opik-optimize SKILL.md skillA

opik-optimize from comet-ml/opik-claude-code-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add comet-ml/opik-claude-code-plugin/opik-optimize@git:20260921.9843278

Pins git:20260921.9843278 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
comet-ml/opik-claude-code-plugin
Path
skills/opik-optimize/SKILL.md
Versions recorded
2
Latest version
git:20260921.9843278, committed Sep 21, 2026
First version recorded
Sep 17, 2026
Size
12,730 bytes
Repository stars
25
License
Apache-2.0

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 a new prompt version with the optimization run link. Runs via the opik-optimizer package; reads prompts and datasets via the MCP when connected. Use for "optimize this prompt", "improve my system prompt", "make the agent answer better", "tune the prompt against my dataset", "run the prompt optimizer".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Optimize — Improve a Prompt Against Data

**Definition of done:** an **optimized prompt** whose score on the metric **beats the baseline on data it was not tuned on**, the **optimization run link** in Opik, the cost of getting there, and the winner **saved as a new prompt version** (when the prompt lives in the library) — with the swap into code left as the next step. If the optimization can't run within a stated budget, stop at the **first** genuine blocker and return **exactly one** next step. A prompt that scores higher only on its own training items is not an improvement.

Operate: **measure the baseline first, state the budget before spending it, hold data out, pick the algorithm for the failure you see, save the winner where it can be versioned — and change no application code.** The only file this skill writes is a runner outside the repo; the prompt is saved to Opik, not into the codebase.

## Inputs

The entry point is `/opik-optimize <prompt-name>` (a prompt-library prompt), `/opik-optimize <path or function>` (a prompt in code), or `/opik-optimize` (find the system prompt in this repo). Infer the rest; treat these as **optional overrides**:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add comet-ml/opik-claude-code-plugin/opik-optimize@sha256:008305d6028fabfe

The line at the top of this page pins the label git:20260921.9843278, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ycol4t4zhnxpzzry.svg)](https://markdownregistry.com/a/art_ycol4t4zhnxpzzry)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 17, 2026 and Sep 21, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260921.9843278 latest2026-09-21 9843278 12,730 BA view · diff
git:20260917.109a5512026-09-17 109a551 12,446 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12730 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

comet-ml/opik-claude-code-plugin · 25 stars · license Apache-2.0 · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ycol4t4zhnxpzzry
GET https://markdownregistry.com/api/v1/resolve?ref=comet-ml/opik-claude-code-plugin/opik-optimize
GET https://markdownregistry.com/api/v1/blob/008305d6028fabfed3a689c56322b5599f22cf5d9cead37a290184b208fb6d8e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from comet-ml/opik-claude-code-plugin

opik-compare SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-compare/SKILL.md · Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got…
git:20260921.9843278 · audit A · 25 stars
opik-diagnose SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-diagnose/SKILL.md · Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed…
git:20260917.109a551 · audit A · 25 stars
opik-evaluate SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-evaluate/SKILL.md · Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test…
git:20260921.9843278 · audit A · 25 stars
opik-explain SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-explain/SKILL.md · Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik…
git:20260917.109a551 · audit A · 25 stars
opik-instrument SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-instrument/SKILL.md · Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and…
git:20260917.109a551 · audit A · 25 stars
opik-online-eval SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-online-eval/SKILL.md · Take a judge live on production traffic — create an Opik online evaluation rule (LLM-as-judge or Python metric) on a…
git:20260917.109a551 · audit A · 25 stars
opik-test SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-test/SKILL.md · Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the…
git:20260917.109a551 · audit A · 25 stars
opik-verify SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik-verify/SKILL.md · Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions…
git:20260921.9843278 · audit A · 25 stars
opik SKILL.md skill
comet-ml/opik-claude-code-plugin · skills/opik/SKILL.md · Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python…
git:20260921.9843278 · audit A · 25 stars

Every file in comet-ml/opik-claude-code-plugin

Browse by kind, by grade A, or by owner.