CtrlK
BlogDocsLog inGet started
Tessl Logo

database

Use BEFORE editing any file in `supabase/migrations/` or `supabase/schemas/`, OR when the user runs a `/database` subcommand (`compact local migration`, `rls scenarios`, `align`). Encodes the three contracts that protect the Grida database layer: applied migrations are immutable, RLS implementation mirrors tests (never the reverse), `schemas/*.sql` is the human-readable end-state. Companion to `supabase/AGENTS.md` (RLS, grants, security boundaries).

76

Quality

96%

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

100%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, well-structured operational skill that assumes competence and gives executable guidance with validation feedback loops for destructive database operations. References are appropriately delegated one level deep.

DimensionReasoningScore

Conciseness

Lean and operational throughout — no padding explaining what migrations or RLS are; every section earns its tokens with contracts, procedures, and edge cases.

5 / 5

Actionability

Concrete commands (supabase db reset, db test), explicit idempotent forms (CREATE TABLE IF NOT EXISTS, CREATE OR REPLACE FUNCTION), a naming rule keyed on the latest local timestamp, and a worked example with real filenames.

5 / 5

Workflow Clarity

Numbered procedures for all three subcommands with explicit validation checkpoints (db reset, db test) and a user-confirmation gate before touching files — feedback loops are present for these destructive/batch operations.

5 / 5

Progressive Disclosure

Well-organized per-subcommand sections that delegate detail one level deep to supabase/AGENTS.md and the opt-library skill rather than inlining it, with no nested references.

5 / 5

Total

20

/

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, tightly-scoped description that clearly states both what it protects and when to invoke it, with concrete subcommand triggers. The only minor gap is keyword-synonym breadth, which is partly recovered in the body.

DimensionReasoningScore

Specificity

Names the domain (migrations, RLS, schemas) and multiple concrete actions ("compact local migration", "rls scenarios", "align") plus the three governing contracts, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what ("Encodes the three contracts that protect the Grida database layer") and when ("Use BEFORE editing any file in... OR when the user runs a /database subcommand") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers ("Use BEFORE editing any file in supabase/migrations/", "/database subcommand") with the real subcommand names, but synonym-style keyword richness like "consolidate"/"clean up" lives in the body rather than the description.

4 / 5

Distinctiveness Conflict Risk

Scoped to the Grida supabase database layer with specific paths and named subcommands, giving it a clear niche with minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
gridaco/grida
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.