Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

OpenAI AgentKit Expert Skill · majiayu000 | DecimalAI

agent toolingby majiayu000

OpenAI AgentKit Expert Skill

majiayu000/OpenAI AgentKit Expert

Source majiayu000/claude-skill-registry ↗License MIT

Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration, handoffs, and routines

SkillScore95Maintained

Automatic

AI Engineer pack

Last verified 9/2/2026

What it changes

Passed 21 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill95%

Checks it passed that the model alone missed

Recommends using OpenAI Agents SDK for multi-agent orchestration.
Tracks handoff accuracy or task completion rate as agent-level metrics.
Recommends replacing Swarm runner execution with Agents SDK orchestration patterns.

and 6 more in the full report

7 fixed14 passed either way0 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +87%
Agent turns: 0%
Response time: -21%

Model gemini-3.6-flashMeasured 9/2/2026v221 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-openai-agentkit-expert/SKILL.md https://app.decimal.ai/s/majiayu000-openai-agentkit-expert/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-openai-agentkit-expert, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-openai-agentkit-expert/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-openai-agentkit-expert

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-openai-agentkit-expert/SKILL.md https://app.decimal.ai/s/majiayu000-openai-agentkit-expert/SKILL.md

Raw file: /s/majiayu000-openai-agentkit-expert/SKILL.md ↗ · machine-readable summary at /s/majiayu000-openai-agentkit-expert.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Our enterprise uses both Anthropic models for creative writing and OpenAI models for customer automation. How should we structure our orchestration SDK selection across these model providers?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends AgentKit for OpenAI-native workflows and Claude SDK for Anthropic-native workflows.	Missed	Passed

case-14 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md437 linessingle file

OpenAI AgentKit Expert Skill

Purpose

This skill provides comprehensive guidance on building production-ready multi-agent systems using OpenAI's AgentKit platform and Agents SDK, following 2026 best practices.

Platform Overview

OpenAI AgentKit (2026)

Complete platform for building, deploying, and optimizing agents with enterprise-grade tooling.

Core Components:

Agent Builder - Visual canvas for creating and versioning multi-agent workflows
Connector Registry - Central management for data and tool connections
ChatKit - Embeddable customizable chat-based agent experiences
Evaluation Suite - Datasets, trace grading, automated prompt optimization
Multi-Model Support - Third-party model integration capabilities

Agents SDK (Production-Ready)

The Agents SDK is the production evolution of the experimental Swarm framework. Use Agents SDK for all production work - Swarm is educational only.

Migration Note: If you encounter legacy Swarm code, migrate to Agents SDK immediately.

Core Concepts

1. Agents

An Agent encapsulates:

A set of instructions (system prompt)
A set of functions/tools
The capability to hand off execution to another Agent

Design Principle: Agents should be lightweight and specialized rather than monolithic and general-purpose.

2. Routines

A routine is a sequence of actions an agent can perform:

Natural language instructions (via system prompt)
Available tools needed to execute
Context and state management
Success criteria

Think of it as: A mini-workflow that an agent owns and executes autonomously.

Track record

Benchmark

21 / 22

test cases passed, vs 15 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/openai-agentkit-frankxai-agentic-creator-os/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

OpenAI AgentKit Expert Skill

Purpose

Platform Overview

OpenAI AgentKit (2026)

Agents SDK (Production-Ready)

Core Concepts

1. Agents

2. Routines

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills