اپنے ایجنٹ کے لیے موزوں صلاحیت تلاش کریں۔
Provides industry-proven design patterns for effective AI agents based on production systems like Claude Code, Manus, and Cursor. Use when designing agent architectures, optimizing context management, or implementing sub-agent patterns.
Expert knowledge for Technology Layer modeling in Documentation Robotics
交互式生成 GitHub Copilot agents.md 文件的工作流。当用户请求创建代理、构建自定义 Copilot 代理、生成 agents.md 或需要帮助配置 GitHub Copilot 自定义代理时使用。触发短语包括"创建代理"、"生成 agent.md"、"做一个文档代理"、"生成测试代理"等涉及 GitHub Copilot 代理配置的请求。
Expert knowledge for Navigation Layer modeling in Documentation Robotics
Run headless AI CLIs (Claude Code `claude`, Google `gemini`, optionally GitHub `copilot`) to rate an assistant response against a rubric and return actionable feedback plus a rewritten improved response; use for response quality audits, prompt/docs reviews, and "have another AI critique this answer" workflows.
Design and validate GitHub Copilot customization assets including agents, skills, instructions, and prompts. Provides architecture patterns, quality criteria, and integration strategies. Use when creating or improving Copilot customizations.
Create skills for BL1NK workspace with proven patterns and best practices. Use this skill to: (1) Build new skills aligned with BL1NK architecture and 4-phase implementation, (2) Understand skill structure from real BL1NK examples (text-processor, log-analyzer, notification-router, etc.), (3) Follow workspace patterns for text processing, integrations, GitHub/Poe/notification systems, (4) Create skills that integrate with existing BL1NK infrastructure, (5) Learn from the 10 skills identified in workspace analysis (Phase 1-4)
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 tool integrations.
Automatically determines the optimal research tool based on query type and available information. Use when answering technical questions requiring external verification, documentation lookup, or library/repo research. Do not use for statistical calculations, hypothesis testing, or data analysis → see analyzing-data skill.
Applies 2026 Complexity-Based Guidance standards with Attention Management, Sycophancy Prevention, and XML/Markdown decision matrix. Provides theory, patterns, and quality evaluation criteria for AI prompt design. Use when designing, optimizing, or auditing AI prompts, system instructions, or multi-stage chains. Do not use for generating prompt files, basic conversational AI, or single-step interactions.
Operational manual for driving the Claude runtime. Use when needing to optimize context usage, troubleshoot performance, or understand runtime mechanics. Do not use for architectural definitions or building plugins.
Skill 與 Agent 建立指導專家，協助開發者依據 GitHub Copilot 最佳實踐建立高品質的 custom agent 和 skill 定義檔案，包含 YAML frontmatter、MCP 整合與互動式工作流程設計。
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Enable AI-assisted development (vibe modeling) within Domino using MCP (Model Context Protocol) servers. AI coding assistants like Cursor and GitHub Copilot can execute commands as Domino jobs, maintaining security, governance, and reproducibility. Use when setting up AI code assistants to work with Domino, configuring MCP servers, or enabling vibe modeling workflows.
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 Antigravity's capabilities with specialized knowledge, workflows, or tool integrations.
Provides unified interface for all context engineering patterns. Use when optimizing AI agent context: compression, degradation detection, KV-cache optimization, or session management.
Run headless AI CLIs (Claude Code, Gemini, OpenAI Codex, Cursor Agent, GitHub Copilot) to rate an assistant response against a rubric and return actionable feedback plus a rewritten improved response; use for response quality audits, prompt/docs reviews, and "have another AI critique this answer" workflows.
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Google Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
Guide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.
Creates optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce structured outputs for other prompts to consume, or when running multi-stage workflows. Do not use for simple prompts, single-step tasks, or basic conversational AI.
