CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

supabase

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/supabase/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 strong, genuinely Supabase-specific body: the security checklist and CLI gotchas are concrete and executable, with real validation checkpoints in the commit workflow. The main costs are token-efficiency — the approval-gate language is repeated many times and repo-specific overrides are inlined — and a few vague hand-waves where commands are expected.

Suggestions

State the disposable-local-database/approval policy once (e.g., in a short 'Safety boundaries' section) and reference it elsewhere instead of repeating it ~5 times.

Extract the BigSimmo/PsychSift repository override into a reference file (or trim it), so the generic skill body stays lean.

Replace vague steps with commands: specify what 'the smallest repository-provided offline or local-emulator proof' and 'the approved local workflow' actually run.

DimensionReasoningScore

Conciseness

Mostly dense, high-value Supabase-specific traps, but the disposable-local-database/approval-gate policy is restated ~5 times across the override section, CLI gotchas, and schema-changes section, and the repository-specific 'BigSimmo/PsychSift' override is padding for general users. More than the 'minor instances' of anchor 4, well short of the padded-concept-explanations of anchor 2.

3 / 5

Actionability

Concrete throughout: executable curl connectivity check, `supabase --help` discovery pattern, copy-paste SQL policy examples with TO/USING/WITH CHECK, specific CLI version floors, and the .md-suffix doc-fetching trick. Minor gaps like 'create the migration file through the approved local workflow' and 'run the smallest repository-provided offline proof' keep it below fully-executable anchor 5.

4 / 5

Workflow Clarity

Ordered MCP troubleshooting steps, a numbered commit workflow with validation checkpoints (advisors → security checklist → migration → `supabase migration list --local`), and an explicit error-recovery loop ('If an approach fails after 2-3 attempts, stop and reconsider'). The 'Verify your work' principle is underspecified for a skill gating destructive database operations, so not anchor 5.

4 / 5

Progressive Disclosure

Well-sectioned body; the single reference (references/skill-feedback.md) exists, is one level deep, clearly signaled with a 'MUST read when' condition, and correctly links to the real assets/feedback-issue-template.md. Minor gap: the repeated repo-override/approval policy is a natural candidate for extraction into a reference file.

4 / 5

Total

15

/

20

Passed

Description

73%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 trigger-optimized description with excellent, granular keyword coverage and a clear Supabase niche. Its main weakness is that it never states what the skill does when triggered, leaning entirely on an exhaustive 'when' list. Adding a one-clause capability statement would raise completeness and specificity.

Suggestions

Open with a concrete 'what' clause (e.g., 'Guides Supabase development: verifies against current docs/changelog, applies a Supabase security checklist, and manages CLI/MCP migrations') before the trigger list.

Tighten 'Use when doing ANY task involving Supabase' — 'ANY' in caps is an over-claim next to an already-exhaustive trigger list.

Qualify generic Postgres terms (migrations, RLS, extensions) with Supabase context to reduce overlap with plain Postgres skills.

DimensionReasoningScore

Specificity

Enumerates many concrete items ("Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues", "supabase-js, @supabase/ssr", "pg_graphql, pg_cron, pg_vector"), but the capability itself is only "doing ANY task involving Supabase" — the actions the skill performs are implied, never stated, so it falls short of the comprehensive-actions anchor 5.

4 / 5

Completeness

The 'when' is explicit and thorough ("Use when doing ANY task involving Supabase. Triggers: ..."), but the 'what' — what the skill actually does (verify against changelog, security checklist, migration workflow) — is only weakly implied by the domain list. Not 4 because a real 'what' statement is absent.

3 / 5

Trigger Term Quality

Covers natural terms comprehensively down to API-method level: "login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS", framework names (Next.js, SvelteKit, Astro, Remix), plus "CLI or MCP server" — matching the anchor-5 bar of synonyms and specific user-facing phrases.

5 / 5

Distinctiveness Conflict Risk

"ANY task involving Supabase" plus product and library names carve a clear niche with distinct triggers, but generic terms like "JWT, cookies, sessions", "schema changes, migrations", and Postgres extensions (pg_cron, pg_vector) create minor overlap risk with plain Postgres or auth skills.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.cursor/skills/supabase/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.