Repository
comet-ml/opik-mcp agent skills
- skills
- 10
- GitHub stars
- 220
GitHub description: “Model Context Protocol (MCP) server for Opik, the open-source LLM observability and evaluation platform, built by Comet. Read traces, log scores, and manage prompts from Claude Code, Cursor, or VS Code.”
- Stars
- 220 (37 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Mar 2025
- Homepage
- comet.com/site/products/opik
- mcp-server
- claude-code
- llm-observability
- mcp
- model-context-protocol
- opik
- python
- generative-ai
Install all skills
npx skills add comet-ml/opik-mcpAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in comet-ml/opik-mcp, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Opik Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST). | comet-ml/ | 220 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are… | comet-ml/ | 220 | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | today |
| 3 | 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. | comet-ml/ | 220 | — | ~2.7k | Automated safety check: Notes | Apache-2.0 | today |
| 4 | Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. | comet-ml/ | 220 | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | today |
| 5 | Add Opik tracing to an existing app and verify a real trace lands. | comet-ml/ | 220 | — | ~2.7k | Automated safety check: Notes | Apache-2.0 | today |
| 6 | Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as… | comet-ml/ | 220 | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | today |
| 7 | Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost… | comet-ml/ | 220 | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | today |
| 8 | Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. | comet-ml/ | 220 | — | ~2.4k | Automated safety check: Notes | Apache-2.0 | today |
| 9 | Take a judge live on production traffic — create an Opik online evaluation rule (LLM-as-judge or Python metric) on a project with sampling, filters, variable mapping, and a cost cap, then confirm… | comet-ml/ | 220 | — | ~3k | Automated safety check: Notes | Apache-2.0 | today |
| 10 | 10.Opik Test Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the… | comet-ml/ | 220 | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill in comet-ml/opik-mcp?
Opik from comet-ml/opik-mcp ranks first of the 10 skills in comet-ml/opik-mcp listed here, with the highest score: its repository has 220 GitHub stars, its SKILL.md loads about 2.1k tokens and it passes the automated safety check with no findings. Next come Opik Compare and Opik Diagnose.
Are the skills in comet-ml/opik-mcp official?
None yet. All 10 skills in comet-ml/opik-mcp listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from comet-ml/opik-mcp?
Run npx skills add comet-ml/opik-mcp in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.