Langsmith Online Eval Engineering
langchain-ai/langsmith-skills
Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads.
Fetch, organize, and analyze LangSmith traces for debugging and evaluation.
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/langsmith-trace-analyzer .claude/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.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/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .claude/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/langsmith-trace-analyzer .agents/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .agents/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/langsmith-trace-analyzer .cursor/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .cursor/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/soba-labs/langchain-agent-skills.git --path skills/langsmith-trace-analyzer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/langsmith-trace-analyzer .gemini/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .gemini/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/langsmith-trace-analyzer .github/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .github/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install soba-labs/langchain-agent-skills langsmith-trace-analyzer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/langsmith-trace-analyzer .opencode/skills/langsmith-trace-analyzer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "langsmith-trace-analyzer" agent skill from https://github.com/soba-labs/langchain-agent-skills/tree/main/skills/langsmith-trace-analyzer into .opencode/skills/langsmith-trace-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "langsmith-trace-analyzer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
langsmith-trace-analyzerFetch, organize, and analyze LangSmith traces for debugging and evaluation.
Langsmith Trace Analyzer is an agent skill from soba-labs/langchain-agent-skills. Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Use when you need to: query traces/runs by project, metadata, status, or time window; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns; compare passed vs failed behavior; or investigate benchmark and production failures.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/analysis-patterns.md`, `references/benchmark-analysis.md` and `references/filtering-querying.md`).
It sits in AI & LLM Engineering, covering LLM observability. It works with LangSmith. The repository describes itself as: A collection of agent-optimized LangChain, LangGraph and LangSmith skills for AI coding assistants. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a2d4a10. It shows what the files ask for, not the result of running them.
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.
Ships 3 files in scripts/ (Python and TypeScript), which the agent can run.
Shell commands in SKILL.md call:
uvFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
LANGSMITH_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Langsmith Trace Analyzer loads about 1.4k tokens when it runs, and up to ~9.9k if it reads all its reference files. Until then it costs about 98 tokens; SKILL.md has 365 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from soba-labs/langchain-agent-skills at commit a2d4a10, republished under its MIT licence (© soba-labs). 365 words, ~1,401 tokens.
.claude/skills/langsmith-trace-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.Use this skill to move from raw LangSmith traces to actionable debugging/evaluation insights.
# Install dependencies
uv pip install langsmith langsmith-fetch
# Auth
export LANGSMITH_API_KEY=<your_langsmith_api_key>scripts/download_traces.py (or scripts/download_traces.ts).scripts/analyze_traces.py.references/filtering-querying.md for query/filter syntaxreferences/analysis-patterns.md for deeper diagnosticsreferences/benchmark-analysis.md for benchmark-specific workflowsKnown trace IDs
Use langsmith-fetch trace <id> directly, or --trace-ids in downloader scripts.
Need to discover traces first
Use LangSmith SDK list_runs/listRuns with filters, then download selected trace IDs.
Need aggregate insights
Run analyze_traces.py for summary stats, patterns, and passed-vs-failed comparisons.
Python:
uv run skills/langsmith-trace-analyzer/scripts/download_traces.py \
--project "my-project" \
--filter "job_id=abc123" \
--last-hours 24 \
--limit 100 \
--output ./traces \
--organizeTypeScript:
ts-node skills/langsmith-trace-analyzer/scripts/download_traces.ts \
--project "my-project" \
--filter "job_id=abc123" \
--last-hours 24 \
--limit 100 \
--output ./tracesOutput layout:
traces/
├── manifest.json
└── by-outcome/
├── passed/
├── failed/
└── error/
├── GraphRecursionError/
├── TimeoutError/
└── DaytonaError/Notes:
--organize/--no-organize.langsmith-fetch for full trace payload export.# Markdown report
uv run skills/langsmith-trace-analyzer/scripts/analyze_traces.py ./traces --output report.md
# JSON output
uv run skills/langsmith-trace-analyzer/scripts/analyze_traces.py ./traces --json
# Compare passed vs failed (expects by-outcome folders)
uv run skills/langsmith-trace-analyzer/scripts/analyze_traces.py ./traces --compare --output comparison.mdThe analyzer reports:
Use official LangSmith run filter syntax via filter and/or start_time:
from datetime import datetime, timedelta, timezone
from langsmith import Client
client = Client()
start = datetime.now(timezone.utc) - timedelta(hours=24)
filter_query = 'and(eq(metadata_key, "job_id"), eq(metadata_value, "abc123"))'
runs = client.list_runs(
project_name="my-project",
is_root=True,
start_time=start,
filter=filter_query,
)For TypeScript:
import { Client } from "langsmith";
const client = new Client();
for await (const run of client.listRuns({
projectName: "my-project",
isRoot: true,
filter: 'and(eq(metadata_key, "job_id"), eq(metadata_value, "abc123"))',
})) {
console.log(run.id, run.status);
}status, error, total_tokens, start_time, end_time).metadata or extra.metadata) and/or messages.analyze_traces.py is resilient to multiple payload shapes, including raw array payloads.list_runs results.| Issue | Likely Cause | Action |
|---|---|---|
LANGSMITH_API_KEY missing | Auth not configured | export LANGSMITH_API_KEY=<your_langsmith_api_key> |
| No runs returned | Wrong project/filter/time range | Verify project name and filter syntax |
| Empty/partial message arrays | Run schema differs or incomplete data | Use downloaded trace JSON and inspect status/error fields |
| JSON parse error on downloaded files | Bad/incomplete export | Re-download trace; use --format raw paths in scripts |
| Re-downloading same traces repeatedly | Existing files in nested folders | Use current scripts (they check existing files across output tree) |
manifest.json, trace JSON dumps) unless sanitized.scripts/download_traces.py: Python downloader + organizerscripts/download_traces.ts: TypeScript downloader + organizerscripts/analyze_traces.py: Offline analysis and reportingreferences/filtering-querying.md: LangSmith query/filter examplesreferences/analysis-patterns.md: Diagnostic patterns and heuristicsreferences/benchmark-analysis.md: Benchmark-oriented analysis© soba-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts, references) in skills/langsmith-trace-analyzer of soba-labs/langchain-agent-skills.
