trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens
npx skills add majiayu000/claude-skill-registry --skill skills-finimo-solutions-research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# TruLens Evaluation Workflow A systematic approach to evaluating your LLM application. ## When to Use This Skill Use this skill when you want to: - Set up comprehensive evaluation for a new LLM app - Improve an existing app's evaluation coverage - Understand the full TruLens workflow - Know which sub-skill to use for your current task ## Required Questions to Ask User **Before implementing, always ask the user these questions:** ### 1. App Type (determines instrumentation wrapper) - What framework is your app built with? (LangChain, LangGraph/Deep Agents, LlamaIndex, Custom) ### 2. Evaluation Metrics (determines feedback functions) Ask: **"Which evaluation metrics would you like to use?"** | App Type | Recommended Metrics | Description | |----------|--------------------| ------------| | **RAG** | RAG Triad | Context Relevance, Groundedness, Answer Relevance | | **Agent** | Agent GPA | Tool Selection, Tool Calling, Execution Efficiency, etc. | | **Simple** | Answer Relevance | Basic input-to-output relevance check | | **Custom** | Ask user | Let user describe what they want to evaluate | **For Agents, also ask:** - Does your agent do explicit planning? (determines if Plan Quality/A
- When to Use This Skill
- Required Questions to Ask User
- 1. App Type (determines instrumentation wrapper)
- 2. Evaluation Metrics (determines feedback functions)
- 3. Additional Metrics (optional)
- The Evaluation Workflow
- Sub-Skills Reference
- Interactive Workflow Guide
- Where are you in the process?
- What's your immediate goal?
- Quick Start Paths
- Path A: Evaluate a RAG App
- Path B: Evaluate an Agent
- Path C: Regression Testing
What does the trulens-evaluation-workflow skill do?
Systematically evaluate your LLM application with TruLens
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill skills-finimo-solutions-research --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.