firebase-ai-logic-basics
Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
56
33%
Does it follow best practices?
Impact
100%
1.42xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/firebase-ai-logic-basics/SKILL.mdQuality
Discovery
32%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 identifies its domain (Firebase AI Logic / Gemini API) and lists topic areas but lacks concrete actions and explicit trigger guidance. The absence of a 'Use when...' clause is a significant weakness that would make it harder for Claude to know when to select this skill. The topic-level terms (setup, multimodal inference, structured output, security) are too broad to serve as effective differentiators.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about integrating Gemini or Firebase AI into a web app, calling generative AI models from client-side code, or configuring Firebase App Check for AI endpoints.'
Replace topic-level terms with concrete actions, e.g., 'Initialize the Firebase AI Logic SDK, send text and image prompts to Gemini models, define structured JSON response schemas, and configure App Check security rules.'
Include more natural trigger terms and variations users might say, such as 'Gemini model', 'Firebase generative AI', 'vertex AI in Firebase', '@firebase/ai', or 'AI content generation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Firebase AI Logic / Gemini API) and lists some actions (setup, multimodal inference, structured output, security), but these are more like topic areas than concrete actions. It doesn't specify what concrete tasks the user can accomplish (e.g., 'configure API keys', 'send image prompts', 'define response schemas'). | 2 / 3 |
Completeness | It describes what the skill covers at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also only weakly specified, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Firebase', 'Gemini API', 'multimodal', and 'web applications' that users might mention. However, it misses common variations and natural phrases users would say, such as 'AI in Firebase', 'Gemini model', 'Firebase ML', 'vertex AI', 'generate content', or 'LLM integration'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Firebase AI Logic' and 'Gemini API' provides some distinctiveness, but 'web applications', 'setup', and 'security' are generic enough to overlap with other Firebase or web development skills. It could conflict with general Firebase skills or general AI/LLM integration skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable overview of Firebase AI Logic with good setup commands and important security warnings, but falls short on actionability — most core capability sections are descriptive placeholders without executable code examples. The content would benefit significantly from concrete code snippets for each capability and clearer validation steps in the workflow.
Suggestions
Add executable code examples for each core capability section (Text-Only Generation, Chat Session, Streaming, Structured Output) — even minimal 3-5 line snippets would dramatically improve actionability.
Either populate the empty sections (Text-Only Generation, Search Grounding) with concrete guidance or remove them and point to reference files instead.
Add validation/verification steps after setup (e.g., a test call to confirm the API is working) to improve workflow clarity.
Trim descriptive explanations of what features do (e.g., the multimodal paragraph) and replace with concise code showing how to use them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., explaining what Firebase AI Logic is, describing what multimodal means, listing supported platforms verbosely) that Claude already knows. However, it's not egregiously padded and does contain useful setup commands and configuration details. | 2 / 3 |
Actionability | The skill is mostly descriptive rather than instructive. Core capabilities sections like Text-Only Generation, Chat Session, Streaming Responses, Structured Output, and Search Grounding are headers with little to no executable code or concrete examples. The setup commands are concrete, but the majority of the skill describes features without showing how to implement them. | 1 / 3 |
Workflow Clarity | The setup section has a reasonable sequence (prerequisites → install → project check → app list → init), but there are no validation checkpoints or error recovery steps. The App Check warning is good but lacks implementation steps. The overall flow from setup to implementation to production is implied but not explicitly sequenced with verification gates. | 2 / 3 |
Progressive Disclosure | The skill references external files (references/usage_patterns_web.md, references/ios_setup.md, references/flutter_setup.md, references/usage_patterns_android.md) and external Firebase docs, which is good structure. However, the main file contains several empty or near-empty sections (Text-Only Generation, Search Grounding) that should either have brief content or explicitly point to references. The initialization code references table mixes internal and external links inconsistently. | 2 / 3 |
Total | 7 / 12 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.
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
- firebase/agent-skills
- Commit
f8e7f0e
- 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.