CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

firebase-data-connect

Builds and deploys Firebase SQL Connect (aka Firebase Data Connect) backends with PostgreSQL securely. Use when designing schemas with tables and relations, writing authorized queries and mutations, configuring real-time data updates, or generating type-safe SDKs. Use when you need a relational database with Firebase, or when the user mentions SQL Connect or Data Connect.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-structured overview body with copy-paste CLI commands, a clear default-vs-advanced strategy table, and strongly signaled one-level-deep references for each workflow step. The main weaknesses are the absence of validate→fix→retry feedback loops and pre-deploy verification — significant for a skill whose workflows mutate database schemas — plus slightly inconsistent reference path conventions.

Suggestions

Add an explicit feedback loop after validation in the local-build workflow, e.g. 'If dataconnect:compile reports errors, fix the schema/operations and re-run until it passes cleanly' (workflow_clarity).

Insert a pre-deploy checkpoint in 'How to deploy SQL Connect to Cloud SQL', e.g. 'Run dataconnect:compile and confirm emulator tests pass before deploying, since deploy applies schema changes to the production Cloud SQL instance' (workflow_clarity).

Make the initialize step's verification concrete by naming the command or artifact to check (e.g. 'Verify dataconnect/ directory and generated SDK output exist; run dataconnect:compile to confirm') instead of the vague 'Validate that the app template and generated SDK are setup' (actionability).

Standardize reference paths so templates.md and examples.md use the same reference/ prefix (and section) as the other linked files for consistent navigation (progressive_disclosure).

DimensionReasoningScore

Conciseness

The body is efficient: a compact project-structure tree, a tight strategy table, and copy-paste CLI commands, delegating syntax details to reference files rather than re-teaching GraphQL or PostgreSQL concepts. Minor trimmable padding remains — the product-rename NOTE block, the one-line intro that repeats the description, and the Feature Capability Map re-listing reference files already linked in the workflow steps — which keeps it at 'efficient with minor instances of over-explanation' rather than the lean score-5 anchor.

4 / 5

Actionability

Mostly executable guidance: concrete commands ("npx -y firebase-tools@latest dataconnect:compile", "emulators:start --only dataconnect", "deploy --only dataconnect", "dataconnect:sdk:generate"), a full copy-paste SDK-generation YAML block, and a file-layout tree. Minor gaps: the core authoring work (schema.gql, queries.gql) has no inline example (fully delegated to references), and steps like "Validate that the app template and generated SDK are setup" give no concrete command — so it fits the 'concrete code or commands with minor gaps' anchor rather than 'specific examples cover the common cases'.

4 / 5

Workflow Clarity

The Development Workflow (model → operations → SDK) and the three Deployment & CLI procedures are clearly sequenced, and the local-build path includes a validation checkpoint ("Run ... dataconnect:compile ... to validate them"). However, this is a database-deployment skill where feedback loops matter, and no fix-and-retry loop follows validation, nor is there any pre-deploy verification before "deploy --only dataconnect" mutates the Cloud SQL instance. Per the rubric's cap for database operations lacking feedback loops, workflow clarity is capped at 3 (steps present but checkpoints lack error-recovery), not 4.

3 / 5

Progressive Disclosure

Good structure: SKILL.md stays an overview, each workflow step signals exactly which reference to read with a bullet list of what it contains ("Read [reference/schema.md] for: @table, @ref..."), and the Feature Capability Map aids feature-to-file navigation; all references are one level deep. Minor organization gaps keep it below the 5 anchor: path conventions are inconsistent (most files under reference/, but templates.md and examples.md referenced at skill root), and the inline connector.yaml SDK block overlaps with the also-linked reference/config.md. No bundle directories were present to verify the referenced files exist.

4 / 5

Total

15

/

20

Passed

Description

92%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.

A strong description: it states concrete capabilities in third person and provides explicit, multi-clause 'Use when...' triggers with both product names as synonyms. The only shortcoming is a handful of missing natural trigger terms such as 'GraphQL' and 'Cloud SQL'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Builds and deploys Firebase SQL Connect... backends", "designing schemas with tables and relations", "writing authorized queries and mutations", "configuring real-time data updates", "generating type-safe SDKs" — comprehensively covering the skill's capabilities in third-person voice. This matches the anchor for multiple specific concrete actions with comprehensive coverage, not the score-4 anchor (which expects minor coverage gaps).

5 / 5

Completeness

It explicitly answers both questions: the "what" ("Builds and deploys Firebase SQL Connect... backends with PostgreSQL securely" plus enumerated sub-tasks) and the "when" with two explicit trigger sentences ("Use when designing schemas..., writing authorized queries..., configuring real-time data updates, or generating type-safe SDKs. Use when you need a relational database with Firebase, or when the user mentions SQL Connect or Data Connect."). This mirrors the anchor-5 example's structure exactly, not the score-4 anchor where 'when' is only adequately specific.

5 / 5

Trigger Term Quality

Good natural-term coverage with synonyms — "SQL Connect or Data Connect", "aka Firebase Data Connect", "relational database with Firebase", "queries and mutations", "real-time data updates", "type-safe SDKs", "PostgreSQL". A few natural terms users would say are missing (e.g., "GraphQL", "Cloud SQL"), and no file extensions (.gql/.yaml), so it sits between good coverage (4) and comprehensive synonym+extension coverage (5), closer to 4.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — Firebase's relational/PostgreSQL product — with product-name triggers ("SQL Connect", "Data Connect") that are unlikely to fire for unrelated database or Firebase skills. The only conceivable overlap is generic PostgreSQL work, but the trigger phrase "relational database with Firebase" keeps that risk minimal, matching the clear-niche anchor.

5 / 5

Total

19

/

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

relative_links

Relative link issues: 25 missing

Warning

Total

14

/

16

Passed

Repository

firebase/agent-skills

Path

skills/firebase-data-connect-basics/SKILL.md

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.