storing-data

How to store application data in agent-native apps. All data lives in SQL. Use when adding data models, deciding where to store data, or reading/writing application data.

Quality

83%

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

82%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 dense, highly actionable skill body with concrete commands, code, and decision tables that assume Claude's competence. It is well structured and mostly concise, with only minor verbosity in the migration rationale and the absence of an explicit validation feedback loop for destructive maintenance.

Suggestions

Add an explicit validate/retry checkpoint to the ad-hoc maintenance workflow (e.g., run db-query to confirm affected rows before/after a db-exec UPDATE or db-patch) to satisfy the feedback-loop expectation for destructive database operations.

Tighten the migration-collision narrative: keep the prescriptive 'always give new migrations a unique name:' rule and a one-sentence rationale, and move the full analytics incident story into a reference file to reclaim context budget.

Consider extracting the per-template tables and the db-exec vs db-patch decision matrix into a reference file, keeping SKILL.md as a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	Largely efficient and assumes Claude's competence, with concrete tables, commands, and code; a few explanatory passages (e.g., the migration collision war story and the db-patch rationale) are longer than strictly necessary but earn their place through high practical value.	4 / 5
Actionability	Provides copy-paste-ready code, exact commands (pnpm action db-patch/db-exec with flags), a decision table for db-exec vs db-patch, and schema examples that cover the common cases concretely.	5 / 5
Workflow Clarity	Multi-step processes (migration naming, production deploy steps 1-3, the db-exec vs db-patch decision flow) are clearly sequenced with explicit guardrails ('fail closed', 'schema changes are blocked'), though destructive/batch maintenance paths lack an explicit validate-then-retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with inline reference tables and pointers to related skills (context-awareness, real-time-sync, actions); no bundle files exist, so depth is one level, with minor inlining of material (template table, store table) that could live separately.	4 / 5
	Total	17 / 20 Passed

Description

83%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 clear, third-person description that states both what the skill does and when to use it with explicit trigger guidance. It is specific and distinct, with only minor room to add more concrete operations and natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (storing application data) and concrete actions (adding data models, deciding where to store data, reading/writing data), though the actions are activity-level rather than fully concrete operations like the 5-anchor 'extract, fill, merge'.	4 / 5
Completeness	Explicitly answers both 'what' (how to store application data; all data lives in SQL) and 'when' with a concrete 'Use when adding data models, deciding where to store data, or reading/writing application data' clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('data models', 'store data', 'reading/writing application data') with good coverage, but lacks synonyms or concrete file/extension-style terms that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The SQL/agent-native niche and 'store application data' framing are mostly distinct from sibling skills, though 'reading/writing application data' is broad enough to risk minor overlap with data-access or actions skills.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/storing-data/SKILL.md
Commit: bb282b1

Reviewed: ~20 hours 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.