Opik Skills

Official Opik skill pack for coding agents. Install it with one command to give your agent
practical guidance for tracing, evaluating, configuring, and debugging LLM applications with Opik.

This repository is generated. The skills are authored in comet-ml/opik-mcp under src/opik_mcp/skills/ and published here automatically. Edits made here are overwritten by the next sync — please open your pull request against opik-mcp instead.

Opik is the open-source LLM observability and evaluation platform, built by Comet. These agent skills teach coding agents to instrument applications with Opik.

Install

npx skills add comet-ml/opik-skills -g --all

This works across ~40 coding agents, including Claude Code, Cursor, Codex, and GitHub Copilot.

Using the Opik MCP server as well? One command installs this skill pack together with the server for Claude Code, Cursor, VS Code Copilot, Codex and opencode, and needs no Opik SDK:

uvx opik mcp configure

Skills in this pack

Skill	What it does
opik	Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST). Use for "what span types exist", "how do I flush", "track_openai", "add OpikTracer", "version a prompt". To instrument a repo end to end, use the opik-instrument skill.
opik-diagnose	Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agent_insights_issue entities, then fills the gaps with list (filters, sort, a time window); without the MCP it reads the same via the SDK (agent_insights and search_traces), so it works with no MCP. Returns a ranked shortlist, each item ready to hand to the explain skill. Use for "what is broken in production", "which traces need attention", "find failing or slow traces", "which tool calls are failing", "triage my agent". Not for offline experiment results (use evaluate or compare) and not for root-causing one trace (use explain).
opik-evaluate	Build an LLM evaluation and run it against your app, returning an experiment with scores. Covers datasets, LLM judges, RAG evaluation, synthetic data, error analysis, and validating evaluators against human labels. Use when the user wants to measure or improve AI product quality, or asks about evals, judges, or evaluation metrics.
opik-explain	Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace fail", "explain this trace", "debug this trace", "why is my agent slow or wrong". Not for adding tracing to an app (use the instrument skill) or for changing code.
opik-instrument	Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability", "trace my agent". Not for building a new app from scratch, or a review-only pass with no code changes.

One-time Opik setup

Before using them, authenticate Opik once in the environment where your agent will work:

• Python: run opik configure
• TypeScript: run npx opik-ts configure

Those commands save your Opik configuration locally, including the API key and connection details the agent will use while wiring up instrumentation.

For setup details, see the Opik documentation.

Example prompts

Once installed, you can ask your agent things like:

• "Add Opik tracing to this FastAPI app."
• "Instrument this TypeScript OpenAI app with Opik."
• "Help me connect this local agent to Opik with opik connect."
• "Create a Test Suite for this chatbot."
• "Add thread_id support so Opik groups each conversation correctly."

Repository structure

opik-skills/
├── skills/
│   ├── opik/
│   ├── opik-diagnose/
│   ├── opik-evaluate/
│   ├── opik-explain/
│   └── opik-instrument/
├── README.md
├── index.json
└── LICENSE

Opik for Claude Code

This repo is part of a set of tools for observing Claude Code and other coding agents with Opik:

• opik-claude-code-plugin: log Claude Code sessions as Opik traces, with skills and agents included
• ccsync: export Claude Code conversation history to Opik
• cost-intelligence-proxy: meter Claude Code token spend and cost per call
• opik-skills: agent skills for instrumenting your code with Opik (this repo)

Learn more

• Opik repository
• Opik documentation

License

Apache-2.0