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.
47
51%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/community/jeremy-firebase/skills/firebase-vertex-ai/SKILL.mdQuality
Discovery
67%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 covers a clear domain (Firebase with Vertex AI) and includes an explicit 'Use when' clause with some trigger phrases, which is good. However, the opening phrase 'Execute firebase platform expert' is awkward and non-descriptive, the listed capabilities are service names rather than concrete actions, and the closing sentence 'Trigger with relevant phrases based on skill purpose' is meaningless filler that wastes space.
Suggestions
Replace 'Execute firebase platform expert' with concrete action verbs describing what the skill does, e.g., 'Configures Firebase Authentication, sets up Firestore databases, deploys Cloud Functions, manages Storage buckets, and integrates Vertex AI Gemini models.'
Remove the vague filler 'Trigger with relevant phrases based on skill purpose' and instead add more natural trigger terms users would say, such as 'firebase auth', 'firestore rules', 'cloud functions', 'firebase deploy', 'firebase hosting', 'gemini API'.
Expand the 'Use when' clause to cover more user scenarios, e.g., 'Use when configuring Firebase services, writing Firestore security rules, deploying cloud functions, setting up authentication flows, or adding Gemini AI features to a Firebase project.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Firebase platform) and lists several services (Authentication, Firestore, Storage, Functions, Hosting, Vertex AI Gemini), but the actions are vague — 'Execute firebase platform expert' is not a concrete action, and it doesn't describe what specific operations are performed with each service. | 2 / 3 |
Completeness | It does answer both 'what' (Firebase platform services and Vertex AI integration) and 'when' (explicit 'Use when' clause with trigger phrases like 'setup firebase', 'deploy to firebase', 'integrate vertex ai with firebase'). Both components are present, though the 'what' could be more detailed. | 3 / 3 |
Trigger Term Quality | It includes some useful trigger terms like 'setup firebase', 'deploy to firebase', 'integrate vertex ai with firebase', and service names like Firestore, Storage, Functions. However, it misses many natural variations users might say (e.g., 'firebase auth', 'cloud functions', 'firebase database', 'firestore rules', 'firebase config'). The phrase 'Trigger with relevant phrases based on skill purpose' is vague filler that adds no value. | 2 / 3 |
Distinctiveness Conflict Risk | The Firebase + Vertex AI combination is somewhat distinctive, but the broad scope covering Authentication, Firestore, Storage, Functions, and Hosting could overlap with general cloud deployment skills, backend development skills, or individual service-specific skills. The phrase 'AI-powered features' is particularly generic. | 2 / 3 |
Total | 9 / 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.
This skill provides a reasonable high-level framework for Firebase + Vertex AI projects but critically lacks actionability — there are zero executable code snippets, CLI commands, or concrete configuration examples. The workflow is sequenced but missing validation checkpoints. The content reads more like a project plan outline than an actionable skill that Claude can follow to produce working code.
Suggestions
Add concrete, executable code examples: a minimal Cloud Function calling Vertex AI/Gemini, specific `firebase init` and `firebase deploy` commands, and a sample Firestore security rule.
Include validation checkpoints in the workflow: e.g., 'Run `firebase emulators:start` and test locally before deploying' and 'Verify with `curl https://<project>.web.app/api/chat`'.
Replace the abstract examples with at least one complete, copy-paste-ready implementation showing the Function code, secret configuration, and deployment commands.
Either provide the referenced `SKILL.full.md` bundle file or inline the critical details (IAM setup, Secret Manager commands, Firestore index creation) that are currently missing from the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some unnecessary framing (e.g., the Overview section largely restates the description). Phrases like 'Use this skill to design, implement, and deploy' and the Prerequisites section explaining what a Firebase project needs are somewhat padded for Claude's knowledge level. | 2 / 3 |
Actionability | The instructions are entirely abstract and descriptive — no executable code, no specific CLI commands (e.g., `firebase init`, `firebase deploy`), no concrete configuration snippets, no actual Vertex AI integration code. Every step says what to do conceptually but never shows how. The examples describe inputs and results but provide no actual implementation. | 1 / 3 |
Workflow Clarity | There is a numbered sequence of steps covering init → implement → configure → deploy → ops, which provides a reasonable high-level workflow. However, there are no validation checkpoints between steps, no feedback loops for error recovery during deployment, and the 'deploy and verify' step lacks specifics on what constitutes passing smoke tests. | 2 / 3 |
Progressive Disclosure | The skill references a detailed guide at `${CLAUDE_SKILL_DIR}/references/SKILL.full.md` and external docs, which is good structure. However, no bundle files were provided to verify the reference exists, and the main content includes sections (Error Handling, Examples) that are too shallow to be useful inline yet too present to justify their space — they should either be fleshed out or moved to the reference file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
16dfbca
Table of Contents
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.