Skip to main content
skill CX Codex

opik · akillness — Claude Code skill for LLM tracing and evaluation

Configure Opik to trace LLM calls, evaluate responses, and monitor runs. Use the skill when you need to assess prompts or compare experiments.

no license 146 installs ★ 61 updated 2026-11-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add akillness/jeo-skills --skill opik -a claude-code
Open on GitHub

What opik does

The opik skill guides setup for Opik: choose Comet.com cloud, a local Docker Compose deployment, or Kubernetes, then configure an SDK and capture traces. Use a supported framework integration or the @opik.track decorator to log activity.

It also covers response scoring with metrics such as Hallucination and Answer Relevance, dataset experiments, and PyTest checks in CI. The SDK requires Python 3.8+. Running ./opik.sh locally requires Docker and Docker Compose, so that deployment path depends on a working container setup.

What it helps with

  • capture traces from LLM calls and agents
  • score generated answers with evaluation metrics
  • compare prompt and model variants on datasets
  • fail CI checks when evaluations regress

Example prompts for the agent

  • Set up Opik tracing for the LLM calls in this project.
  • Add a Hallucination metric to evaluate these responses.
  • Prepare a PyTest evaluation check for CI.

How to install opik

1Skills CLI (Vercel)

npx skills add akillness/jeo-skills --skill opik -a claude-code

2Manually: put the files in place

~/.claude/skills/opik/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/opik/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about opik

How do I install opik in Claude Code?

Run npx skills add akillness/jeo-skills --skill opik -a claude-code. The skill file is placed at ~/.claude/skills/opik/SKILL.md.

What does opik do?

It guides Opik setup for tracing LLM activity, scoring outputs, and monitoring runs. It also covers dataset experiments and PyTest checks in CI.

What do I need to run Opik locally?

Local startup with ./opik.sh requires Docker and Docker Compose. The SDK requires Python 3.8+.

Similar skills

All skills for AI and ML →

opik by other authors comes first.

opik comet-ml Reference for Opik SDK 2.x tracing, span types, framework integrations, and prompt library management. CX Codex +1 562installs opik-explain comet-ml opik-explain — a skill for Claude Code that investigates Opik traces to find root causes and links them to repository code. Resolves execution failures, anomalies, or slow runs from a trace ID or pattern. CX Codex +1 111installs opik-evaluate comet-ml The opik-evaluate Claude Code skill builds and runs evaluations of an app or prompt through Opik. It examines agent and RAG quality, analyzes errors, and returns an experiment with scores and a link. CX Codex +1 122installs logfire-instrumentation pydantic logfire-instrumentation adds Pydantic Logfire observability to Python, TypeScript, or Rust code. Configures traces, structured logs, metrics, and AI agent spans. CX Codex +1 2,600installs Comet Opik official github Comet Opik — a GitHub Copilot subagent that wires Opik in over MCP: versions prompts, manages projects, and digs through LLM traces and metrics. CX Codex +1 ★ 41,430repo stars phoenix-error-analysis arize-ai phoenix-error-analysis — a skill for Claude Code that identifies LLM agent failure modes using open and axial coding on Phoenix traces. Guides error taxonomy creation directly from runtime telemetry. CX Codex +1 126installs nemo-evaluator-sdk Orchestra Research nemo-evaluator-sdk — a skill for Claude Code and five other agent environments. Runs language models through 100+ benchmarks from 18+ harnesses with containerized, multi-backend execution. CX Codex +1 1,100installs

From the same set99

The whole set →
react-bits Steers an agent through react-bits: pick dependencies, drop an animated component into a React project, fix GSAP and Three.js leaks, or send your own component upstream. CX Codex +1 211installs deep-dive deep-dive — a two-stage skill: three parallel lanes trace why something broke, then a requirements interview starts from those findings. Built for bugs and changes in code you don't know yet. CX Codex +1 177installs spec-kit Installs GitHub's specify CLI, bootstraps a spec-driven project for your agent, and runs the /speckit.* pipeline from constitution to implementation. CX Codex +1 167installs academic-research academic-research sorts a research topic or paper draft into one of several linked academic workflows, from literature discovery to peer review. The skill itself decides which branch and mode fit the request. CX Codex +1 148installs heretic The heretic skill runs directional ablation and refusal analysis on open-weight models. Use it to study refusals or reduce benign over-refusal without fine-tuning. CX Codex +1 143installs astryx astryx is a Claude Code skill for building React design systems and component libraries. It activates for work on themes, design tokens, and accessible UI components. CX Codex +1 141installs slides-grab slides-grab turns a topic into a deck of HTML/CSS slides, lets you box a region in the browser and have the agent redo just that part, then exports to PDF or PNG. CX Codex +1 141installs typesense Sets up Typesense search backend, collection schemas, and typo tolerance. Useful for building product search or migrating from Algolia. CX Codex +1 139installs

Project sponsors

Companies that keep this analytics open