CtrlK
BlogDocsLog inGet started
Tessl Logo

firebase-ai-logic-basics

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

73

1.47x
Quality

61%

Does it follow best practices?

Impact

96%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/firebase-ai-logic-basics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

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

The skill is well-structured with real, one-level-deep bundle references carrying the platform-specific code, and setup/App Check guidance is concrete. Weaknesses are concentrated in actionability and conciseness: several capability headings are empty or one-liners with no code, and the body carries duplicated warnings and product-history padding.

Suggestions

Fill the empty sections ("Text-Only Generation", "Search Grounding with the built in googleSearch tool") with at least one short code snippet or remove them, and add a minimal structured-output schema example to the "Structured Output (JSON)" section.

Remove the duplicated 'CRITICAL: Use current model names' warning block (it appears verbatim in both Core Capabilities and Initialization Code References) and trim the rebranding history from the Overview.

Add explicit validation checkpoints to the setup workflow, e.g. how to confirm the Gemini Developer API was enabled after `npx firebase-tools init ailogic` and what to do if `apps:list` shows no apps.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but includes unnecessary explanation Claude doesn't need ("Firebase AI Logic is a product of Firebase that allows developers to add gen AI to their mobile and web apps", "represents the evolution of Google's AI integration platform") and duplicates the identical 'Use current model names' warning block twice. This matches anchor 3's 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not anchor 4 because the duplication and product-history padding are more than minor trimmable instances.

3 / 5

Actionability

Setup and App Check sections are concrete ("npm install firebase@latest", "npx -y firebase-tools@latest init ailogic", specific debug-token registration steps), but several core capability sections are empty or vague: "Text-Only Generation" and "Search Grounding with the built in googleSearch tool" have no content at all, "Structured Output (JSON)" says only "Enforce a specific JSON schema for the response" with no schema example, and "Chat Session (Multi-turn)" gives only "Maintain history automatically using startChat". This lands between anchors 3 and 4; empty headings and missing code for the core use cases justify 3 rather than 4.

3 / 5

Workflow Clarity

Setup has a rough ordered sequence (prerequisites → install → verify apps:list → init) and the debug-token flows are numbered with specific console paths, but the overall document is a capability catalog rather than a sequenced workflow, and validation checkpoints are implicit at best (e.g., no check that init succeeded or how to verify the API is enabled). Matches anchor 3: 'sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

The body appropriately delegates per-platform code to four real one-level-deep bundle files (references/usage_patterns_web.md, usage_patterns_android.md, ios_setup.md, flutter_setup.md), all of which exist, and links them clearly. Good structure matching anchor 4; not anchor 5 because the 'Initialization Code References' and 'References' sections redundantly list the same files, and the duplicated model-name warning adds noise.

4 / 5

Total

13

/

20

Passed

Description

70%Weight 40%Scale 1-5

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 and highly distinguishable, with good natural keywords around Firebase and the Gemini API. Its main weakness is the absence of any explicit 'when to use' trigger clause, and it under-represents scope by saying only 'web applications' although the skill covers Android, iOS, Flutter, and Unity as well.

Suggestions

Add an explicit trigger clause, e.g. 'Use when integrating the Gemini API or Firebase AI Logic into a web, Android, iOS, or Flutter app, or when the user mentions Gemini, Vertex AI for Firebase, or adding AI features to a Firebase project.'

Reflect the full platform scope (web, Android, iOS, Flutter, Unity) instead of only 'web applications', since the body covers all of them.

Include a few more natural trigger synonyms such as 'gen AI features', 'Vertex AI for Firebase', or 'AI chat' to improve keyword coverage.

DimensionReasoningScore

Specificity

"integrating Firebase AI Logic (Gemini API) into web applications" names a concrete action and the description lists several specific capability areas ("setup, multimodal inference, structured output, and security"), matching anchor 4's 'several specific actions; minor gaps in coverage'. It is not anchor 5 because the items are topic nouns rather than explicit actions, and notable capabilities (chat, streaming, image generation) are omitted; not anchor 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

The 'what' is clear (integrating Firebase AI Logic into web apps covering setup, multimodal inference, structured output, security), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not anchor 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

Strong natural keywords users would actually say: "Firebase AI Logic", "Gemini API", "structured output", "web applications". Not anchor 5 because common synonyms and variations are missing (e.g., "gen AI", "Vertex AI", "chatbot", "LLM", other platform names); not anchor 3 because coverage is clearly better than 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

"Firebase AI Logic (Gemini API)" names a specific product niche with distinct triggers, unlikely to fire for unrelated skills. Not anchor 4 because there is no meaningful overlap risk with another plausible skill category; the product name itself is the trigger.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
firebase/agent-skills
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.