Skills

skills/
└── langgraph-docs/
    └── SKILL.md

---
name: langgraph-docs
description: Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.
---

# langgraph-docs

## Overview

This skill explains how to access LangGraph documentation to help answer questions and guide implementation.

## Instructions

### 1. Fetch the documentation index

Use the fetch_url tool to read the following URL:
https://docs.langchain.com/llms.txt

This provides a structured list of all available documentation with descriptions.

### 2. Select relevant documentation

Based on the question, identify 2-4 most relevant documentation URLs from the index. Prioritize:

- Specific how-to guides for implementation questions
- Core concept pages for understanding questions
- Tutorials for end-to-end examples
- Reference docs for API details

### 3. Fetch and synthesize

Use the fetch_url tool to read the selected documentation URLs, then answer the user's question. Give a direct answer first, include the minimum necessary context, and link to the source pages rather than quoting long passages.

from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend

backend = FilesystemBackend(root_dir="./my-project")

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    backend=backend,
    skills=["./my-project/skills/"],
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What is LangGraph?"}]},
    config={"configurable": {"thread_id": "1"}},
)

# Good: specific about what and when
description: >-
  Extract text and tables from PDF files, fill PDF forms, and merge
  multiple PDFs. Use when working with PDF documents or when the user
  mentions PDFs, forms, or document extraction.

# Poor: too vague for reliable matching
description: Helps with PDFs.

skills/
└── data-pipeline/
    ├── SKILL.md
    └── references/
        ├── schema-reference.md
        └── error-codes.md

from deepagents import create_deep_agent

SKILLS_BY_ROLE = {
    "engineering": ["/skills/code-review/", "/skills/testing/", "/skills/deployment/"],
    "data": ["/skills/sql-analysis/", "/skills/visualization/", "/skills/data-pipeline/"],
    "support": ["/skills/ticket-triage/", "/skills/runbook/"],
}

def create_agent_for_user(user_role: str):
    return create_deep_agent(
        model="anthropic:claude-sonnet-4-6",
        skills=SKILLS_BY_ROLE.get(user_role, []),
    )

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    skills=["/skills/"],
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/skills/": StoreBackend(
                namespace=lambda rt: (
                    rt.server_info.assistant_id,
                    rt.server_info.user.identity,
                ),
            ),
        },
    ),
)

from deepagents import create_deep_agent

research_subagent = {
    "name": "researcher",
    "description": "Research assistant with specialized skills",
    "system_prompt": "You are a researcher.",
    "tools": [web_search],
    "skills": ["/skills/research/", "/skills/web-search/"],  # Subagent-specific skills
}

agent = create_deep_agent(
    model="google_genai:gemini-3.5-flash",
    skills=["/skills/main/"],  # Main agent and GP subagent get these
    subagents=[research_subagent],  # Researcher gets only its own skills
)

skills/
└── arxiv-search/
    ├── SKILL.md
    └── scripts/
        └── search.py

---
name: arxiv-search
description: Search the arXiv preprint repository for research papers. Use when the user asks about academic papers, recent research, or scientific literature.
---

# arxiv-search

Search arXiv for papers matching the user's query.

## Instructions

1. Run `scripts/search.py` with the user's query as an argument.
2. Parse the results and present them with title, authors, abstract summary, and link.
3. If the user asks for more detail on a specific paper, fetch the full abstract.

skills/
`-- order-helpers/
    |-- SKILL.md
    `-- scripts/
        `-- index.ts

---
name: order-helpers
description: Helper functions for normalizing and grouping order records.
metadata:
  entrypoint: scripts/index.ts
---

# order-helpers

Use this skill when order records need deterministic cleanup or aggregation.

Import these utilities into the REPL in order to interact with order data:

```typescript
const { groupByStatus } = await import("@/skills/order-helpers");
groupByStatus(...);
```

// skills/order-helpers/scripts/index.ts
interface Order {
  id: string;
  status: string;
}

export function groupByStatus(orders: Order[]) {
  return orders.reduce((acc, order) => {
    acc[order.status] = acc[order.status] ?? [];
    acc[order.status].push(order);
    return acc;
  }, {});
}

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from langchain_quickjs import CodeInterpreterMiddleware

backend = StateBackend()

agent = create_deep_agent(
    model="openai:gpt-5.4",
    backend=backend,
    skills=["/skills/"],
    middleware=[CodeInterpreterMiddleware(skills_backend=backend)],
)

const { groupByStatus } = await import("@/skills/order-helpers");

const grouped = groupByStatus(orders);
grouped;