发现 research 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。
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, prog...
Install the Vercel AI SDK with AI Elements components. Build a streaming chat interface with the useChat hook.
Build a custom durable AI agent with full control over streamText options, provider configs, and tool loops. Compatible with the Workflow Development Kit.
Build a chat list page with search, rename, and delete functionality. Uses nuqs for URL-synced filters and deep-linkable modal dialogs.
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose improvements plus OSS candidat...
Debug and improve the Bifrost vibe coding experience. Use this skill when working on Bifrost platform development in Claude Code where you have access to Bifrost source code. Helps identify system bugs vs docum...
Best practices for using the Council MCP server in Tzurot v3 development - When to consult external AI, how to structure prompts, model selection, and multi-turn conversations. Use when planning major changes o...
Meta-skill for writing and maintaining Claude Code skills. Use when creating new skills, updating existing skills, or reviewing skill quality. Enforces progressive disclosure and size limits.
Transform raw ideas into structured business requirements by clarifying the problem, defining the solution, and identifying target users. Use when starting stage 00 (init-ideas) or when user asks to define busi...
Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or update an existing skill.
Review and refine MCP skill descriptions to follow the agent skill specification, and record approved overrides in dev-swarm/mcp_descriptions.yaml. Use when the user asks to update one MCP skill description, al...
Add and manage Model Context Protocol (MCP) servers for AI agents, including transports, scopes, and config files. Use when extending agent capabilities with new tools or data sources.
Install AI code agent CLI tools including claude-code, gemini-cli, codex, and github copilot-cli. Use when setting up AI coding assistants or when the user asks to install an AI code agent.
Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash commands, custom commands, or reusable prompts for AI agent CLIs.
Create and maintain AgentV YAML evaluation files for testing AI agent performance. Use this skill when creating new eval files, adding eval cases, or configuring custom evaluators (code validators or LLM judges...
Call LLM via CLI for transcription, vision, speech/image generation, piping prompts, sub-agents, ...
Text manipulation and documentation engine. PRIMARY TOOL FOR TEXT EDITING. Use this skill for ALL text replacement, documentation updates, and file rewriting tasks. SUPERIOR to 'grep' or 'sed' because it unders...
Project Cortex - Structural Knowledge Injection for LLM
The Hippocampus Interface - Vector-based Memory for LLM (LanceDB + FastEmbed)
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely ind...
Create and manage agents (orchestrators, skills, sub-agents). Use when user mentions "create agent", "build agent", "recruit", "new orchestrator", "design skill", "make a sub-agent", or discusses agent architec...
Guide learning and deep understanding through proven methodologies (Socratic, Feynman, Problem-Based). Use when user says "help me understand", "teach me", "explain this", "learn about", "socratic", "feynman",...
Explore problems from multiple perspectives through structured role-playing techniques. Use when user wants to "see different viewpoints", "consider perspectives", "what would X think", "six hats", "stakeholder...
Gera agents experts especializados em areas especificas da codebase. Use quando precisar criar um novo agent expert com knowledge base, sub-comandos e integracao com a codebase.
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。