openapi-openai

Update the openai_dart package from OpenAI OpenAPI spec changes through fetch, review, scaffold, and verify steps.

Updated May 23, 2026
One-click install
npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill openapi-openai-kiranimmadi2
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openapi-openai
Source: https://github.com/kiranimmadi2/promptforge-ai/tree/main/ai_clients_dart/packages/openai_dart/.agents/skills/openapi-openai
Command: npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill openapi-openai-kiranimmadi2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Keeping a Dart client library in sync with the evolving OpenAI API spec is manual and error-prone. This Skill automates fetching the latest OpenAI OpenAPI spec, reviewing changes, scaffolding new models, and verifying the openai_dart package against the spec. ## Core Features & Use Cases - Spec Fetch & Review: Downloads the latest OpenAI OpenAPI spec and audits changes against the reference Python SDK implementation. - Scaffolding & Verification: Generates Dart model scaffolds from spec schemas and runs verification checks for coverage, exports, and drift patterns. - OpenAI-Specific Guidance: Enforces patterns like base64 data URL formatting for binary fields and nullable fields for multi-model response shapes. - Use Case: When OpenAI ships new API fields, run the fetch and review workflow to detect changes, scaffold the new schemas into lib/src/models, then verify with dart analyze, format, and unit tests. ## Quick Start Use the openapi-openai skill to fetch the latest OpenAI spec, review the changes, and verify the openai_dart package.

Frequently Asked Questions about openapi-openai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I update a Dart client from OpenAI OpenAPI spec changes?▼

Run the api_toolkit.py fetch command with the skill's config directory to download the latest spec, then run review to audit changes. Scaffold new schemas, promote the candidate spec into packages/openai_dart/specs, and finish with the verify command.

How do I verify Dart models match an OpenAPI spec?▼

Run api_toolkit.py verify with --checks all --scope all against the skill config. It validates type mappings, expected properties, and coverage defined in config/manifest.json, then run dart analyze, dart format, and unit tests.

Why does the OpenAI API reject raw base64 file data?▼

OpenAI binary fields require data URL format (data:<mediaType>;base64,<data>), not raw base64, despite misleading spec descriptions. Convenience factories must build the data URL, and integration tests should confirm the behavior.

Does this workflow require API keys or authentication?▼

No authentication environment variables are required. The spec is fetched from a public URL, and the toolkit commands run locally with python3 from the repository root.

How are nullable fields handled for multiple OpenAI model families?▼

Fields returned only by newer model families, such as omni-moderation versus text-moderation, must be nullable in Dart so responses from older models parse without throwing. Check spec examples and the Python SDK to determine true requirement levels.