gemini-live-api-dev

Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, and all Live API configuration options. SDKs covered - google-genai (Python), @google/genai (JavaScript/TypeScript).

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%Weight 40%Scale 1-3

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

A code-rich, actionable reference for the Live API with strong executable examples in both SDKs and a clear Quick Start sequence. It is somewhat verbose in catalog-style sections and keeps reference/time-sensitive detail inline rather than splitting it into bundle files, leaving room for tighter progressive disclosure.

Suggestions

Move the partner-integrations catalog and 'Supported Languages' list into a separate reference file (or trim to the top recommendation) to recover tokens and tighten conciseness.

Add an explicit validation/checkpoint flow for the core session lifecycle (e.g. verify connection open before sending, confirm interrupted handling, retry on close) to lift workflow clarity above a capability list.

Split audio-format specs and deprecated-model tables into a dedicated reference or 'deprecated' section so the main SKILL.md stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body is largely code-forward and assumes competence (no explaining of WebSockets/VAD), but the partner-integrations catalog, the 'Supported Languages' list, and inline deprecated-model dates add tokens that could be tightened or moved, matching the 'mostly efficient but could be tightened' anchor rather than the lean 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python and JavaScript examples for auth, connect, send text/audio/video, and receive, with concrete MIME types and config objects — matching the 'fully executable code, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Quick Start sequences auth → connect → send → receive and Best Practices gives a checklist, but the body reads more as a capability catalog than a sequenced workflow, and explicit validation checkpoints / error-recovery feedback loops are only implicit (e.g. the JS onerror callback), fitting the 'steps present but checkpoints missing or implicit' anchor.	2 / 3
Progressive Disclosure	Sections are well organized and the 'How to use the Gemini API' block clearly signals one-level-deep external doc pointers (llms.txt index + page links), but no local bundle files exist and reference-like content (audio format specs, model deprecation dates, language list) lives inline, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

A strong, third-person description that names concrete capabilities, includes an explicit 'Use this skill when' trigger, and occupies a clear niche unlikely to collide with other skills. It is comprehensive without being padded.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — 'WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both: what it covers ('Covers WebSocket-based ... all Live API configuration options. SDKs covered - ...') and when to use it ('Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API'), satisfying the what-and-when anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	Developer-facing natural terms are well covered — 'Gemini Live API', 'real-time, bidirectional streaming', 'audio/video/text streaming' — the phrasings a user would actually say when reaching for this skill; not merely generic jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to the Gemini Live API niche with distinct triggers (real-time bidirectional streaming, Live API), making conflict with other skills unlikely; it is not a generic 'helps with code' style description.	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
Path: gemini-live-api-dev/SKILL.md
Commit: e0f258b

Reviewed: 2 months 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.