update

Author: Palashio

src/docs.json

@@ -191,8 +191,8 @@
                 {
                   "group": "Additional resources",
                   "pages": [
-                    "langsmith/langsmith-cli",
                     "langsmith/polly",
+                    "langsmith/langsmith-cli",
                     "langsmith/skills",
                     {
                       "group": "Data management",

src/langsmith/skills.mdx

@@ -82,7 +82,7 @@ export LANGSMITH_PROJECT=<default-project>
 - Datasets: Turn traces into evaluation datasets (final_response, single_step, trajectory, RAG) and optionally upload to LangSmith.
 - Evaluators: Define code or LLM‑as‑judge evaluators and attach them to datasets (offline) or projects (online).
 
-Each skill directory ships with a `SKILL.md` plus optional `scripts/` helpers you can run or adapt. These skills are designed to plug into compatible coding agents (such as Claude Code or DeepAgents CLI), though you can also reuse the helper scripts directly if you prefer not to wire up a full agent.
+Each skill directory ships with a `SKILL.md` plus optional `scripts/` helpers you can run or adapt. These skills are designed to plug into compatible coding agents (such as Claude Code or DeepAgents CLI), though you can also reuse the helper scripts directly if you prefer not to wire up a full agent. For heavier querying, exports, or automation, you can pair these skills with the [LangSmith CLI](/langsmith/langsmith-cli) to script against the same projects, datasets, and evaluators from your terminal.
 
 ## Manual install