gemini-api-dev

The Gemini API provides access to Google's most advanced AI models. Key capabilities include:

Quality

36%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/gemini-api-dev/SKILL.md

Quality

Content

61%Scale 1-5

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

This skill provides solid, actionable quick-start guidance for the Gemini API with executable code examples in three languages, current model information, and clear deprecation warnings. Its main weaknesses are moderate verbosity (overview bullets, lengthy Go example, empty 'When to Use' section) and a lack of validation/error-handling guidance in the workflow. The progressive disclosure strategy of pointing to llms.txt as a documentation index is effective.

Suggestions

Remove the vacuous 'When to Use' section and trim the overview bullet list, as Claude already understands what text generation, embeddings, etc. are.

Add error handling or validation guidance (e.g., checking response status, handling rate limits) to improve workflow clarity.

Consider shortening the Go quick-start example or moving it to a separate reference file to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary verbosity like the overview bullet list restating what the Gemini API is (Claude knows this), the 'When to Use' section is vacuous, and the Go example is quite long. However, the model list, SDK info, and deprecation warnings add genuine value. Mixed efficiency overall.	3 / 5
Actionability	Provides executable quick-start code in three languages, specific model names, exact package install commands, and concrete URLs for fetching documentation. Minor gap: it doesn't show examples for advanced features (function calling, structured output, etc.) inline, instead deferring to external docs, but the quick-start examples are copy-paste ready.	4 / 5
Workflow Clarity	The skill describes a workflow for fetching documentation (fetch llms.txt → find page → fetch specific page) but lacks validation checkpoints. There's no guidance on error handling, verifying API responses, or what to do if fetches fail. For a skill that's primarily a reference/setup guide rather than a multi-step destructive operation, this is adequate but could be clearer.	3 / 5
Progressive Disclosure	Good structure with clear sections and well-signaled external references to documentation pages via llms.txt and specific .md.txt URLs. The approach of pointing to an index file for discovery is smart. Minor gap: no bundle files exist to offload the lengthy Go example or detailed API usage patterns, and the skill could benefit from separating quick-start examples into a referenced file.	4 / 5
	Total	14 / 20 Passed

Description

11%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.

This description is severely incomplete—it appears truncated after 'Key capabilities include:' with no actual capabilities listed. It provides no concrete actions, no trigger guidance, and no 'when to use' clause. It reads as a marketing tagline rather than a functional skill description.

Suggestions

Complete the description by listing specific capabilities (e.g., 'Generate text, analyze images, create embeddings, call function tools via the Gemini API').

Add an explicit 'Use when...' clause with trigger terms like 'Gemini', 'Google AI', 'Gemini API call', 'gemini-pro', etc.

Remove the trailing colon and incomplete sentence structure; ensure the description is self-contained and fully describes what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The description is entirely vague. It mentions 'Google's most advanced AI models' and 'Key capabilities include:' but then lists no actual capabilities. No concrete actions are described.	1 / 5
Completeness	The 'what' is extremely vague ('access to Google's most advanced AI models') with no actual capabilities listed despite promising them. There is no 'when' clause at all. The description appears truncated.	1 / 5
Trigger Term Quality	Contains 'Gemini API' and 'Google' as keywords, which are somewhat relevant, but lacks any natural user phrases like 'generate text', 'call Gemini', 'Google AI', or specific task-related terms users would say.	2 / 5
Distinctiveness Conflict Risk	While 'Gemini API' is a specific product name, the description is so vague ('AI models', 'key capabilities') that it could overlap with any AI-related skill. The lack of concrete actions makes it hard to distinguish from other API or AI skills.	2 / 5
	Total	6 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/gemini-api-dev/SKILL.md
Commit: 57c135b

Reviewed: 4 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.