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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%Weight 40%Scale 1-3

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

The body is concise and well-organized with a sensible high-level workflow, but it stays at an abstract task-checklist level with no executable code and an internal reference that points to a non-existent file while ignoring the real bundle files. Actionability and navigation are the main gaps.

Suggestions

Fix the broken reference: replace '${CLAUDE_SKILL_DIR}/references/SKILL.full.md' with links to the actual bundle files (implementation.md, examples.md, errors.md) and reference scripts/init-firebase.sh where initialization is discussed.

Add at least one concrete, executable snippet — e.g. a minimal Cloud Function calling Vertex AI with Secret Manager wiring — so the Instructions move from describing to instructing.

Make the workflow's validation explicit with a feedback loop, e.g. after step 4 add 'If smoke tests fail: review Error Handling, fix, redeploy, and re-run until passing'.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned (Overview, Prerequisites, Instructions, Output, Error Handling, Examples, Resources) without explaining what Firebase or Vertex AI is, so every section earns its place; it assumes Claude's competence rather than padding with known concepts.	3 / 3
Actionability	Instructions name concrete components ('Cloud Function/HTTP endpoint that calls Gemini/Vertex AI', 'Firestore rules + indexes', 'Secret Manager') but provide no executable code or commands — they describe what to build rather than how, matching 'some concrete guidance but incomplete; missing key details'; not level 1 because it is more specific than a single vague directive, and not level 3 because nothing is copy-paste ready.	2 / 3
Workflow Clarity	The five numbered steps give a clear sequence and step 4 includes a verify action ('run smoke tests against deployed endpoints'), but there is no explicit feedback loop (e.g. if smoke tests fail → fix → redeploy) and checkpoints are implicit; matching 'steps listed but validation gaps', not level 3 which requires explicit validation checkpoints and error-recovery loops.	2 / 3
Progressive Disclosure	The body is well sectioned and attempts to offload detail to a reference, but the one internal link points to '${CLAUDE_SKILL_DIR}/references/SKILL.full.md' which does not exist — the actual bundle contains errors.md, examples.md, implementation.md, and scripts/init-firebase.sh, none of which are linked; matching 'references present but not clearly signaled' rather than level 3's well-signaled one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, complete, and uses natural trigger phrases a user would actually say, with a clear niche that is unlikely to conflict with other skills. Its only weakness is the redundant filler sentence 'Trigger with relevant phrases based on skill purpose' that adds nothing after the explicit triggers.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'Authentication, Firestore, Storage, Functions, Hosting, and AI-powered features' plus 'Vertex AI Gemini integration' — matching the anchor for listing several specific concrete actions; not the level below which only names a domain and some actions.	3 / 3
Completeness	Explicitly answers both what (the Firebase services + Vertex AI integration) and when (an explicit 'Use when asked to...' clause with quoted triggers), satisfying the top anchor; not capped at 2 since an explicit trigger clause is present.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — 'setup firebase', 'deploy to firebase', 'integrate vertex ai with firebase' — that a user would actually say, giving good coverage; the trailing 'Trigger with relevant phrases based on skill purpose' is filler but does not displace the natural keywords.	3 / 3
Distinctiveness Conflict Risk	The Firebase + Vertex AI/Gemini pairing with its quoted triggers is a clear niche unlikely to fire for unrelated skills; not level 2 because the triggers are specific rather than broadly overlapping.	3 / 3
	Total	12 / 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
Path: plugins/community/jeremy-firebase/skills/firebase-vertex-ai/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.