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。
Build production-ready FastAPI applications with async patterns, Pydantic validation, dependency injection, middleware, and database integration. Use for FastAPI endpoints, async workflows, or API design.
Feature development using DPPM framework (Discover, Plan, Prototype, Monitor). Use for feature planning and multi-agent orchestration.
Reference guide for LLM model IDs, capabilities, pricing, and provider endpoints. Use when selecting a model, comparing provider capabilities, or validating model IDs for {{PROJECT_NAME}}.
Run and evaluate the Skillset smoke test (aliases, sets, and skill invocation) and interpret its JSON reports. Use this when validating $skill/$set behavior or checking Claude Code/Codex headless runs.
0G TeeMLプライバシー保護AI推論の知識。「0G」「TeeML」「プライバシー」「AI推論」で使用。
Analyze the conversation for corrections, approvals, and patterns. Update project skills with learned preferences. Use this when the user says "reflect" or after sessions with explicit feedback/corrections. Aut...
Carga el archivo CLAUDE_PROMPT.md como contexto para aplicar las instrucciones y mejores prácticas del proyecto. Úsalo cuando el usuario quiera aplicar las guías personalizadas, principios de trabajo, o cuando...
Copy or sync Claude skills from ~/.claude/skills into ~/.codex/skills so they are available in Codex. Use when asked to import, migrate, copy, or sync Claude skills, or when moving skills between Claude and Cod...
Guide for using Claude Code subagents effectively. Use when deciding whether to delegate a task to a subagent or handle it directly.
Create new Claude Agent Skills following best practices. Use when user wants to create, scaffold, or update a skill package with proper progressive disclosure structure.
Generate architecture, sequence, state, and ERD diagrams for code understanding. Use when user wants to visualize code structure or document systems.
Capture task outcomes and patterns after completing work. Use after /verify or when a task succeeds/fails to enable adaptive skill evolution.
Analyzes prompts and produces improved versions using Anthropic's prompt engineering best practices. Use when asked to improve, optimize, or review a prompt. Works with standalone prompts or prompts embedded in...
Guide on how to implement Synapse Axons (clients). Covers Smart Axons (interactive) and Raw Axons (reporting only) using MQTT or HTTP. Use this skill when the user asks how to create a new service, sidecar, or...
Build terminal CLI apps using Ink (React for CLIs). This skill should be used when the user wants to create command-line interfaces with React components, terminal UIs, interactive CLI tools, or needs help with...
Automatically manage agent lifecycle, proposals, and registry.
Use when the user asks for a plan or the task is complex/ambiguous. Enforces AGENTS.md workflow and encourages loading other relevant skills.
Document architectural decisions with context and consequences.
Run the full autonomy bootstrap with minimal questions.
Automatiza processo de pesquisa de documentação oficial, extração de melhores práticas e aplicação no projeto Plataforma B2B de treinamento técnico corporativo através de skills/agents/hooks
Bootstrap skill that teaches Claude about the shared Agent-memory system for cross-session and cross-team knowledge
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. LOAD THIS SKILL WHEN: Conversation exceeds 10 turns | completing major features | User says "checkpoint", "...
Build agentic AI applications with multi-step task orchestration, tool calling, and state management. Use when creating AI agents that autonomously perform complex workflows like the Scout Travel Concierge - an...
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...
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。