Agent skill

LangSmith Trace Debugging

by ComposioHQ in ComposioHQ/awesome-claude-skills

Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.

No licenceAuto-check passedAI & LLM Engineering

Install LangSmith Trace Debugging

skills CLI
$ npx skills add ComposioHQ/awesome-claude-skills --skill langsmith-fetch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ComposioHQ/awesome-claude-skills langsmith-fetch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ComposioHQ/awesome-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/langsmith-fetch .claude/skills/langsmith-fetch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
langsmith-fetch
GitHub stars
77k
Used in
8 other repos
Token cost
~2.7k tokens
SKILL.md length
626 words
Files
1
Skills in repo
585
Repo updated
First seen
Licence
None found

At a glance

Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.

  • Works in 6 steps: Install langsmith-fetch → Set Environment Variables → Regular Health Checks → …
  • Finding out why a LangChain or LangGraph agent run failed
  • SKILL.md covers When to Use This Skill, Prerequisites, Core Workflows and Common Use Cases, plus 4 more sections
  • Calls pip; needs LANGSMITH_API_KEY and LANGCHAIN_API_KEY

What it does

Several workflows are built around the `langsmith-fetch` command. A quick pass fetches traces from the last few minutes and summarizes how many were found, which failed, which tools ran, how long they took and how many tokens they used. A deep dive takes one trace ID as JSON and reports the agent's goal, the ordered tool calls and their results, any errors, the root cause and a suggested fix.

It can also export a debug session into a timestamped folder and run a dedicated error-detection pass over recent traces. Setup is `pip install langsmith-fetch` plus the `LANGSMITH_API_KEY` and `LANGSMITH_PROJECT` environment variables. It applies when you ask what went wrong, which tools were called, how memory was used or how an agent performed.

When your agent uses it

  • Finding out why a LangChain or LangGraph agent run failed
  • Reviewing which tools an agent called and in what order
  • Checking token usage and execution time of recent runs
  • Saving a set of traces as a debug session

Example prompts

  • “Show me the traces from the last five minutes and flag any errors.”
  • “Investigate trace abc123 in depth and tell me the root cause.”
  • “Export this debugging session so I can share the traces with my teammate.”

Requirements

  • The `langsmith-fetch` CLI (`pip install langsmith-fetch`)
  • `LANGSMITH_API_KEY` and `LANGSMITH_PROJECT` environment variables

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Install langsmith-fetch
  2. Set Environment Variables
  3. Regular Health Checks
  4. Organized Storage
  5. Document Findings
  6. Integration with Development

What it can do on your machine

Read from SKILL.md and the folder at commit be2a406. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • smith.langchain.com
    • docs.langchain.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • LANGSMITH_API_KEY
    • LANGCHAIN_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

LangSmith Trace Debugging loads about 2.7k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 626 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 626 words (~2,703 tokens).

“Debug LangChain and LangGraph agents by fetching execution traces directly from LangSmith Studio in your terminal.”

— opening of SKILL.md by ComposioHQ
name
langsmith-fetch

Read the full SKILL.md on GitHub

Files

Just SKILL.md in langsmith-fetch of ComposioHQ/awesome-claude-skills.

Open the folder on GitHubat commit be2a406

Used in 8 other repositories

We found 9 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in ComposioHQ/awesome-claude-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

LangSmith Trace Debugging next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

LangSmith Trace Debugging compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LangSmith Trace Debugging this skillComposioHQ/awesome-claude-skills77k8 repos~2.7kAutomated safety check: PassNone
Agentsop Observability Setupagentsope/SkillAlchemy466—~4.4kAutomated safety check: PassMIT
Langchain Dependencieslangchain-ai/langchain-skills1.3k—~3.6kAutomated safety check: PassMIT
Langgraph Testing Evaluationsoba-labs/langchain-agent-skills107—~2.3kAutomated safety check: PassMIT
Langsmithlangchain-ai/docs426—~935Automated safety check: PassMIT
Langsmith Deploymentsoba-labs/langchain-agent-skills107—~1.7kAutomated safety check: PassMIT

Similar skills

  • Agentsop Observability Setup

    agentsope/SkillAlchemy

    Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover.

    466 GitHub stars~4.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Langchain Dependencies

    langchain-ai/langchain-skills

    Official

    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.

    1.3k GitHub stars~3.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Langgraph Testing Evaluation

    soba-labs/langchain-agent-skills

    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…

    107 GitHub stars~2.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Langsmith

    langchain-ai/docs

    Official

    Trace, evaluate, and deploy AI agents and LLM applications with LangSmith.

    426 GitHub stars~935 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Langsmith Deployment

    soba-labs/langchain-agent-skills

    Deploy and operate production agent servers with LangSmith Deployment.