Open the folder on GitHubat commit a2d4a10
Langsmith Trace Analyzer 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Langsmith Trace Analyzer this skillsoba-labs/langchain-agent-skills | 107 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Langsmith Online Eval Engineeringlangchain-ai/langsmith-skills | 159 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Langsmith ObservabilityOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.4k | Automated safety check: Pass | MIT | |
| LangSmith Trace DebuggingComposioHQ/awesome-claude-skills | 77k | 9 repos | ~2.7k | Automated safety check: Pass | None | |
| Migrate To Langfuselangfuse/skills | 299 | — | ~1.7k | Automated safety check: Notes | MIT | |
| Langchain Dependencieslangchain-ai/langchain-skills | 1.3k | 1 repos | ~3.6k | Automated safety check: Pass | MIT |
langchain-ai/langsmith-skills
Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads.
Orchestra-Research/AI-Research-SKILLs
LLM observability platform for tracing, evaluation, and monitoring.
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.
langfuse/skills
Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...).
langchain-ai/langchain-skills
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/langsmith-skills
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.
soba-labs/langchain-agent-skills
Use the writetodos tool effectively for task planning and decomposition in Deep Agents.
soba-labs/langchain-agent-skills
Initialize, validate, and troubleshoot Deep Agents projects in Python or JavaScript using the deepagents package.
soba-labs/langchain-agent-skills
Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications.
soba-labs/langchain-agent-skills
Implement LangGraph error handling with current v1 patterns.
soba-labs/langchain-agent-skills
Initialize and configure LangGraph projects with proper structure, langgraph.json configuration, environment variables, and dependency management.
soba-labs/langchain-agent-skills
Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications.
Works with
Categories
Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Langsmith Trace Analyzer is an agent skill from soba-labs/langchain-agent-skills. Fetch, organize, and analyze LangSmith traces for debugging and evaluation.
Langsmith Trace Analyzer fits situations like: you need to: query traces/runs by project; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns.
Run `npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a claude-code`. Or copy the skill folder (skills/langsmith-trace-analyzer in soba-labs/langchain-agent-skills) into .claude/skills/langsmith-trace-analyzer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -a codex`. Or copy the skill folder (skills/langsmith-trace-analyzer in soba-labs/langchain-agent-skills) into .agents/skills/langsmith-trace-analyzer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add soba-labs/langchain-agent-skills --skill langsmith-trace-analyzer -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-trace-analyzer, .gemini/skills/langsmith-trace-analyzer, .github/skills/langsmith-trace-analyzer and .opencode/skills/langsmith-trace-analyzer in your project.
Going by SKILL.md and its folder, Langsmith Trace Analyzer needs Python and TypeScript for the scripts in its folder, the command-line tools its instructions call (uv) and credentials named LANGSMITH_API_KEY. Our summary lists: Python 3; Node.js; A credential in LANGSMITH_API_KEY.
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Langsmith Trace Analyzer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Langsmith Trace Analyzer: Langsmith Online Eval Engineering (langchain-ai/langsmith-skills, 159 stars), Langsmith Observability (Orchestra-Research/AI-Research-SKILLs, 13k stars), LangSmith Trace Debugging (ComposioHQ/awesome-claude-skills, 77k stars) and Migrate To Langfuse (langfuse/skills, 299 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
soba-labs (a GitHub organization) maintains it in soba-labs/langchain-agent-skills, which has 107 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 17, 2026.
Source: soba-labs/langchain-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.