CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gemini-api-agent-platform

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cli-tool/components/skills/ai-research/gemini-api-agent-platform/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

The body is a strong, highly actionable SDK reference: executable code in all supported languages, clear auth/configuration guidance, and exemplary progressive disclosure with nine verified one-level-deep reference files. The main improvement opportunities are removing the duplicated legacy-SDK warning and tightening the multi-language quick-start section.

DimensionReasoningScore

Conciseness

The body is efficient and directive — install commands, env vars, and quick-start code with minimal explanatory prose — but has minor trimmable redundancy: the legacy-SDK warning appears twice (Core Directives and the WARNING block) and five full quick-start samples could be tightened. Time-sensitive model versions are properly quarantined in explicit legacy/deprecated guidance rather than scattered.

4 / 5

Actionability

Fully executable guidance throughout: copy-paste-ready install commands for all five languages, concrete env-var exports, client initialization snippets, and working quick-start code in every SDK. The single placeholder (${LAST_VERSION}) is explicitly justified with a live version-listing URL, and common cases are covered.

5 / 5

Workflow Clarity

A clear logical sequence is present (authenticate via env vars → initialize client → select model → generate content → follow reference files for advanced cases), and the guidance on defaulting to location='global' vs. explicit regions is unambiguous. However, there are no explicit validation checkpoints or error-recovery loops, which the top anchor requires.

4 / 5

Progressive Disclosure

SKILL.md is a well-organized overview: all nine referenced files exist in references/ and are exactly one level deep, each clearly signaled with a descriptive label ('Text & Multimodal', 'Embeddings', 'Structured Output & Tools', etc.) and a markdown link. Content is appropriately split between inline quick-starts and detailed per-topic references, making navigation easy.

5 / 5

Total

18

/

20

Passed

Description

66%Weight 40%Scale 1-5

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 clearly communicates what the skill covers with a good list of concrete capability areas and SDK language support, but it entirely lacks 'when to use' trigger guidance. Adding an explicit 'Use when...' clause with natural trigger phrases (including the 'Vertex AI' legacy name) would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building against the Gemini API / Agent Platform (formerly Vertex AI), or when the user mentions Gemini models, Gen AI SDK, Vertex AI, or google-genai.'

Include common synonyms and legacy names users would naturally say ('Vertex AI', 'Gemini Pro', 'Gemini Flash') to improve trigger term coverage.

Lead with concrete action verbs (e.g. 'Generate text, call tools, stream live voice/video, cache contexts, and run batch predictions') instead of the generic 'Guides the usage of' framing.

DimensionReasoningScore

Specificity

Names the domain and lists several specific capability areas ('Live API, tools, multimedia generation, caching, and batch prediction') plus SDK languages (Python, JS/TS, Go, Java, C#), but phrases them as capability categories rather than the fully concrete action verbs of the top anchor.

4 / 5

Completeness

The 'what' is clear (guides Gemini API usage on Agent Platform with the Gen AI SDK, covering the listed capabilities), but there is no 'Use when...' clause or equivalent explicit trigger guidance for when to invoke the skill, which caps this dimension at 3.

3 / 5

Trigger Term Quality

Good natural keywords such as 'Gemini API', 'Gen AI SDK', 'caching', and 'batch prediction', but common synonyms users would actually say are missing — notably 'Vertex AI' (the legacy name the body acknowledges many resources use) and model names like 'Gemini Pro' or 'Gemini Flash'.

4 / 5

Distinctiveness Conflict Risk

The specific platform and SDK names ('Gemini API on Agent Platform with the Google Gen AI SDK') carve out a fairly distinct niche with minor overlap risk against generic Google Cloud or other Gemini-related skills; not the minimal-conflict clarity of the top anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

davila7/claude-code-templates

Path

cli-tool/components/skills/ai-research/gemini-api-agent-platform/SKILL.md

Reviewed

Table of Contents

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.