发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Use when user asks to "create lovable prompts", "convert PRD to lovable", "generate lovable sequence", or provides a PRD file and asks to break it into implementation prompts. Converts PRDs into sequenced Lovab...
Use when user asks to "create a skill", "build a skill", or "design a skill". Guides through requirements, solution design, and implementation of token-efficient Claude Code skills.
SmartACE (Agentic Context Engineering) workflow engine with MCP-B (Master Client Bridge) and AMUM-QCI-ETHIC module. Dual database architecture using DuckDB (analytics) + SurrealDB (graph). Uses Blender 5.0 (bpy...
ai-tools同期 - リポジトリと~/.claude/間の設定ファイル同期。to-local/from-local/diffモード。
Context preservation across sessions, checkpoint monitoring, and agent handoffs. Triggers include "save context", "checkpoint", "hand off", "relay context", or when transitioning between sessions.
This skill should be used for autonomous single-repo orchestration. Triggers include "use auto", "autonomous mode", "work on this repo", or when starting a deep work session. LLM ideation discovers work, copilo...
This skill should be used when orchestrating multiple skills together for complex workflows. Triggers include "chain these skills", "use X then Y skill", "multi-skill workflow", "which skills", "suggest skills"...
This skill should be used for autonomous work on complex tasks with ZERO context required. Triggers include "start a loop", "work autonomously", "before I sleep", "take this and run with it", or when claude det...
This skill should be used for all external AI collaboration - consulting, implementing, or reviewing with codex/copilot. Triggers include "pair with codex", "get a second opinion", "delegate this", "consult on"...
This skill should be used when generating structured metaprompts for repeatable tasks. Triggers include "create a metaprompt for X", "generate a review prompt", "make a prompt template", or when building prompt...
This skill should be used when enriching Linear issues with intelligent codebase context, architecture diagrams, and agent-ready prompts. Use for preparing issues for implementation, transforming vague tickets...
Create or refactor skills, guiding an interactive questionnaire, selecting an archetype (workflow/tool/domain), scaffolding from templates, and validating the result. Triggers include "create skill", "new skill...
Orchestrate multiple skills together for complex workflows. Triggers include "chain these skills", "use X then Y skill", "multi-skill workflow", "which skills", or when a task requires capabilities from several...
This skill should be used when creating or refactoring Claude Code skills, guiding an interactive questionnaire, selecting an archetype (workflow/tool/domain), scaffolding from templates, and validating the res...
This skill should be used for interactive clarification with smart HIL question flows. Triggers include "ask me questions", "help me think through", "what should we consider", session start ("what are we workin...
This skill should be used for autonomous work on complex tasks with ZERO context required. Triggers include "start a loop", "work autonomously", "before I sleep", "take this and run with it", or when claude det...
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 Codex's capabilities with specialized knowledge, workflows, or too...
Multi-perspective analysis through parallel agent sessions. Triggers include "analyze from multiple angles", "what are the gaps/patterns/friction", "explore before deciding", pre-refactor landscape mapping. Eac...
Interactive clarification with smart HIL question flows. Triggers include "ask me questions", "help me think through", "what should we consider", session start ("what are we working on"), scope definition ("wha...
External AI collaboration with output contracts. Triggers include "pair with codex", "get a second opinion", "delegate this", "consult on", "review this work". Returns lean, structured JSON responses.
Generate structured metaprompts for repeatable AI tasks. Triggers include "create a metaprompt for X", "generate a review prompt", "make a prompt template", or when building prompts for AI tools.
Generate `llms.txt` and `llms-full.txt` for a docs/product website from just a URL. Detect and reuse an existing `/llms.txt`, discover the docs source repo via “Edit this page”/GitHub links, fall back to `sitem...
Configure and optimize AI assistance (Copilot, agents, skills) for AROG development. Use when users ask about Copilot, custom agents, or AI integration.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fi...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。