Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

extension-lm-provider

改 VS Code 语言模型提供商、多协议请求/流解析、工具调用、thinking、models.dev 发现或 Commit Message。Use when: genericProvider, lmChatProviderAdapter, coding-plans.vendors, apiStyle, anthropic/openai 兼容。

132 repo starsObserved in 1 repos
Agent Building

langchain-dev-guide

LangChain / LangGraph engineering pitfalls and verified fixes. Covers DeepAgents, OpenAI-compatible model integration (including Chinese provider adapters: DeepSeek, Qwen, GLM, etc.), middleware, streaming, multi-agent orchestration, and other common development issues. Use when hitting unexpected behavior, making architecture decisions, or integrating Chinese LLM providers during LangChain development.

132 repo starsObserved in 1 repos
Agent Building

memory-engine

Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/save, /reflect, /handoff, /check) or memory-related questions. Not for general programming tasks.

132 repo starsObserved in 1 repos
Agent Building

ml-foundation-potentials

Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.

132 repo starsObserved in 1 repos
Agent Building

neqsim-agent-handoff

Agent-to-agent communication schema for NeqSim. USE WHEN: composing multi-agent pipelines where one agent's output feeds another agent's input. Defines structured result formats for fluid definitions, simulation results, and design outputs that agents can pass to each other.

132 repo starsObserved in 1 repos
Agent Building

openviking-memory

Reference guidance for OpenViking setup and layered-memory migration in Aeloon. Runtime usage should rely on provider-native viking_* tools, not this skill.

132 repo starsObserved in 1 repos
Agent Building

prompt-patterns

Practical prompt patterns and techniques for effective Claude Code usage. Reference when crafting prompts, planning workflows, or debugging interactions.

132 repo starsObserved in 1 repos
Agent Building

tracking-schema

Use when the user wants schema preparation, event design, selector validation, schema review, or event-spec generation.

132 repo starsObserved in 1 repos
Agent Building

Claude Code Orchestration

Skill for orchestrating Claude Code sessions from OpenClaw. Covers launching, monitoring, multi-turn interaction, lifecycle management, notifications, and parallel work patterns.

131 repo starsObserved in 1 repos
Agent Building

customize-system-prompt

Guide for customizing OhMyCode's AI personality and behavior via system prompt. Use when user wants to change how the AI behaves, its tone, or its instructions.

131 repo starsObserved in 1 repos
Agent Building