GitHub
nlx-design-stack
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
☆ 2查看技能
tools llm ai AI 技能
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。
分类目录: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
unstuck-scaling
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers
☆ 2查看技能
GitHub
ai-teammate-model
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
☆ 2查看技能
GitHub
three-layer-agent-stack
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
☆ 2查看技能
GitHub
chatter-driven-development
Use when designing futuristic agentic workflows, when wanting AI to proactively act on team communications, or when eliminating the bottleneck of formal specifications
☆ 2查看技能
GitHub
codex-collaboration
This skill should be used when the user asks to "collaborate with Codex", "use Codex for planning", "get Codex review", "delegate to Codex", "Codexと協調", "Codexにレビューを依頼", "Codexに計画を作成させたい",...
☆ 2查看技能
GitHub
opence-compound
Document learnings, capture repeatable workflows as skills, and prepare to compound an opence change.
☆ 2查看技能
GitHub
prompt-sync-workflow
Coordinate prompt and skill updates across related changes
☆ 2查看技能
GitHub
create-plan
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
☆ 2查看技能
GitHub
retrace
This skill should be used when the user asks to "find past conversations", "recall what was done", "search history", "look up previous work", "how did we handle X", "what was that implementation", "find similar...
☆ 2查看技能
GitHub
web-research
Web search with automatic Qdrant storage for building persistent knowledge
☆ 2查看技能
GitHub
rag-builder
Build Retrieval-Augmented Generation systems with vector databases
☆ 2查看技能
GitHub
agent-builder
Build specialized sub-agents for the workflow system
☆ 2查看技能
GitHub
knowledge-ingestion-patterns
Patterns for ingesting knowledge into vector databases and RAG systems
☆ 2查看技能
GitHub
prompt-template
Create and manage reusable prompt templates
☆ 2查看技能
GitHub
task-decomposition
Break down complex tasks into actionable, atomic steps that can be executed by individual agents.
☆ 2查看技能
GitHub
embedding-comparison
Compare and evaluate embedding models for semantic search
☆ 2查看技能
GitHub
ai-video-generation
AI video generation patterns using Sora, Runway, Pika, and other AI video tools. Use when generating videos from text prompts, image-to-video conversion, AI video editing, or integrating AI video APIs.
☆ 2查看技能
GitHub
qdrant-patterns
Store and retrieve documents using Qdrant for RAG workflows. Use for persistent memory, research storage, and semantic search.
☆ 2查看技能
GitHub
rag-wrapper
Patterns for wrapping any agent with RAG context from Qdrant. Use to add persistent memory to imported or external agents.
☆ 2查看技能
GitHub
mcp-server-builder
Build Model Context Protocol servers for Claude Code integration
☆ 2查看技能
GitHub
skill-creator
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 to...
☆ 2查看技能
GitHub
deep-research
Conduct comprehensive, multi-source research on any topic using web search, documentation lookup, and critical analysis. This skill should be used when users request thorough investigation, deep research, or co...
☆ 2查看技能
GitHub
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
☆ 2查看技能
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。