gemini-api-dev

Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable code and live reference URLs, and is well structured with one-level-deep external pointers. Its main weakness is token efficiency — four near-identical quick-start blocks and a long doc-page list carry content that assumes less of Claude's competence than warranted.

Suggestions

Collapse the four full quick-start blocks into one canonical example plus a compact per-language SDK install/invocation table, keeping executable snippets but cutting boilerplate repetition.

Replace the enumerated documentation-page list with a short pointer to the llms.txt index plus the 2-3 most-used pages, since the body already instructs fetching the index to discover the rest.

Move the per-language install snippets into a single condensed reference table to avoid restating Maven/Gradle/pip/npm/go-get mechanics Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but four full boilerplate quick-start blocks (Python, JS, Go, Java) and a long enumerated documentation-page list add tokens Claude could largely derive, and the per-language install snippets are padded. It is not a wall of tutorial prose, but it could be tightened.	2 / 3
Actionability	Fully executable copy-paste-ready code in every supported SDK, concrete model names, real install commands, and live URLs for the discovery spec and llms.txt index — Claude can act on this directly.	3 / 3
Workflow Clarity	The doc-discovery workflow is explicit and sequenced ('Fetch llms.txt to discover available documentation pages' then 'Fetch specific pages'), and the API-spec section clearly designates v1beta as the default source of truth; no destructive operation requires validation checkpoints here.	3 / 3
Progressive Disclosure	The body is organized into clear sections (Overview, Models, SDKs, Quick Start, API spec, docs, Live API) and points one level deep to live external doc URLs plus a sibling skill for Live API, with no nested file references and no bundle files present.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, uses natural trigger terms, and explicitly pairs the 'what' with a 'when' clause, all while staying tightly scoped to the Gemini API. It is concise yet comprehensive enough to avoid conflict with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'building applications with Gemini models', 'working with multimodal content (text, images, audio, video)', 'implementing function calling', 'using structured outputs', plus concrete SDK packages for four languages.	3 / 3
Completeness	Explicitly answers 'what' (SDK usage, model selection, API capabilities) and 'when' via the 'Use this skill when building applications with... or needing current model specifications' trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms appear throughout: 'Gemini models', 'Gemini API', 'function calling', 'structured outputs', 'multimodal content' — the phrasing a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to the Gemini API and its SDKs, with a clear niche (model specs, multimodal, function calling) that is unlikely to trigger for non-Gemini skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: JetBrains/skills
Commit: e0f258b

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.