Skip to content
Skills Library
AI & agents · Building & coding

deep

/deep

Load the Deep Agents reference before planning, writing, reviewing, testing or debugging anything that uses deepagents, create_deep_agent, LangChain agents, LangGraph (checkpointers, stores, threads, interrupts, streaming), backends, subagents, agent memory, skills or middleware. Use for any work on this repo's agent, and as the framework check in Topping Out's ground investigation. Layer 1 is deepagents-ref/ (checked against deepagents 0.7.34 code); layer 2 is the docs-langchain MCP server.

Repository
toppingout ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Load the Deep Agents reference before planning, writing, reviewing, testing or debugging anything that uses deepagents, create_deep_agent, LangChain agents, LangGraph (checkpointers, stores, threads, interrupts, streaming), backends, subagents, agent memory, skills or middleware. Use for any work on this repo's agent, and as the framework check in Topping Out's ground investigation. Layer 1 is deepagents-ref/ (checked against deepagents 0.7.34 code); layer 2 is the docs-langchain MCP server.

Triggers from the description

s agent, and as the framework check in Topping Out
Original author description

Load the Deep Agents reference before planning, writing, reviewing, testing or debugging anything that uses deepagents, create_deep_agent, LangChain agents, LangGraph (checkpointers, stores, threads, interrupts, streaming), backends, subagents, agent memory, skills or middleware. Use for any work on this repo's agent, and as the framework check in Topping Out's ground investigation. Layer 1 is deepagents-ref/ (checked against deepagents 0.7.34 code); layer 2 is the docs-langchain MCP server.

How it works

SKILL.md has no level-two headings · 17 lines, 186 words

SKILL.md preview
---
name: deep
description: Load the Deep Agents reference before planning, writing, reviewing, testing or debugging anything that uses deepagents, create_deep_agent, LangChain agents, LangGraph (checkpointers, stores, threads, interrupts, streaming), backends, subagents, agent memory, skills or middleware. Use for any work on this repo's agent, and as the framework check in Topping Out's ground investigation. Layer 1 is deepagents-ref/ (checked against deepagents 0.7.34 code); layer 2 is the docs-langchain MCP server.
---

# Deep Agents reference

Never answer Deep Agents, LangChain or LangGraph questions from memory: this API changed a lot in 0.7.

1. Read `deepagents-ref/AGENTS.md`. It holds the layer map, the find order, the layer-2 usage and the review checklist.
2. Read `deepagents-ref/wiki/constitution.md`. For agent work, also read `deepagents-ref/wiki/agent-setup.md`, the checked setup.
3. Then follow the section of `AGENTS.md` that fits the task:
   - **Plan or design:** `wiki/decisions.md`, then `wiki/anti.md`, then the topic page.
   - **Build:** the topic page's `## Quick reference` and `## Gotchas`. Quote the gotcha that applies. For tests, `wiki/testing.md`.
   - **Debug:** the Symptom → cause table in `wiki/anti.md`.
   - **Review:** the review checklist in `AGENTS.md`.
   - **Unknown term or symbol:** `wiki/lookup.md`.
   - **Not in layer 1:** `wiki/gaps.md`, then layer 2, the `docs-langchain` MCP. Put "python" in the query, read the page by the exact path returned, and label the answer "not checked against 0.7.34".
4. After writing code, run `python deepagents-ref/scripts/check_imports.py <files>` and do the rest of the verify step in `AGENTS.md`.
5. Cite the wiki page or source path behind each claim. Where layer 2 and layer 1 disagree, layer 1 wins.

Versions

RepositoryScoreLicence
This page · kaithoughtarchitect/toppingout86MIT
gtlpanda/PandaStack100MIT

Database snapshot: 13.11.2026 · package version 89458ec902e1 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100langchain
    Build AI agents with LangChain v1 and LangGraph in Python. Use this skill whenever the user mentions LangChain, LangGraph, create_agent, init_chat_model, @tool, ToolRuntime, agent middleware, human-in-the-loop, structured output, MCP tools (langchain.mcp, MCPAdapter), RAG,…
  • 100langchain-components
    Decision guide for building agents with LangChain, LangGraph, and Deep Agents in Python, covering framework choice, multi-agent patterns, checkpointers, middleware, and tool safety. Use when designing, building, or reviewing LangChain agents or RAG apps.
  • 100migrating-deep-agents-to-pydantic-ai-harness
    Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use…
  • 100deepagents-implementation
    Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
  • 100migrating-langchain-to-pydantic-ai
    Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct LangGraph graphs, persistence, interrupts, streaming, and `create_deep_agent` projects…
  • 100langchain-dev-guide
    LangChain / LangGraph engineering pitfalls and verified fixes. Covers DeepAgents, structured output, OpenAI-compatible model integration (including Chinese provider adapters: DeepSeek, Qwen, GLM, etc.), middleware, streaming, multi-agent orchestration, and other common…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.