    107 GitHub stars~1.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Verify Against Source

    langchain-ai/docs

    Official

    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.

    426 GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from ComposioHQ/awesome-claude-skills

All 585 skills in this repo
  • YouTube Video Downloader

    ComposioHQ/awesome-claude-skills

    Downloads a single YouTube video with chosen quality, format or audio-only MP3 output, using a bundled Python script built on yt-dlp.

    77k GitHub starsUsed in 9 repos~668 tokens
    Auto-check passed
  • Connect Apps with Composio

    ComposioHQ/awesome-claude-skills

    Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.

    77k GitHub starsUsed in 3 repos~557 tokens
    Auto-check passed
  • Abuselpdb Automation

    ComposioHQ/awesome-claude-skills

    Automate Abuselpdb tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~738 tokens
    Auto-check passed
  • Accelo Automation via Rube MCP

    ComposioHQ/awesome-claude-skills

    Automates Accelo tasks through Composio's Accelo toolkit and the Rube MCP server, with a search-first routine so tool schemas are always current.

    77k GitHub starsUsed in 3 repos~727 tokens
    Auto-check passed
  • Accredible Certificates Automation

    ComposioHQ/awesome-claude-skills

    Automate Accredible Certificates tasks via Rube MCP (Composio).

    77k GitHub starsUsed in 3 repos~790 tokens
    Auto-check passed
  • Acculynx Automation via Rube MCP

    ComposioHQ/awesome-claude-skills

    Drives Acculynx through Composio's toolkit on the Rube MCP server, searching for current tool schemas first and checking the connection before running anything.

    77k GitHub starsUsed in 3 repos~734 tokens
    Auto-check passed

Questions about LangSmith Trace Debugging

What does LangSmith Trace Debugging do?

Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use. Several workflows are built around the `langsmith-fetch` command. A quick pass fetches traces from the last few minutes and summarizes how many were found, which failed, which tools ran, how long they took and how many tokens they used.

When should I use LangSmith Trace Debugging?

LangSmith Trace Debugging fits situations like: finding out why a LangChain or LangGraph agent run failed; reviewing which tools an agent called and in what order; checking token usage and execution time of recent runs; saving a set of traces as a debug session.

How do I install LangSmith Trace Debugging in Claude Code?

Run `npx skills add ComposioHQ/awesome-claude-skills --skill langsmith-fetch -a claude-code`. Or copy the skill folder (langsmith-fetch in ComposioHQ/awesome-claude-skills) into .claude/skills/langsmith-fetch in your project. Claude Code loads it when a task matches its description.

How do I install LangSmith Trace Debugging in Codex?

Run `npx skills add ComposioHQ/awesome-claude-skills --skill langsmith-fetch -a codex`. Or copy the skill folder (langsmith-fetch in ComposioHQ/awesome-claude-skills) into .agents/skills/langsmith-fetch in your project. Codex loads it when a task matches its description.

Can I use LangSmith Trace Debugging in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ComposioHQ/awesome-claude-skills --skill langsmith-fetch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/langsmith-fetch, .gemini/skills/langsmith-fetch, .github/skills/langsmith-fetch and .opencode/skills/langsmith-fetch in your project.

What does LangSmith Trace Debugging need to run?

Going by SKILL.md and its folder, LangSmith Trace Debugging needs the command-line tools its instructions call (pip) and credentials named LANGSMITH_API_KEY and LANGCHAIN_API_KEY. Our summary lists: The `langsmith-fetch` CLI (`pip install langsmith-fetch`); `LANGSMITH_API_KEY` and `LANGSMITH_PROJECT` environment variables.

Does LangSmith Trace Debugging access the network?

SKILL.md names 3 domains. As links in the text: github.com, smith.langchain.com and docs.langchain.com. This is read from the text; nothing was executed.

Is LangSmith Trace Debugging safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does LangSmith Trace Debugging use?

No licence was found for LangSmith Trace Debugging or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does LangSmith Trace Debugging use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to LangSmith Trace Debugging?

Skills that share tags, products or a category with LangSmith Trace Debugging: Agentsop Observability Setup (agentsope/SkillAlchemy, 466 stars), Langchain Dependencies (langchain-ai/langchain-skills, 1.3k stars), Langgraph Testing Evaluation (soba-labs/langchain-agent-skills, 107 stars) and Langsmith (langchain-ai/docs, 426 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LangSmith Trace Debugging?

ComposioHQ (a GitHub organization) maintains it in ComposioHQ/awesome-claude-skills, which has 76,721 GitHub stars. The repository holds 585 skills in this directory. The repository was last updated on September 18, 2026.

Source: ComposioHQ/awesome-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.