Editorial illustration for LangSmith CLI adds three portable skills for coding agents in the repo
LangSmith CLI Boosts Coding Agents with 3 New Skills
LangSmith CLI adds three portable skills for coding agents in the repo
Why does a CLI matter for today’s coding agents? While many tools claim to boost productivity, only a handful let developers plug in reusable capabilities without rewriting core logic. The LangSmith command‑line interface now bundles three portable “skills” that any agent supporting skill functionality can import directly.
Here’s the thing: the new additions sit in the publicly available langsmith‑skills repository, meaning teams don’t need to wait for a proprietary rollout. Instead, they can pull the modules, integrate them into their pipelines, and start leveraging the same building blocks that power LangSmith’s own services. The move hints at a modest shift toward modular AI tooling—one that could ease the friction of adding tracing, dataset curation, or evaluation steps to existing codebases.
It’s not a wholesale overhaul, but a practical set of utilities aimed at developers who want to extend their agents with minimal overhead. The upcoming quote spells out exactly what those three skills are and how they’re intended to be used.
We're sharing a set of LangSmith skills that can be ported to any coding agent that supports skill functionality. LangSmith Skills Within the langsmith-skills repo, we maintain a set of 3 skills: - trace: add tracing to existing code, and query traces - dataset: build up datasets of examples - evaluator: evaluate agents over those datasets These three areas represent the three core areas of LangSmith AI engineering. We will add to this set of skills over time. Skill Impacts Using skills, we saw significant improvements in Claude Code's performance on basic LangSmith tasks.
Will developers adopt it? The LangSmith CLI arrives with three portable skills—trace, dataset, and evalu—aimed at giving coding agents direct access to the LangSmith ecosystem. By embedding tracing into existing code and exposing query capabilities, the trace skill promises clearer insight into agent execution, while the dataset skill automates the assembly of example collections, and the evalu skill offers a built‑in performance gauge.
On a recent evaluation set, Claude Code’s success rate leapt from 17 % to 92 % when these tools were applied, suggesting a substantial boost in task accuracy. Yet the report provides no detail on the diversity of tasks, the size of the test set, or how other models might respond, leaving open questions about generalizability. The CLI is described as agent‑native, offering developers the building blocks they need, but whether the skill interface integrates smoothly with all existing agents remains uncertain.
In short, the addition of these three skills marks a concrete step toward more observable and measurable coding agents, though broader validation is still pending.
Further Reading
- Introducing LangSmith Fetch: Debug agents from your terminal - LangChain Blog
- Debugging Deep Agents with LangSmith - LangChain Blog
- Top 5 CLI coding agents in 2026 - Pinggy
Related Reading
Research & Benchmarks Hyperparameter Tuning Reaches 0.9617 Accuracy in 64.59 Seconds
Research & Benchmarks Pharma Cautious as AI Promises Faster Drug Discovery and Smarter Trials
Research & Benchmarks Google AI Advisors Let Users Probe Performance with Conversational “Why” Queries
From Archives Secret meeting sees 94% approve even least‑popular AI resistance stance
From Archives AI data centers move to Arctic edge, boosting Nordic rural economies
Common Questions Answered
What are the three core skills included in the LangSmith CLI?
The LangSmith CLI introduces three portable skills: trace, dataset, and evaluator. These skills enable developers to add tracing to existing code, build datasets of examples, and evaluate agent performance across different scenarios.
How can developers access the new LangSmith skills?
The skills are available in the publicly available langsmith-skills repository, allowing teams to directly import and use them without waiting for a proprietary rollout. Any coding agent that supports skill functionality can leverage these portable capabilities.
What specific benefits does the trace skill provide for coding agents?
The trace skill allows developers to add tracing to existing code and query traces, providing clearer insight into agent execution. This capability helps developers understand and debug the internal workings of their coding agents more effectively.