Writes connector_config for segment/journey activations using `tdx connection schema <type>` to discover available fields. Use when configuring activations - always run schema command first to see connector-specific fields.
Reconciles data sources using stable identifiers (Pay Number, driving licence, driver card, and driver qualification card numbers), producing exception reports and “no silent failure” checks. Use when you need weekly matching with explicit reasons for non-joins and mismatches.
Advanced td_interval patterns including offset dates (-1d/2025-10-01, -7d/-1d, 0M/now), td_interval_range for debugging, td_time_string for display formatting, and partition pruning optimization.
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.
Managing design tokens and system context for LLM-driven UI development. Covers loading, persisting, and optimizing design decisions within context windows.
ベクトルデータベースとセマンティック検索を使用してLLMアプリケーションのためのRetrieval-Augmented Generation（RAG）システムを構築します。知識に基づいたAI、ドキュメントQ&Aシステムの構築、またはLLMと外部ナレッジベースの統合時に使用します。
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. Keywords: 创建技能, 技能开发, 构建claude技能, 技能设计, 技能模板, create skill, build skill, develop skill, skill creation, skill development, skill template, skill design, skill builder, skill generator, 技能生成器, 技能构建器
Comprehensive template and guidelines for documenting Field Agents including technical specifications, system prompts, tool specifications, user interactions, and standardized documentation structure
One-way TTS mode - Claude speaks aloud while user types. Use when user says: 'speak', 'read aloud', 'vocal on', 'lis-moi', 'parle-moi', or wants Claude to vocalize responses without responding vocally themselves. For bidirectional voice conversation (user speaks too), use /conversation instead.
MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer functions, (3) building evaluation datasets from traces, (4) using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), (5) analyzing traces for latency/errors/architecture, (6) optimizing agent context/prompts/token usage, (7) debugging evaluation failures. Covers the full eval workflow: trace analysis -> dataset building -> scorer creation -> evaluation execution.
Official skill generator for VS Code Agent Skills; scaffolds new skills with correct directory structure and validation, and is the upstream dependency for authoring or modifying any other skill in this repository.
Apply prompting techniques when creating prompts, agents, commands, system instructions, or SKILL.md files. Use for XML tags, multishot examples, chain-of-thought, response prefilling, and Claude 4-specific patterns.
Prioritize brevity, directness, and clarity in all responses with minimal token usage.
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 services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Comprehensive guide for debugging Claude Agent SDK errors, TypedDict contracts, and internal SDK processing issues
AI 采访式内容创作系统。不是人写，也不是 AI 自动写，而是 AI 分析后采访人再按人的风格写。通过问答不断沉淀用户画像（观点、写作风格、思考逻辑），持续迭代演进。支持博客、社交媒体、观点文章等场景。
Extract topics from text collections using LDA (Latent Dirichlet Allocation) with keyword extraction and topic visualization.
Guide for building MCP (Model Context Protocol) servers that integrate external APIs/services with LLMs. Covers Python (FastMCP) and TypeScript (MCP SDK) implementations.
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Gong API for searching calls, transcripts, and conversation intelligence. Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics. Supports listing calls, fetching transcripts, user management, and activity stats.
