Claude Skills by majiayu000

Use when selecting between MCP tools based on task complexity and requirements - provides a structured selection workflow and decision rationale.

Tool use patterns for Claude including schema design, tool_choice modes, result handling, parallel execution, error recovery, and extended thinking integration.

Patterns for Claude tool use including tool definition schemas, multi-tool orchestration, parallel tool calls, error handling, and result formatting. Use when the user is defining tools for Claude, building agentic workflows with tool calling, handling tool errors, or implementing multi-step tool pipelines.

Auto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on project needs and waits for user approval before writing to .claude/.

Troubleshooting protocol with MiniMax subagent delegation - NEVER stop early, use all resources before asking user

Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot

Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot

Invoke Claude Code CLI from Python orchestrators and shell scripts. Use when asked to "spawn claude as subprocess", "automate claude cli", "run claude headless", "configure --allowedTools", "set up claude hooks", or "parallel claude invocation". Covers permissions, directory access (--add-dir), hooks, sandbox mode, and async patterns.

Use when programmatically creating or managing agent trajectories in TypeScript - provides TrajectoryClient for persistent storage and TrajectoryBuilder for in-memory construction

Validation agent that validates plan tech choices against current best practices

Ultimate autonomous execution engine. Plan → Execute → Test → Never Stop Until Done. Use when the user wants hands-off completion with no questions, automatic recovery from any failure, and proven results.

Short alias for vc-phase-loop. Use when the user invokes "vcf:" or "use vcf:" and wants maximum hands-off completion.

Create and configure VoltAgent AI agents with tools, memory, hooks, and sub-agents. Use when building AI agents, adding agent tools, configuring VoltAgent memory, creating multi-agent workflows, or debugging VoltAgent integrations.

Also called "wr". Optional research agent for broad multi-source research without polluting context. Use when user requests it or when research needs depth across many sites.

当用户要求"微信监听"、"消息提取"、"Agent 开发"、"wxauto"、"Accessibility API"、"UI 自动化"、"输入框控制"、"Platform Agent"，或者提到"微信自动化"、"消息监控"、"WeChat monitoring"时使用此技能。用于开发 WeReply 的 Platform Agent（Windows wxauto 或 macOS Accessibility API）、实现微信消息监听、消息提取、输入框控制和 Agent 错误处理。

Start an autonomous implementation loop from a spec or PRD. Enters plan mode for user approval, enforces command gates (test/lint/typecheck/build), validates dependencies, commits incrementally, and maintains documentation and changelog. Production-ready quality gates.

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.

Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.

Use when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory or context providers; when threads won't deserialize; when workflow checkpointing fails; when migrating from Semantic Kernel or AutoGen; when seeing ChatAgent or AgentThread errors

Train and deploy generative UI agents using behavioral programming constraints, A2A protocol for agent interoperability, and pattern registry for composition. Use when working with agent training, trajectory generation, reward computation, A2A integration, or deploying models.

Complete fixer agent workflow including report discovery, validation strategy (HIGH/MEDIUM/FALSE_POSITIVE confidence), fix application, and fix report generation. Use when implementing or updating fixer agents.

Step-by-step validation workflow for checker agents - initialize report, discover content, validate progressively, finalize with summary. Use when implementing or updating checker agents.

Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic. Use when creating new specialized subagents for Claude Code with agent composition, MCP tool integration, or skill references. Validated with phase-planner-executor (V_instance=0.895).

Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution.

zhimeng's Agent 智能助手操作技能。 触发场景：用户提到"问知识库"、"发日报"、"检查Agent"、"重建索引"、"知识问答"等。

Create your llmops-fine-tuner skill from Unsloth documentation before learning fine-tuning theory

Create your ChatKit Server skill in one prompt, then learn to improve it throughout the chapter

Create your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chapter

Create your RAG skill in one prompt, then learn to improve it throughout the chapter

[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.

Create your OpenAI Apps SDK skill in one prompt, then learn to improve it throughout the chapter

Create your RAG skill in one prompt, then learn to improve it throughout the chapter

Create a reusable skill for evaluating fine-tuned models, benchmarking performance, and detecting quality regressions

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with word-level timestamps. Use when users want to transcribe songs, generate LRC files, or extract lyrics with timestamps from audio.

Add image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.

Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.

Add Ollama MCP server so the container agent can call local models for cheaper/faster tasks like summarization, translation, or general queries.

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.

Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.

Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.

Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.