skills.rest
kiranimmadi2
kiranimmadi2COMMUNITY
Explore all skills by this author →
WebsiteGitHub

openapi-googleai

Updates the googleai_dart package from Google AI OpenAPI spec changes.

Updated May 23, 2026
Search Tags:#openapi#code generation#gemini api#dart#google ai#spec verification#sdk maintenance
One-click install
npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill openapi-googleai-kiranimmadi2
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openapi-googleai
Source: https://github.com/kiranimmadi2/promptforge-ai/tree/main/ai_clients_dart/packages/googleai_dart/.agents/skills/openapi-googleai
Command: npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill openapi-googleai-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 Google AI (Gemini) OpenAPI specifications requires manually fetching specs, reviewing diffs, scaffolding new models, and verifying coverage. This Skill automates that workflow for the googleai_dart package. ## Core Features & Use Cases - Spec Fetch and Review: Downloads the latest main (Gemini API) and interactions OpenAPI specs and reviews changes against the current implementation using the shared api-toolkit CLI. - Scaffolding and Verification: Scaffolds new Dart model files from spec schemas and verifies implementation coverage, drift patterns, and removed APIs via manifest-driven checks. - Use Case: When Google publishes a new version of the Generative Language API spec, run the fetch, review, scaffold, and verify cycle to update Dart models, then confirm quality with dart analyze, format, and unit tests. ## Quick Start Use the openapi-googleai skill to fetch the latest main spec, review the changes, and verify the googleai_dart package implementation.

Frequently Asked Questions about openapi-googleai

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

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

Fetch the latest spec with the api-toolkit fetch command, review the diff with review, scaffold new types, copy the candidate spec into the package specs directory, then run verify with all checks. Finish with dart analyze, format, and unit tests.

What specs does the googleai_dart OpenAPI workflow support?▼

It supports two specs: main, covering the core Gemini API such as generation, embeddings, files, and models, and interactions, an experimental spec for server-side state, agents, and background execution. Select one with the --spec-name flag.

Does the spec fetch require authentication?▼

The main spec requires a GEMINI_API_KEY or GOOGLE_AI_API_KEY sent as the x-goog-api-key header. The interactions spec is fetched from a public URL and requires no authentication.

Why does verification fail on scaffolded Dart files?▼

Scaffolded files contain a private _UnsetCopyWithSentinel placeholder and missing imports. Replace the sentinel block with an import of the shared copy_with_sentinel.dart and add relative imports for referenced types before verifying.

How are empty spec schemas like ImageSearch handled?▼

Empty-marker schemas are confirmed against the js-genai types.ts reference and kept as kind skip in the manifest rather than mapped as objects, because the verifier fails on object schemas with no properties.

Related Skills

Explore More Software Engineering Skills→
reason-machinesreason-machines
10

n8n-marketing-flows

Import n8n workflow templates for marketing automation across social media, ads, and content generation.

Official
Intermediate
TiendaNubeTiendaNube
29

changelogs

Generate and update CHANGELOG.md entries from branch commits.

Official
Intermediate
nick-ortonnick-orton
4

google-genai-sdk-unified-v157

Standardize Google GenAI SDK v1.57+ imports, client setup, and async generation.

Community
Intermediate
ConsiliencyConsiliency
8

test-scaffolding

Generate language-aware test scaffolds from analyzed source code.

Official
Advanced