firebase-ai-logic
Integrate Firebase AI Logic (Gemini in Firebase) for intelligent app features. Use when adding AI capabilities to Firebase apps, implementing generative AI features, or setting up Firebase AI SDK. Handles Firebase AI SDK setup, prompt engineering, and AI-powered features.
83
77%
Does it follow best practices?
Impact
95%
1.15xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/firebase-ai-logic/SKILL.mdQuality
Discovery
89%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 solid skill description with explicit 'Use when' triggers and good keyword coverage for Firebase AI/Gemini integration. The main weakness is that some capability descriptions are vague ('AI-powered features', 'intelligent app features') rather than listing specific concrete actions like 'generate text responses', 'implement chat interfaces', or 'configure model parameters'.
Suggestions
Replace vague terms like 'AI-powered features' and 'intelligent app features' with specific actions such as 'generate text responses', 'implement multimodal inputs', or 'configure safety settings'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Firebase AI Logic/Gemini) and some actions ('SDK setup, prompt engineering, AI-powered features'), but the actions are somewhat generic and not comprehensively specific. 'AI-powered features' and 'intelligent app features' are vague. | 2 / 3 |
Completeness | Clearly answers both what ('Integrate Firebase AI Logic...Handles Firebase AI SDK setup, prompt engineering, and AI-powered features') and when ('Use when adding AI capabilities to Firebase apps, implementing generative AI features, or setting up Firebase AI SDK'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'Firebase AI Logic', 'Gemini in Firebase', 'AI capabilities', 'Firebase apps', 'generative AI features', 'Firebase AI SDK'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Firebase AI Logic/Gemini integration. The combination of 'Firebase' + 'AI SDK' + 'Gemini' creates distinct triggers unlikely to conflict with generic AI skills or other Firebase skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%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 for Firebase AI Logic integration with clear step-by-step setup instructions. However, it lacks validation checkpoints for a multi-step setup process, contains an incorrect SDK dependency, and includes placeholder content that adds no value. The error handling guidance mentioned in constraints is not demonstrated in the code examples.
Suggestions
Add validation steps after Firebase setup (e.g., 'Verify setup: firebase projects:list should show your project') and after SDK initialization
Remove the incorrect '@anthropic-ai/sdk' from the npm install command - this is unrelated to Firebase AI Logic
Add concrete error handling examples in the code to match the stated constraint, showing try/catch patterns and fallback behavior
Either populate the empty Example sections with real content or remove them entirely
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary elements like empty example placeholders, metadata section with version/platform info Claude doesn't need, and the npm install line incorrectly includes @anthropic-ai/sdk which is unrelated to Firebase AI Logic. | 2 / 3 |
Actionability | Provides fully executable TypeScript code examples for initialization, text generation, streaming, and multimodal use cases. Code is copy-paste ready with clear function signatures and usage patterns. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but lacks validation checkpoints. No guidance on verifying Firebase setup succeeded, no error handling examples shown despite being listed as required, and no feedback loop for troubleshooting failed AI responses. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the skill is somewhat monolithic. The empty example sections at the end add no value, and detailed security rules could be referenced externally rather than inline. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- 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.