Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
中文简介正在准备中。当前显示原文说明。
899 个 · 按相关度排序
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
中文简介正在准备中。当前显示原文说明。
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
中文简介正在准备中。当前显示原文说明。
Design AI copilot experiences for products. TRIGGERS - Use when user needs help with ai-copilot-designer related tasks.
中文简介正在准备中。当前显示原文说明。
Evaluate AI copilot performance. TRIGGERS - Use when user needs help with ai-copilot-evaluation related tasks.
中文简介正在准备中。当前显示原文说明。
Visual whiteboard collaboration for Copilot CLI. Creates an interactive whiteboard that opens in your browser — draw, sketch, add sticky notes, then share everything back with Copilot. Copilot sees your drawings and text, and responds with analysis, suggestions, and ideas.
中文简介正在准备中。当前显示原文说明。
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.
中文简介正在准备中。当前显示原文说明。
Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions.
中文简介正在准备中。当前显示原文说明。
Builds an HTML presentation for enterprise AI adoption decisions, using a dark purple gradient template. It organizes local-first agent workflows, risk controls, return on investment, and rollout plans for leadership, IT, and security audiences.
中文简介正在准备中。当前显示英语简介。
Create HTML slides about choosing and connecting AI models in OpenDesign using your own API key. Use a terminal-style template to explain costs, quality, and model routing decisions, with speaker notes and presentation controls.
中文简介正在准备中。当前显示英语简介。
Create an HTML engineering presentation using the tech-sharing template, with OpenDesign internals as the example subject. Organize the slide plan, supporting evidence, visual direction, and speaker notes, with presentation controls and animation support.
中文简介正在准备中。当前显示英语简介。
Build HTML slides for an OpenDesign live demo, showing how a short prompt becomes a runnable design. Organize the presentation, visual direction, speaker notes, and animations using the supplied deck template.
中文简介正在准备中。当前显示英语简介。
Define security controls for AI coding agents used by a team. Covers command and file permissions, secret scanning, isolated execution environments, code review gates, and audit trails, with configuration examples to adapt.
中文简介正在准备中。当前显示英语简介。
Translate an English MkDocs documentation set into a chosen language while preserving folder structure and Markdown formatting. Update shared content references, navigation labels, notice labels, and language configuration, and check that every source file has been translated.
中文简介正在准备中。当前显示英语简介。
Prevent recurring coding-agent mistakes by turning repository evidence into specific instructions, automated checks, regression tests, and failure records. Also checks whether guidance has become outdated and documents changes, verification results, and follow-up work in an adoption report.
中文简介正在准备中。当前显示英语简介。
Analyze local documents or public web pages and produce a Word report with source screenshots beside each factual claim. Yellow highlights identify the supporting passages so readers can visually check the analysis against the original.
中文简介正在准备中。当前显示英语简介。
Set up a dedicated workspace for a new workstream, with a journal and a folder for structured signals. Record its purpose, scope, and first steps so later sessions can pick up the context.
中文简介正在准备中。当前显示英语简介。
Configure GitHub Dependabot to keep dependencies, the packages a project relies on, updated. Organize update pull requests into groups, set schedules and exclusion rules, and configure security updates across projects with multiple packages or package systems.
中文简介正在准备中。当前显示英语简介。
Builds an evidence map for a disputed decision, linking supporting evidence, counterevidence, qualifications, and missing facts to precise source passages. Produces a structured JSON artifact that makes the reasoning and unresolved questions available for review.
中文简介正在准备中。当前显示英语简介。
Design, refine, or review web and iOS interfaces using the product’s existing components and visual style. Consult relevant screen examples when useful, then inspect the result for layout problems, inaccessible controls, and broken interactions.
中文简介正在准备中。当前显示英语简介。
Guides development of MCP servers that let AI access external actions and data using mcp-use. Covers project setup, tools, reusable prompts, interactive React interfaces, authentication, validation, and deployment through task-specific reference guides.
中文简介正在准备中。当前显示英语简介。
Guides development of ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK, covering server tools, React interfaces, and shared state. This skill is deprecated and directs users to mcp-app-builder.
中文简介正在准备中。当前显示英语简介。
Build MCP servers, which expose tools and data to AI agents, with mcp-use. The material covers server functions, reusable prompts, and interactive React widgets, but this skill is deprecated and points to mcp-app-builder as its replacement.
中文简介正在准备中。当前显示英语简介。
Reorganize long AGENTS.md, CLAUDE.md, and similar instruction files into a short main file with links to topic-specific documents. Identifies conflicting rules and deletion candidates, then checks links and coverage so instructions remain organized and accessible.
中文简介正在准备中。当前显示英语简介。
Route data analysis, large-file processing, and web retrieval through context-mode tools, returning only relevant results to the conversation. This helps preserve the context window, the limited amount of information an AI can work with at once.
中文简介正在准备中。当前显示英语简介。