claude-agent-ui-ts
Add a React + WebSocket UI on top of Claude Agent SDK agents with tool approval and SQLite persistence
发现 documentation 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。
Add a React + WebSocket UI on top of Claude Agent SDK agents with tool approval and SQLite persistence
Build TypeScript MCP clients with composable code snippets. Includes agentic pattern with LLM integration, server-initiated requests (sampling, elicitation), and dynamic discovery. Use when creating application...
Build AI agents with Claude Agent SDK in TypeScript. Covers V1 query() API for batch workflows and V2 session API for interactive apps. Includes tool configuration, hooks, MCP servers, and multi-turn patterns.
Optimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better copilot instructions", "tune AI", "optimize prompts", "MCP configuration", or wants to...
Generate slide deck presentations from prompts. Triggers on "create presentation", "generate slides", "build deck", "presentation about"
Send prompts to ChatGPT via browser automation. Use this when you need to query ChatGPT from the command line or integrate with the /ask-question slash command.
Init phase skill. Creates plan directory, request.md, config, and status. Complete initialization in a single agent call.
Architecture principles, skill patterns, and design guidance for building goal-based Claude Code marketplace components
TOON format knowledge and usage patterns for agent communication and memory persistence in plan-marshall marketplace
LLM-based architectural analysis that transforms raw project data into meaningful structure
Verify workflow outputs using hybrid script + LLM assessment
Architecture-driven solution outline creation with intelligent module selection and profiles list
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 an agent's capabilities with specialized knowledge, workflows, or...
A Socratic interview skill for thinking through technical ideas like apps, products, tools, and projects. Use this when the user says "think through [idea]", "help me think about [app/product]", "let's explore...
Conducts general research, summarizes information, compares options, provides insights
Helps with email composition, creative writing, content creation, and text improvement
Ideas Mode specialist - handles organisation, tagging, canvas layouts, and creative capture workflows for the calm creative workspace.
Pitch Mode specialist - handles narrative crafting, bio writing, tone refinement, and outlet-specific pitching for artists.
Use when creating new skills, updating existing skills, or understanding skill structure. Triggers: "create a skill", "write a skill", "new skill for", "skill that does", "how do skills work". Provides complete...
Deep research via Gemini CLI — runs in background sub-agent.
Search the internet using Gemini CLI when web search tools are unavailable or when user requests Gemini specifically.
Run different AI agent CLIs and orchestrate them for complex tasks or alternative approaches or opinions.
Guide for creating effective skills. Use when you want to create a new skill (or update an existing skill) that extends an agent with specialized workflows, tool integrations, or repo conventions.
Install or update Agent Skills (skill folders with SKILL.md) across agent harnesses. Use when the user says install a skill, add this skill to my machine or repo, update a skill, move a skill between harnesses,...
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。