Name: firebase-ai-logic-basics
Rating: 57.599999999999994 (1 reviews)
Author: firebase

firebase-ai-logic-basics

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/firebase-ai-logic-basics/SKILL.md

Quality

Content

63%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 skill is well-structured with good progressive disclosure and a clear setup workflow, but its core capability sections lack inline executable code and carry redundant/empty padding. Adding concrete generation examples and trimming repetition would materially improve it.

Suggestions

Add small executable code snippets for the core capabilities (text generation, multimodal input, startChat, generateContentStream, structured output) instead of one-line mentions.

Remove the duplicate 'Use current model names' warning (keep a single instance) and either fill or delete the empty stub headings (Text-Only Generation, Search Grounding).

Tighten the Overview by dropping the generic 'what is Firebase AI Logic' background and the malformed wrapped table; link the platform details directly from the References section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with headings, bullets, and commands, but it carries avoidable padding: the 'Use current model names' warning is repeated near-verbatim, several core-capability headings are empty stubs, and the rebranding explanation adds background Claude largely already knows.	3 / 5
Actionability	Setup and App Check sections give concrete, executable commands and snippets, but the core generation capabilities (text, multimodal, chat, streaming, structured output) mention function names like `generateContentStream` and `startChat` without any executable code, deferring the actual inference examples entirely to references.	3 / 5
Workflow Clarity	The Setup & Initialization flow is clearly sequenced (prerequisites → install → list projects/apps → init ailogic) with implicit checkpoints like confirming an app exists, and the App Check debug-token steps are well numbered; only minor explicit validation gaps keep it below 5.	4 / 5
Progressive Disclosure	The body is a concise overview that defers detailed per-platform code to real one-level-deep reference files (ios_setup.md, flutter_setup.md, usage_patterns_web.md, usage_patterns_android.md), all of which exist and are clearly signaled via the table and References section.	5 / 5
	Total	15 / 20 Passed

Description

70%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 is specific and clearly niched, but it lacks any explicit 'Use when...' trigger guidance, which caps its completeness. Adding a concrete trigger clause would raise the overall quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when integrating Gemini/Firebase AI Logic into web apps, or when the user mentions Firebase AI Logic, Gemini API, multimodal inference, or structured JSON output.'

Include natural synonyms users might say (e.g., 'Gemini', 'AI generation', 'image/vision input') alongside the technical terms.

Clarify that 'web applications' is the focus and note when other platforms (iOS/Android/Flutter) are covered, to reduce ambiguity about scope.

Dimension	Reasoning	Score
Specificity	Names the domain ('integrating Firebase AI Logic (Gemini API) into web applications') and lists several concrete capability areas ('setup, multimodal inference, structured output, and security'), with only minor gaps in coverage; it stops short of the comprehensive, fully enumerated action list of a 5.	4 / 5
Completeness	It clearly answers 'what' but provides no explicit 'Use when...' trigger guidance, so per the rubric's cap a missing 'when' clause holds completeness at 3.	3 / 5
Trigger Term Quality	Contains natural developer-facing terms like 'Firebase AI Logic', 'Gemini API', 'setup', and 'structured output'; a few common synonyms a user might say (e.g., 'Gemini', 'vision', 'images') are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Firebase AI Logic / Gemini API niche is specific and clearly distinguishable from other skills, with distinct triggers and minimal overlap risk.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: firebase/agent-skills
Path: skills/firebase-ai-logic-basics/SKILL.md
Commit: a0b4e14

Reviewed: 10 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.