managed-deep-agents

github:langchain-ai/langchain-skills · first committed 2026-05-21 · source · badge

INVOKE THIS SKILL when creating, running, or operating a Managed Deep Agent against the LangSmith /v1/deepagents private-preview REST API. Covers the agent → MCP server → thread → streamed run flow, tool/interrupt configuration, and the agent file tree (AGENTS.md, skills/, subagents/, tools.json).

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

8 commits to this file on GitHub (newest first).

2026-10-02 · commit 381a7fc · docs: address open skills maintenance issues (#72)
2026-08-26 · commit bd7c43d · fix(managed-deep-agents): MCP connectors exist — correct the "removed" claim
2026-08-07 · commit 92e4f3b · Update managed-deep-agents skill for public beta, add guided setup flow (#58)
2026-07-07 · commit 162bb97 · skills: rewrite managed-deep-agents for the code-first mda CLI iteration (#46)
2026-06-08 · commit 203e837 · docs: update managed deep agents skill
2026-05-22 · commit e252dc3 · fix(mda): interrupt resolution (#41)
2026-05-22 · commit 03d2998 · fix: tavily search tool typo (#40)
2026-05-21 · commit c33cec8 · feat(deploy): add langgraph-cli and managed deep agents skills (#34)

Archived snapshots