Agent skill · AI & Agents

langsmith-testing-skill

CRITICAL for RAG: Every RAG query MUST be traced in LangSmith for observability. Silent failures (bad retrieval, hallucinations) are only detectable through tracing.'

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill langsmith-testing-skill --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 11 KB
Bundled scripts: none
Path: skills/ai-llm/langsmith-testing-skill/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: langsmith-testing version: 1.0 last_updated: 2025-12-04 description: LangSmith trace validation for RAG observability - every query must be traced license: MIT priority: critical triggers: - "LangSmith", "trace", "evaluation", "tracking", "observability" - RAG query execution - Evaluation tasks dependencies: - rag-accuracy-SKILL.md compatibility: - langchain: ">=0.1.0" - langsmith: ">=0.1.0" changelog: - version: 1.0 date: 2025-12-04 changes: - Initial release for RAG demo - LangSmith API integration - Trace collection and validation --- # 📊 LangSmith Testing SKILL ## Purpose **CRITICAL for RAG:** Every RAG query MUST be traced in LangSmith for observability. Silent failures (bad retrieval, hallucinations) are only detectable through tracing. --- ## Auto-Trigger Conditions **Activate when:** - User mentions: "LangSmith", "trace", "evaluation", "tracking" - RAG query execution - Evaluation tasks - Performance debugging --- ## LangSmith Setup ### 1. Installation ```bash # Python pip install langsmith langchain # Environment variables export LANGSMITH_API_KEY="your-api-key" export LANGCHAIN_TRACING_V2=true export LANGCHAIN_PROJECT="rag-demo" ``` ### 2. Basic Integration ```

What's inside
Steps it walks through
  1. Purpose
  2. Auto-Trigger Conditions
  3. LangSmith Setup
  4. 1. Installation
  5. 2. Basic Integration
  6. Trace Collection
  7. 1. Automatic Tracing (Recommended)
  8. 2. Manual Tracing
  9. 3. Trace Metadata
  10. Metrics Collection
  11. 1. Core RAG Metrics
  12. 2. Custom Metrics (Faithfulness, Relevance)
  13. Trace Validation
  14. 1. Query Trace
Ships with 1 file
  • metadata.json
Commands it runs
Python
pip install langsmith langchain
Environment variables
export LANGSMITH_API_KEY="your-api-key"
export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_PROJECT="rag-demo"
More from claude-skill-registry
All skills →
About this skill
What does the langsmith-testing-skill skill do?

CRITICAL for RAG: Every RAG query MUST be traced in LangSmith for observability. Silent failures (bad retrieval, hallucinations) are only detectable through tracing.'

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill langsmith-testing-skill --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going