firebase-vertex-ai

tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill firebase-vertex-ai

Execute firebase platform expert with Vertex AI Gemini integration for Authentication, Firestore, Storage, Functions, Hosting, and AI-powered features. Use when asked to "setup firebase", "deploy to firebase", or "integrate vertex ai with firebase". Trigger with relevant phrases based on skill purpose.

55%

Overall

Validation — 81%

Implementation — 42%

Activation — 50%

SKILL.md

Review

Evals

Validation

81%

Warnings & errors only

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata' field is not a dictionary	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Implementation

42%

This skill has good organizational structure and appropriate progressive disclosure, but critically lacks actionable, executable guidance. The instructions read like a high-level checklist rather than concrete implementation steps. Without actual code examples, specific CLI commands, or copy-paste ready snippets, Claude would struggle to execute this skill effectively.

Suggestions

Add executable code examples for the Cloud Function calling Gemini/Vertex AI, including proper secrets handling with Secret Manager

Include specific Firebase CLI commands (e.g., 'firebase init functions', 'firebase deploy --only functions') in the workflow steps

Add concrete Firestore security rules examples and validation commands

Replace abstract 'smoke tests' with actual test commands or curl examples against deployed endpoints

Dimension	Reasoning	Score
Conciseness	Content is reasonably efficient but includes some unnecessary framing ('Operate Firebase projects end-to-end') and the Overview section largely restates what the skill does rather than adding actionable value. Could be tightened.	2 / 3
Actionability	Instructions are abstract and vague ('add a Cloud Function/HTTP endpoint that calls Gemini/Vertex AI', 'validate inputs'). No executable code, no specific commands, no copy-paste ready examples. The Examples section describes outcomes but provides no actual implementation.	1 / 3
Workflow Clarity	Steps are listed in sequence (1-5) but lack explicit validation checkpoints. 'Run smoke tests' is mentioned but not defined. No feedback loops for error recovery during deployment. Missing concrete verification commands.	2 / 3
Progressive Disclosure	Good structure with clear sections. References external detailed guide and official docs appropriately. Content is well-organized with Overview, Instructions, Output, Error Handling, Examples, and Resources clearly separated.	3 / 3
	Total	8 / 12 Passed

Activation

50%

The description identifies the Firebase platform and Vertex AI integration domain but fails to describe concrete actions Claude would perform. It includes some explicit trigger phrases which is good, but the vague 'execute firebase platform expert' phrasing and the unhelpful meta-instruction 'Trigger with relevant phrases based on skill purpose' weaken its effectiveness for skill selection.

Suggestions

Replace 'Execute firebase platform expert' with specific actions like 'Configure authentication flows, create Firestore collections, deploy Cloud Functions, set up hosting'

Remove the meta-instruction 'Trigger with relevant phrases based on skill purpose' and instead add concrete trigger terms like 'firebase auth', 'firestore database', 'cloud functions', 'firebase deploy'

Expand the 'Use when' clause to cover more user scenarios such as 'building serverless backends', 'adding user authentication', or 'deploying web apps to Firebase Hosting'

Dimension	Reasoning	Score
Specificity	Names the domain (Firebase platform) and lists several services (Authentication, Firestore, Storage, Functions, Hosting, Vertex AI), but uses vague language like 'execute firebase platform expert' and 'AI-powered features' without describing concrete actions.	2 / 3
Completeness	Has a partial 'what' (Firebase services listed) and includes a 'Use when' clause with specific triggers, but the 'what' is weak (doesn't describe actual actions) and the meta-instruction about triggering adds no value. The explicit trigger guidance saves it from a 1.	2 / 3
Trigger Term Quality	Includes some useful trigger phrases like 'setup firebase', 'deploy to firebase', and 'integrate vertex ai with firebase', but the final sentence 'Trigger with relevant phrases based on skill purpose' is meta-instruction rather than actual trigger terms, missing common variations like 'firestore database', 'firebase auth', or 'cloud functions'.	2 / 3
Distinctiveness Conflict Risk	Firebase-specific terms provide some distinctiveness, but 'AI-powered features' and generic cloud deployment language could overlap with other cloud platform or AI integration skills. The Vertex AI + Firebase combination is somewhat distinctive.	2 / 3
	Total	8 / 12 Passed

Reviewed

15 days ago

Table of Contents

Validation Implementation Activation

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.