AI model or service
LangSmith agent skills for Claude Code, Codex and other agents.
- skills
- 31
- official
- 20
- Type
- AI model or service
- Website
- langchain.com
- Official GitHub
- langchain-ai
- Reviews
- See LangSmith on Enlisted
LangSmith skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
Official (20 skills)
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads. | langchain-ai/ | 159 | — | ~1.4k | Automated safety check: Pass | MIT | 4 days ago |
| 2 | Add, move, rename, or delete a page on the LangChain docs site. | langchain-ai/ | 424 | — | ~2k | Automated safety check: Pass | MIT | today |
| 3 | Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision. | langchain-ai/ | 1.3k | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 4 | A skill your agent uses when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet scripts and used as Mintlify… | langchain-ai/ | 424 | — | ~4.6k | Automated safety check: Pass | MIT | today |
| 5 | INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. | langchain-ai/ | 1.3k | 1 repo | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 6 | INVOKE THIS SKILL when building, iterating on, copying, or sharing a LangSmith Custom App — a React/TypeScript UI that runs inside LangSmith and reads the LangSmith API. | langchain-ai/ | 159 | — | ~3.2k | Automated safety check: Pass | MIT | 4 days ago |
| 7 | Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice. | langchain-ai/ | 424 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 8 | Build stateful, durable agent workflows with LangGraph. An agent skill from langchain-ai/docs. | langchain-ai/ | 424 | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 9 | Trace, evaluate, and deploy AI agents and LLM applications with LangSmith. | langchain-ai/ | 424 | — | ~935 | Automated safety check: Pass | MIT | today |
| 10 | Starting point for LangChain, LangGraph and Deep Agents projects: picks the right layer for the task, then points to install steps, setup and the next skill to load. | langchain-ai/ | 1.3k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 11 | INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. | langchain-ai/ | 1.3k | — | ~2.8k | Automated safety check: Notes | MIT | yesterday |
| 12 | Document new or changed docs-team tooling on the Notion tooling pages. | langchain-ai/ | 424 | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 13 | Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. | langchain-ai/ | 1.3k | — | ~549 | Automated safety check: Notes | MIT | yesterday |
| 14 | Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. | langchain-ai/ | 1.3k | — | ~548 | Automated safety check: Notes | MIT | yesterday |
| 15 | Scaffold a minimal local LangGraph agent in Python by following the official quickstart. | langchain-ai/ | 1.3k | — | ~454 | Automated safety check: Notes | MIT | yesterday |
| 16 | Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. | langchain-ai/ | 1.3k | — | ~455 | Automated safety check: Notes | MIT | yesterday |
| 17 | INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. | langchain-ai/ | 1.3k | — | ~8.7k | Automated safety check: Notes | MIT | yesterday |
| 18 | Scaffold a minimal local LangChain agent in Python by following the official quickstart. | langchain-ai/ | 1.3k | — | ~368 | Automated safety check: Notes | MIT | yesterday |
| 19 | Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. | langchain-ai/ | 1.3k | — | ~377 | Automated safety check: Notes | MIT | yesterday |
| 20 | Check that a code sample, API signature, default, or behavior claim in the docs is actually true, by running it or reading the product source. | langchain-ai/ | 424 | — | ~1.6k | Automated safety check: Pass | MIT | today |
Community
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 21 | Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use. | ComposioHQ/ | 77k | 9 repos | ~2.7k | Automated safety check: Pass | No licence | 19 days ago |
| 22 | Inspects an LLM evaluation setup for missing error analysis, unvalidated judges and vanity metrics, and ranks the problems by impact with fixes. | ai-evals-course/ | 1.5k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 12 days ago |
| 23 | Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...). | langfuse/ | 299 | — | ~1.7k | Automated safety check: Notes | MIT | 6 days ago |
| 24 | Use the writetodos tool effectively for task planning and decomposition in Deep Agents. | soba-labs/ | 107 | — | ~2.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 25 | LLM observability platform for tracing, evaluation, and monitoring. | Orchestra-Research/ | 13k | 3 repos | ~2.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 26 | Initialize, validate, and troubleshoot Deep Agents projects in Python or JavaScript using the deepagents package. | soba-labs/ | 107 | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 27 | Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. | agentsope/ | 457 | — | ~4.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 28 | A skill your agent uses when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory… | soba-labs/ | 107 | — | ~2.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 29 | Deploy and operate production agent servers with LangSmith Deployment. | soba-labs/ | 107 | — | ~1.7k | Automated safety check: Pass | MIT | 1 mo ago |
| 30 | Fetch, organize, and analyze LangSmith traces for debugging and evaluation. | soba-labs/ | 107 | — | ~1.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 31 | Build original LangGraph agents for Warden Protocol and prepare them for publishing in Warden Studio. | majiayu000/ | 666 | 1 repo | ~4.4k | Automated safety check: Notes | MIT | today |
Questions, answered from the data.
What is the best LangSmith skill?
Langsmith Online Eval Engineering (official) from langchain-ai/langsmith-skills ranks first of the 31 LangSmith skills listed here, with the highest score: its repository has 159 GitHub stars, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Add Docs Page and LangGraph Decision Models.
Is there an official LangSmith skill?
20 of the 31 LangSmith skills are official, published by the vendor's own GitHub organization: Langsmith Online Eval Engineering, Add Docs Page, LangGraph Decision Models, Docs Code Samples, Langchain Dependencies and 15 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.