Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
Log access to Claude configuration artefacts (CLAUDE.md, rules, skills, commands, agents). This skill should be invoked automatically after reading configuration files to track usage.
将多个研究智能体的发现综合成连贯、结构化的研究报告。解决矛盾、提取共识、创建统一叙述。当多个研究智能体完成研究、需要将发现组合成统一报告、发现之间存在矛盾时使用此技能。
Create and manage a Notion-based tweet performance tracking system for "poor man's reinforcement learning"
将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。
Generate website images with Gemini 3 Native Image Generation. Covers hero banners, service cards, infographics with legible text, and multi-turn editing. Includes Australian-specific imagery patterns. Use when stock photos don't fit, need text in images, or require consistent style across assets.
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns. Use when: creating custom sub-agents, delegating bulk operations, parallel research, understanding built-in agents, or configuring agent tools/models.
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.
构建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在使用 Python (FastMCP) 或 Node/TypeScript (MCP SDK) 构建 MCP 服务器以集成外部 API 或服务时使用。
创建高效技能的指南。当用户想要创建新技能（或更新现有技能）以扩展 Claude 的能力，包括专业知识、工作流程或工具集成时，应使用此技能。
Active context curation to fight context rot. Curates what goes into limited context window from constantly evolving information universe. 39% improvement, 84% token reduction.
Migrate AI image generation from Google Gemini 2.5 Flash to BytePlus SeeDream v4.5. Use when: (1) User wants to switch from Gemini to SeeDream/BytePlus for image generation, (2) User asks about migrating image generation APIs or replacing Gemini with BytePlus, (3) User needs cost optimization or better image quality for AI-generated images, (4) User mentions SeeDream, BytePlus, or wants SDK-to-REST API migration for image generation
Guides VibeCoder (non-technical users) through natural language development. Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
Guidance for creating effective prompts, chains, and gates using CAGEERF methodology
Write effective prompts for AI systems — system prompts, agent instructions, skills, or any LLM prompt. Use when creating or improving prompts.
Triggers: question threshold, decisive, autonomous, clarifying questions Guidance on when to ask clarifying questions vs proceed with standard approaches. Reduces interaction rounds while preventing wrong assumptions.
Ensures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'why did you...?', 'will that work?', 'have you considered...?'. Use when user asks about your decisions, challenges an approach, or requests assessment. Prevents interpreting questions as implicit instructions or criticism.
