Claude Skills by majiayu000

Use when building AI agents with OpenAI's Agents SDK. Triggers include creating agents, implementing tools, multi-agent handoffs, guardrails, MCP integration, tracing. Also for using LiteLLM to run agents on free/alternative models (Anthropic, Gemini). NOT for general OpenAI API usage (use openai-python SDK docs instead).

Send bulk messages to dancers via Ballee Support chat. Use when sending apology messages, system updates, or personalized notifications to users.

Use when integrating Drizzle ORM with Bun's SQLite driver for type-safe schema definitions and migrations.

Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.

Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構 agent loop。

Agent development tools - generation and validation. Use when creating new agent templates from scaffolding, or validating and linting existing agent profiles for correctness and completeness.

Analyzes task descriptions and classifies them into categories for agent selection

Analyzes task descriptions and classifies them into categories for agent selection

Anthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP servers, or encountering CLI not found, context length exceeded errors.

Build AI agents using the Claude Agent SDK. Covers query functions,

Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

專責處理 CBF (Commanded Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Command Side 設計與實作。支援 Java、TypeScript、Go 多語言。

This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase agents.

Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

Real-time companion monitor for OpenClaw agents

Use when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration, and best practices for specialized AI assistants

Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows. Covers agent definition, frontmatter options, tool restrictions, and spawning patterns.

Autonomous financial research agent for stock analysis, financial statements, metrics, prices, SEC filings, and crypto data.

Guide for building AI agents with Google ADK (Agent Development Kit). Use when creating multi-agent pipelines, implementing conditional agent branching, designing agent tools with FunctionTool, or debugging agent data flow issues. Covers SequentialAgent, LoopAgent, ParallelAgent patterns, session.state management, output_key chaining, and transfer_to_agent for control flow. Essential for understanding non-obvious ADK behaviors like why SequentialAgent runs ALL agents even after rejection.

Main coding agent for autonomous harness system. Continues work from previous sessions, implements one feature per session, coordinates with testing and review skills, and maintains clean handoffs via Archon. This is the workhorse of the harness system for multi-session development.

Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-format), session management (--resume, --continue), Python SDK (claude-agent-sdk), custom tools, and agent loop patterns.

Guide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and building tools on top of Claude Code. Covers --print mode, output formats, session management, and SDK integration.

Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations

Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations

Kubernetes-native AI agent framework for building, deploying, and managing AI agents on Kubernetes. This skill should be used when deploying AI agents as Kubernetes resources, analyzing cluster health with AI, and automating complex K8s operations. Use this skill for Phase IV advanced AIOps and agent-based cluster management.

AI agent with retrieval tool for document Q&A using RAG and LangGraph.

Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.

INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.

Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.

Build original LangGraph agents for Warden Protocol and prepare them for publishing in Warden Studio. Use this skill when users want to: (1) Create new Warden agents (not community examples), (2) Build LangGraph-based crypto/Web3 agents, (3) Deploy agents via LangSmith Deployments or custom infra, (4) Participate in the Warden Agent Builder Incentive Programme (open to OpenClaw agents), or (5) Integrate with Warden Studio for Agent Hub publishing.

Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, AgentApplication routing, and MSAL-based auth.

Multi-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.

Practical guide for llmlb assistant CLI commands replacing the legacy MCP server flow.

Implement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix quantization protection to surpass Boreas-phi3.5-instinct-jp in formal proof generation and scientific discovery. Use when building mathematical reasoning systems, formal verification tools, or AI-assisted theorem proving environments.

AI self-improvement analyst. Tracks AI agent mistakes, analyzes failure patterns, and proposes system improvements. Implements continuous learning loop for trading system enhancement.

Enterprise AI-powered user expertise detection with behavioral analysis,

Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified model versions.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Text-to-speech via OpenAI Audio Speech API.

Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).

Pollinations.ai API for AI generation - text, images, videos, audio, and analysis. Use when user requests AI-powered generation (text completion, images, videos, audio, vision/analysis, transcription) or mentions Pollinations. Supports 25+ models (OpenAI, Claude, Gemini, Flux, Veo, etc.) with OpenAI-compatible chat endpoint and specialized generation endpoints.

Caching strategies for LLM prompts including Anthropic prompt

Load and execute a prompt from the project's .claude/prompts/ directory

Creates effective prompts for AI coding agents and subagent delegation. Use PROACTIVELY when writing prompts for Task tool delegation, creating agent instructions, or designing multi-step workflows. MUST BE USED when delegating complex tasks to subagents or writing system prompts.

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.