "document this project", "understand this codebase", or starts work on a new/unfamiliar repository. Triggers on new project onboarding and documentation requests.