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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized and reasonably lean, with a clear workflow skeleton and useful error-handling guidance. Its major weakness is actionability: it describes steps abstractly with no executable code or commands, and its progressive disclosure is undermined by a broken reference link and orphaned bundle files.

Suggestions

Add concrete, copy-paste-ready commands and code snippets (e.g., `firebase deploy --only functions`, a sample Cloud Function calling Vertex AI, Secret Manager wiring) instead of describing them abstractly.

Fix the broken reference: replace references/SKILL.full.md with the actual bundle files (errors.md, examples.md, implementation.md) and add a link to scripts/init-firebase.sh so the bundled material is discoverable.

Tighten hedging language ('as needed', 'where appropriate', 'if applicable') and add an explicit validate-fix-retry checkpoint with concrete smoke-test commands in the Deploy and verify step.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but recurring generic qualifiers ('as needed', 'where appropriate', 'if applicable', 'as required') and illustrative-only examples keep it from being fully tight.	2 / 3
Actionability	The instructions describe tasks ('add a Cloud Function/HTTP endpoint that calls Gemini/Vertex AI', 'run smoke tests against deployed endpoints') without any executable code or concrete commands, and the bundled scripts/init-firebase.sh is never referenced from the body.	1 / 3
Workflow Clarity	A clear five-step sequence with a deploy-and-verify step is present, but validation checkpoints are implicit (no concrete smoke-test commands) and there is no explicit validate-fix-retry feedback loop for the deployment workflow.	2 / 3
Progressive Disclosure	The body is well sectioned as an overview, but its single reference link points to references/SKILL.full.md which does not exist, while the actual bundle files (errors.md, examples.md, implementation.md, scripts/init-firebase.sh) are not surfaced or linked.	2 / 3
	Total	7 / 12 Passed

Description

90%

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 strong: it covers a specific niche, names the relevant Firebase services and Vertex AI integration, and includes explicit, natural trigger phrases. The main weakness is the slightly abstract lead verb rather than a crisp enumeration of concrete actions.

Dimension	Reasoning	Score
Specificity	It enumerates concrete Firebase domains (Authentication, Firestore, Storage, Functions, Hosting) plus Vertex AI, but the verb phrase 'Execute firebase platform expert with Vertex AI Gemini integration' is abstract rather than listing multiple distinct concrete actions like 'deploy', 'configure rules', or 'wire secrets'.	2 / 3
Completeness	It states what the skill does (Firebase platform execution with Vertex AI/Gemini integration across listed services) and provides an explicit 'Use when...' clause, answering both what and when.	3 / 3
Trigger Term Quality	The 'Use when asked to "setup firebase", "deploy to firebase", or "integrate vertex ai with firebase"' clause uses natural phrases a user would actually say, with good coverage of the main intents.	3 / 3
Distinctiveness Conflict Risk	The Firebase-plus-Vertex-AI combination is a clear niche with distinct, specific triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	11 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 2cafb23

Reviewed: 2 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.