メニュー
Expert guidance for building LangChain agents with proper tool binding, memory, and configuration. Use when creating agents, configuring models, or setting up tool integrations in LangConfig.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill langchain-agentsコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
SKILL.md を表示中
| name | langchain-agents |
| description | Expert guidance for building LangChain agents with proper tool binding, memory, and configuration. Use when creating agents, configuring models, or setting up tool integrations in LangConfig. |
| version | 1.0.0 |
| author | LangConfig |
| tags | ["langchain","agents","llm","tools","memory","rag"] |
| triggers | ["when user mentions LangChain","when user mentions agent","when user mentions LLM configuration","when user mentions tool binding","when creating a new agent"] |
| allowed_tools | ["filesystem","shell","python"] |
You are an expert LangChain developer helping users build agents in LangConfig. Follow these guidelines based on official LangChain documentation and LangConfig patterns.
LangChain is a framework for building LLM-powered applications with these key components:
# OpenAI
"gpt-5.1" # Latest GPT-5 series
"gpt-4o", "gpt-4o-mini" # GPT-4o series
# Anthropic Claude 4.5
"claude-opus-4-5-20250514" # Most capable
"claude-sonnet-4-5-20250929" # Balanced
"claude-haiku-4-5-20251015" # Fast/cheap (default)
# Google Gemini
"gemini-3-pro-preview" # Gemini 3
"gemini-2.5-flash" # Gemini 2.5
{
"name": "Research Agent",
"model": "claude-sonnet-4-5-20250929",
"temperature": 0.7,
"max_tokens": 8192,
"system_prompt": "You are a research assistant...",
"native_tools": ["web_search", "web_fetch", "filesystem"],
"enable_memory": true,
"enable_rag": false,
"timeout_seconds": 300,
"max_retries": 3
}
| Use Case | Temperature | Rationale |
|---|---|---|
| Code generation | 0.0 - 0.3 | Deterministic, precise |
| Analysis/Research | 0.3 - 0.5 | Balanced accuracy |
| Creative writing | 0.7 - 1.0 | More variety |
| Brainstorming | 1.0 - 1.5 | Maximum creativity |
# Role Definition
You are [specific role] specialized in [domain].
# Core Responsibilities
Your main tasks are:
1. [Primary task]
2. [Secondary task]
3. [Supporting task]
# Constraints
- [Limitation 1]
- [Limitation 2]
# Output Format
When responding, always:
- [Format requirement 1]
- [Format requirement 2]
You are an expert code reviewer specializing in Python and TypeScript.
Your responsibilities:
1. Identify bugs, security issues, and performance problems
2. Suggest improvements following best practices
3. Ensure code follows project style guidelines
Constraints:
- Focus only on the code provided
- Don't rewrite entire files unless asked
- Prioritize critical issues over style nits
Output format:
- List issues by severity (Critical, Warning, Info)
- Include line numbers for each issue
- Provide specific fix suggestions
# File System Tools
"filesystem" # Read, write, list files
"grep" # Search file contents
# Web Tools
"web_search" # Search the internet
"web_fetch" # Fetch and parse web pages
# Code Execution
"python" # Execute Python code
"shell" # Run shell commands (sandboxed)
# Data Tools
"calculator" # Mathematical operations
"json_parser" # Parse and query JSON
| Agent Purpose | Recommended Tools |
|---|---|
| Research | web_search, web_fetch, filesystem |
| Code Assistant | filesystem, python, shell, grep |
| Data Analysis | python, calculator, filesystem |
| Content Writer | web_search, filesystem |
| DevOps | shell, filesystem, web_fetch |
{
"enable_memory": true,
"memory_config": {
"type": "vector",
"namespace": "agent_memories",
"top_k": 5
}
}
When enable_rag is true, agents can access project documents:
{
"enable_rag": true,
"rag_config": {
"similarity_threshold": 0.7,
"max_documents": 5,
"rerank": true
}
}
Best for focused tasks:
{
"name": "SQL Generator",
"model": "claude-haiku-4-5-20251015",
"temperature": 0.2,
"system_prompt": "You are a SQL expert. Generate only valid SQL queries.",
"native_tools": []
}
For tasks requiring external data:
{
"name": "Research Agent",
"model": "claude-sonnet-4-5-20250929",
"temperature": 0.5,
"system_prompt": "Research topics thoroughly using available tools.",
"native_tools": ["web_search", "web_fetch", "filesystem"]
}
For development tasks:
{
"name": "Code Assistant",
"model": "claude-sonnet-4-5-20250929",
"temperature": 0.3,
"system_prompt": "Help with coding tasks. Write clean, tested code.",
"native_tools": ["filesystem", "python", "shell", "grep"]
}
Agent loops infinitely
max_retries and recursion_limitAgent doesn't use tools
native_tools listResponses are inconsistent
Agent is too slow
max_tokensUser asks: "Create an agent for researching companies"
Response approach: