Agent skill

Opik Python SDK Patterns

Developer notes for working inside the Opik Python SDK: layered design, async versus blocking calls, integration styles, batching and dependency rules.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Opik Python SDK Patterns

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/python-sdk .claude/skills/python-sdk && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .claude/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/python-sdk .agents/skills/python-sdk && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .agents/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/python-sdk .cursor/skills/python-sdk && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .cursor/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/comet-ml/opik.git --path .agents/skills/python-sdk

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/python-sdk .gemini/skills/python-sdk && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .gemini/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/python-sdk .github/skills/python-sdk && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .github/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add comet-ml/opik --skill python-sdk -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install comet-ml/opik python-sdk --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/comet-ml/opik.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/python-sdk .opencode/skills/python-sdk && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "python-sdk" agent skill from https://github.com/comet-ml/opik/tree/main/.agents/skills/python-sdk into .opencode/skills/python-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "python-sdk", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: python-sdk
GitHub stars: 22k
Token cost: ~684 tokens
SKILL.md length: 103 words
Files: 5
Skills in repo: 19
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Developer notes for working inside the Opik Python SDK: layered design, async versus blocking calls, integration styles, batching and dependency rules.

Adding a new integration to the Opik Python SDK
SKILL.md covers Three-Layer Architecture, Critical Gotchas, Integration Patterns and Dependency Policy, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Deciding whether an SDK call should be queued or blocking

What it does

The skill summarizes how the SDK in `sdks/python` is put together. It is built in layers, starting with the public API (`opik.Opik` and `@opik.track`) and a message-processing layer for queueing, batching and retry. Gotchas include flushing before exit so queued data is sent, and knowing which calls are fire-and-forget through the message queue (traces, spans, feedback scores, experiment inserts) and which block and return data (datasets, prompts, searching traces and spans).

For integrations, it picks a style by library: pure callbacks for LangChain and LlamaIndex, method patching for OpenAI and Anthropic, and a hybrid for ADK where callbacks are unreliable. Integration modules import their dependency lazily. Rules cover adding no new dependencies, keeping flexible version bounds, create, get, list, update and delete method names, and batch flushing on time, size, memory or manual triggers. Reference files cover testing, error handling and good code, and a refactor-helper agent file is included.

When your agent uses it

Adding a new integration to the Opik Python SDK
Deciding whether an SDK call should be queued or blocking
Reviewing SDK changes against the project's dependency and naming rules

Example prompts

“Add an Opik integration for a library that has no callbacks, using method patching.”
“Why do traces go missing when my script exits, and where does the SDK flush?”
“Name the new SDK method for deleting a dataset in line with the existing CRUD conventions.”

Requirements

A checkout of the Opik repository with `sdks/python`

What it can do on your machine

Read from SKILL.md and the folder at commit f217a86. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 Python SDK Patterns loads about 684 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 103 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~31
When it runs · the whole SKILL.md, loaded when a task matches: ~684

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 comet-ml/opik at commit f217a86, republished under its Apache-2.0 licence (© comet-ml). 103 words, ~684 tokens.

Download SKILL.mdSave it as .claude/skills/python-sdk/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: python-sdk
description: Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.

Python SDK

Three-Layer Architecture

Layer 1: Public API      (opik.Opik, @opik.track)
    ↓
Layer 2: Message Processing   (queue, batching, retry)
    ↓
Layer 3: REST Client     (OpikApi, HTTP)

Critical Gotchas

Flush Before Exit

python

# ✅ REQUIRED for async operations
client = opik.Opik()
# ... tracing operations ...
client.flush()  # Must call before exit!

Async vs Sync Operations

Async (via message queue) - fire-and-forget:

trace(), span()
log_traces_feedback_scores()
experiment.insert()

Sync (blocking, returns data):

create_dataset(), get_dataset()
create_prompt(), get_prompt()
search_traces(), search_spans()

Lazy Imports for Integrations

python

# ✅ GOOD - integration files assume dependency exists
import anthropic  # Only imported when user uses integration

# ❌ BAD - importing at package level
from opik.integrations import anthropic  # Would fail if not installed

Integration Patterns

Pattern Selection

Library has callbacks? → Pure Callback (LangChain, LlamaIndex)
No callbacks?         → Method Patching (OpenAI, Anthropic)
Callbacks unreliable? → Hybrid (ADK)

Method Patching (OpenAI, Anthropic)

python

from opik.integrations.anthropic import track_anthropic

client = anthropic.Anthropic()
tracked_client = track_anthropic(client)  # Wraps methods

Callback-Based (LangChain)

python

from opik.integrations.langchain import OpikTracer

tracer = OpikTracer()
chain.invoke(input, config={"callbacks": [tracer]})

Decorator-Based

python

@opik.track
def my_function(input: str) -> str:
    # Auto-creates span, captures input/output
    return process(input)

Dependency Policy

Avoid adding new dependencies
Use conditional imports for integrations
Keep version bounds flexible: >=2.0.0,<3.0.0

Batching System

Messages batch together for efficiency:

Flush triggers: time (1s), size (100), memory (50MB), manual
Reduces HTTP overhead significantly

API Method Naming

python

# CRUD: create/get/list/update/delete
client.create_experiment(name="exp")
client.get_dataset(name="ds")

# Search for complex queries
client.search_spans(project_name="proj")
client.search_traces(project_name="proj")

# Batch for bulk operations
client.batch_create_items(...)

Reference Files

testing.md - fake_backend, verifiers, test naming
error-handling.md - Exception hierarchy, MetricComputationError
good-code.md - Access control, imports, factories, DI

Files

SKILL.md and 4 other files in .agents/skills/python-sdk of comet-ml/opik.

SKILL.md
agents/refactor-helper.md
error-handling.md
good-code.md
testing.md

Open the folder on GitHubat commit f217a86

Compare with similar skills

Opik Python SDK Patterns next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Opik Python SDK Patterns compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Opik Python SDK Patterns this skillcomet-ml/opik	22k	—	~684	Automated safety check: Pass	Apache-2.0	today
Langfusemajiayu000/claude-skill-registry	666	3 repos	~3.1k	Automated safety check: Pass	MIT	today
Failproof AI SDK IntegrationFailproofAI/failproofai	5.3k	—	~6k	Automated safety check: Pass	Custom licence	yesterday
Upgrade Stripekanchengw/cnllm	175	4 repos	~1.4k	Automated safety check: Pass	Apache-2.0	3 mo ago
Sentence Transformers EmbeddingsOrchestra-Research/AI-Research-SKILLs	13k	3 repos	~1.6k	Automated safety check: Pass	MIT	3 mo ago
Langchain Dependencieslangchain-ai/langchain-skills	1.3k	1 repos	~3.6k	Automated safety check: Pass	MIT	yesterday

Similar skills

Langfuse
majiayu000/claude-skill-registry
Expert in Langfuse - the open-source LLM observability platform.
666 GitHub starsUsed in 3 repos~3.1k tokens
AI & LLM EngineeringAuto-check passed
Failproof AI SDK Integration
FailproofAI/failproofai
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
5.3k GitHub stars~6k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Upgrade Stripe
kanchengw/cnllm
Guide for upgrading Stripe API versions and SDKs. An agent skill from kanchengw/cnllm.
175 GitHub starsUsed in 4 repos~1.4k tokens
AI & LLM EngineeringAuto-check passed
Sentence Transformers Embeddings
Orchestra-Research/AI-Research-SKILLs
Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text.
13k GitHub starsUsed in 3 repos~1.6k tokens
AI & LLM EngineeringAuto-check passed
Langchain Dependencies
langchain-ai/langchain-skills
Official
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents.
1.3k GitHub starsUsed in 1 repo~3.6k tokens
AI & LLM EngineeringAuto-check passed
Phoenix LLM Observability
Orchestra-Research/AI-Research-SKILLs
Sets up Arize Phoenix to trace, evaluate and monitor LLM applications, with instrumentation for OpenAI, LangChain and LlamaIndex and a self-hosted server.
13k GitHub starsUsed in 2 repos~2.9k tokens
AI & LLM EngineeringAuto-check passed

Questions about Opik Python SDK Patterns

What does Opik Python SDK Patterns do?

Developer notes for working inside the Opik Python SDK: layered design, async versus blocking calls, integration styles, batching and dependency rules. The skill summarizes how the SDK in `sdks/python` is put together.track`) and a message-processing layer for queueing, batching and retry.

When should I use Opik Python SDK Patterns?

Opik Python SDK Patterns fits situations like: adding a new integration to the Opik Python SDK; deciding whether an SDK call should be queued or blocking; reviewing SDK changes against the project's dependency and naming rules.

How do I install Opik Python SDK Patterns in Claude Code?

Run `npx skills add comet-ml/opik --skill python-sdk -a claude-code`. Or copy the skill folder (.agents/skills/python-sdk in comet-ml/opik) into .claude/skills/python-sdk in your project. Claude Code loads it when a task matches its description.

How do I install Opik Python SDK Patterns in Codex?

Run `npx skills add comet-ml/opik --skill python-sdk -a codex`. Or copy the skill folder (.agents/skills/python-sdk in comet-ml/opik) into .agents/skills/python-sdk in your project. Codex loads it when a task matches its description.

Can I use Opik Python SDK Patterns in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add comet-ml/opik --skill python-sdk -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/python-sdk, .gemini/skills/python-sdk, .github/skills/python-sdk and .opencode/skills/python-sdk in your project.

What does Opik Python SDK Patterns need to run?

SKILL.md names no scripts, command-line tools or credentials: Opik Python SDK Patterns is instructions for the agent only. Our summary lists: A checkout of the Opik repository with `sdks/python`.

Does Opik Python SDK Patterns access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Opik Python SDK Patterns safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Opik Python SDK Patterns use?

Opik Python SDK Patterns is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Opik Python SDK Patterns use?

About 684 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Opik Python SDK Patterns?

Skills that share tags, products or a category with Opik Python SDK Patterns: Langfuse (majiayu000/claude-skill-registry, 666 stars), Failproof AI SDK Integration (FailproofAI/failproofai, 5.3k stars), Upgrade Stripe (kanchengw/cnllm, 175 stars) and Sentence Transformers Embeddings (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opik Python SDK Patterns?

comet-ml (a GitHub organization) maintains it in comet-ml/opik, which has 22,412 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 7, 2026.

Source: comet-ml/opik on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Opik Python SDK Patterns

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Python SDK

Three-Layer Architecture

Critical Gotchas

Flush Before Exit

Async vs Sync Operations

Lazy Imports for Integrations

Integration Patterns

Pattern Selection

Method Patching (OpenAI, Anthropic)

Callback-Based (LangChain)

Decorator-Based

Dependency Policy

Batching System

API Method Naming

Reference Files

Files

Compare with similar skills

Similar skills

More from comet-ml/opik

Related

Questions about Opik Python SDK Patterns