CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-api-integration

Use when integrating Google Gemini API into projects. Covers model selection, multimodal inputs, streaming, function calling, and production best practices.

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/gemini-api-integration/SKILL.md

The canonical home for this skill is gemini-api-integration in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 code examples covering the major Gemini API use cases, making it practically useful. However, it suffers from being a monolithic document with no progressive disclosure, includes unnecessary framing sections that Claude doesn't need, and lacks validation checkpoints in its workflows. The function calling and error handling examples are incomplete, which reduces their copy-paste readiness.

Suggestions

Split detailed code examples (multimodal, function calling, streaming) and the model selection guide into separate reference files, keeping SKILL.md as a concise overview with links.

Complete the function calling example by showing the full round-trip: execute function → send result back to model → get final response.

Add validation checkpoints: verify API key works with a test call before proceeding, check response safety ratings before using output, and show a complete retry loop for error handling.

Remove the 'Overview' and 'When to Use This Skill' sections — Claude can infer applicability from the content itself.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary framing ('This skill guides AI agents through...', 'When to Use This Skill' section) and provides both Node.js and Python examples for basic setup which adds bulk. The model selection table and best practices are useful but the 'Overview' and 'When to Use' sections explain things Claude already knows. The content could be tightened by ~30%.

3 / 5

Actionability

Provides executable, copy-paste ready code examples for all major use cases (text generation, streaming, multimodal, function calling, chat, error handling). Minor gaps: the function calling example is incomplete (the 'send result back to model' part is left as a comment), and the error handling snippet references an undefined `retryCount` variable without showing the full retry loop.

4 / 5

Workflow Clarity

Steps are numbered and sequenced logically from setup through advanced features. However, there are no validation checkpoints — no steps to verify the API key works, no verification that responses are valid before proceeding, and the function calling workflow lacks a complete feedback loop (execute function → send result back → get final response). For an API integration skill involving potentially costly operations, explicit validation steps would improve reliability.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no references to supporting files. The model selection guide, troubleshooting section, and detailed code examples for each language could be split into separate reference files. With no bundle files provided and no external references, the skill dumps everything into one ~150-line document with no navigation structure beyond section headers.

2 / 5

Total

12

/

20

Passed

Description

83%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 is a well-structured description that clearly states both what the skill covers and when to use it. The 'Use when' clause at the beginning provides an explicit trigger, and the listed capabilities are specific enough to guide selection. Minor improvements could include additional trigger term synonyms and more concrete action verbs.

DimensionReasoningScore

Specificity

Lists several specific capabilities: model selection, multimodal inputs, streaming, function calling, and production best practices. These are concrete actions/topics, though some like 'production best practices' are somewhat vague.

4 / 5

Completeness

Explicitly answers both 'what' (covers model selection, multimodal inputs, streaming, function calling, production best practices) and 'when' ('Use when integrating Google Gemini API into projects') with a clear trigger phrase at the start.

5 / 5

Trigger Term Quality

Includes strong trigger terms like 'Google Gemini API', 'multimodal', 'streaming', 'function calling' that users would naturally use. Missing some variations like 'Gemini Pro', 'Gemini Flash', 'vertex AI', 'generative AI', or specific SDK names.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to Google Gemini API specifically, which distinguishes it from other API integration skills. Minor overlap risk with general LLM API skills or Google Cloud skills, but 'Gemini' is a strong distinguishing term.

4 / 5

Total

17

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.