Opik Optimizer

What it does

When your agent uses it

• Tasks that involve Prompt engineering

Example prompts

• “/opik-optimizer”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Select optimizer strategy (MetaPromptOptimizer, FewShotBayesianOptimizer, HRPO, etc.) based on the target optimization goal.
2. 2Build prompt/dataset/metric wiring and validate placeholder-field alignment.
3. 3Run prompt, tool, or parameter optimization with explicit controls (n_threads, n_samples, max_trials, seed).
4. 4Inspect OptimizationResult and compare score deltas against initial baselines.
5. 5Summarize recommendations, risks, and next experiments.

What it can do on your machine

Read from SKILL.md and the folder at commit b83ca13. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Opik Optimizer loads about 1.7k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~54

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vincentkoc/dotskills at commit b83ca13, republished under its MIT licence (© vincentkoc). 521 words, ~1,684 tokens.

name

opik-optimizer

description

Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.

license

MIT

metadata.source

https://github.com/vincentkoc/dotskills

pip install opik-optimizer

from opik_optimizer import ChatPrompt, MetaPromptOptimizer, HRPO, FewShotBayesianOptimizer
from opik_optimizer import datasets

from opik.evaluation.metrics import LevenshteinRatio

prompt = ChatPrompt(
    system="You are a concise answerer.",
    user="{question}",
)

def metric(dataset_item: dict, output: str) -> float:
    return LevenshteinRatio().score(
        reference=dataset_item["answer"],
        output=output,
    ).value

dataset = datasets.hotpot(count=30)

result = MetaPromptOptimizer(model="openai/gpt-5-nano").optimize_prompt(
    prompt=prompt,
    dataset=dataset,
    metric=metric,
    n_samples=20,
    max_trials=10,
)
result.display()

stateDiagram-v2
    [*] --> SelectObjective
    SelectObjective --> ConfigurePromptOrTools: prompt, agent, or tool objective
    SelectObjective --> ConfigureParameters: parameter objective
    ConfigurePromptOrTools --> ValidateDatasetAndControls
    ConfigureParameters --> ValidateDatasetAndControls
    ValidateDatasetAndControls --> ReportBlocked: fields, metric, or limits invalid
    ValidateDatasetAndControls --> OptimizePrompt: prompt or tool strategy
    ValidateDatasetAndControls --> OptimizeParameter: ParameterOptimizer
    OptimizePrompt --> CompareBaseline
    OptimizeParameter --> CompareBaseline
    OptimizePrompt --> ReportBlocked: run fails
    OptimizeParameter --> ReportBlocked: run fails
    CompareBaseline --> ReportRecommendations
    ReportRecommendations --> [*]
    ReportBlocked --> [*]

© vincentkoc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references, assets) in skills/opik-optimizer of vincentkoc/dotskills.

• SKILL.md
• agents/openai.yaml
• assets/icon.jpg
• references/algorithms.md
• references/datasets_and_setup.md
• references/example_patterns.md
• references/prompt_agent_workflow.md

Open the folder on GitHubat commit b83ca13