CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

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

71%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 thorough, highly actionable policy document with concrete commands, executable examples, and explicit validation rules for risky database operations. Its main weaknesses are a monolithic single-file structure that inlines reference-grade material and some duplicated guidance around db-exec/db-patch.

Suggestions

Move the identity-column policy, state-machine rules, and migration-ownership details into reference files under references/ (e.g., references/identity-columns.md, references/migrations.md) and keep SKILL.md as an overview with one-level-deep pointers.

Consolidate the db-exec vs db-patch guidance into the decision table only, removing its repetition in the Agent Access bullet list and the Do list.

Make the domain-data code example self-contained by showing how `db` is obtained (e.g., const db = getDb()) so the snippet is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no explanations of what Postgres, ORM, or OAuth are), but the db-exec vs db-patch guidance is repeated across the Agent Access list, the decision table, and the Do list, and the migration-naming rationale paragraph runs long — some trimming is possible.

4 / 5

Actionability

Guidance is highly concrete: exact commands with flags (pnpm action db-patch --table <t> --column <c>), executable registerIdentityColumns and Drizzle schema snippets, and named APIs. Minor gap: the domain-data example queries via a `db` variable that is never defined in the snippet (getDb()/createGetDb is described only in prose).

4 / 5

Workflow Clarity

Risky operations carry explicit validation: migrations must be additive and backward compatible, status transitions are compare-and-set with "treat zero updated rows as a lost race or an illegal transition, never success", and a decision table routes db-exec vs db-patch. However, the migration-ownership paths (Drizzle Kit starters vs Chat vs Clips) are scattered across several conditionals rather than one clear sequence.

4 / 5

Progressive Disclosure

The skill is a single ~250-line file with no references/ bundle; well-organized sections and tables exist, but deep policy material that belongs in separate reference files (identity-column policies, state-machine rules, migration ownership details) is fully inlined in SKILL.md.

3 / 5

Total

15

/

20

Passed

Description

87%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 that clearly states both the capability (SQL as the source of truth for application data) and explicit usage triggers in third person. Trigger coverage is good but could add common synonyms like "database" or "schema" to broaden natural matching.

DimensionReasoningScore

Specificity

The description names several specific actions ("adding data models, deciding where to store data, or reading/writing application data") grounded by the concrete claim "All data lives in SQL", but the lead phrase "How to store application data" is generic and it does not enumerate concrete capabilities like anchor 5 requires.

4 / 5

Completeness

It explicitly answers both: what ("How to store application data in agent-native apps. All data lives in SQL.") and when ("Use when adding data models, deciding where to store data, or reading/writing application data.") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ("data models", "where to store data", "reading/writing application data"), but common synonyms such as "database", "schema", or "migrations" are missing, keeping it just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The scope is tightly pinned to "agent-native apps" with a clear SQL-storage niche and distinct triggers (data models, where to store data), so it is unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/storing-data/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.