supabase
Core Supabase CLI, migrations, RLS, Edge Functions
40
40%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/supabase/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a comma-separated list of Supabase-related topics with no verbs, no concrete actions, and no trigger guidance. While the Supabase domain provides some natural distinctiveness, the lack of specificity and completeness makes it very weak for skill selection among a large pool of skills.
Suggestions
Add concrete action verbs describing what the skill does, e.g., 'Generates and manages Supabase database migrations, configures Row Level Security policies, scaffolds and deploys Edge Functions.'
Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user asks about Supabase setup, database migrations, row level security, RLS policies, or deploying Edge Functions.'
Expand trigger term coverage to include natural variations like 'row level security', 'database policies', 'supabase deploy', 'supabase init', and 'serverless functions'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists domain keywords ('Supabase CLI, migrations, RLS, Edge Functions') but does not describe any concrete actions. There are no verbs or actionable phrases—just a list of topics. | 1 / 3 |
Completeness | The description barely answers 'what does this do' (only topic nouns, no actions) and completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords a user might mention ('Supabase', 'migrations', 'RLS', 'Edge Functions'), but misses common variations like 'row level security', 'supabase deploy', 'database policies', or 'serverless functions'. Coverage is partial. | 2 / 3 |
Distinctiveness Conflict Risk | 'Supabase' is a fairly distinct domain, which helps avoid conflicts with generic database or CLI skills. However, the vague phrasing ('Core Supabase CLI') could overlap with other Supabase-related skills if multiple exist. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent, executable code examples across all Supabase domains, making it immediately useful. However, it tries to cover too much in a single file without progressive disclosure — CLI, migrations, RLS, Edge Functions, Storage, env vars, CI/CD, and anti-patterns all inline — resulting in a lengthy monolithic document. The workflow sections would benefit from explicit validation checkpoints, especially around migration deployment and production pushes.
Suggestions
Split content into separate files: move Edge Functions, Storage, CI/CD, and detailed RLS patterns into referenced files (e.g., EDGE_FUNCTIONS.md, STORAGE.md, CI_CD.md) and keep SKILL.md as a concise overview with links.
Add explicit validation checkpoints to the migration workflow, e.g., 'After `supabase db push`, run `supabase migration list` to verify all migrations applied successfully' and error recovery steps.
Remove the Supabase Stack overview table — Claude already knows what these services are; replace with a one-liner like 'Supabase provides Postgres, Auth, Storage, Edge Functions, Realtime, and pgvector.'
Trim the environment variables section — the local vs production distinction and connection pooling details could be moved to a reference file or condensed significantly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill covers a lot of ground efficiently with good use of tables and code blocks, but includes some unnecessary content Claude already knows (e.g., the Supabase Stack table explaining what Auth, Storage, Realtime are) and the environment variables section is somewhat verbose with explanations like 'NEVER expose' that Claude understands. The overall length (~300 lines) is substantial for a single skill file with no bundle support. | 2 / 3 |
Actionability | Excellent actionability throughout — nearly every section includes executable CLI commands, complete SQL examples, working TypeScript code for Edge Functions, and a full CI/CD YAML template. Code is copy-paste ready with realistic examples (RLS policies, triggers, storage buckets). | 3 / 3 |
Workflow Clarity | The migration workflow presents three clear options with numbered steps, and the CI/CD pipeline shows a logical sequence. However, there are no explicit validation checkpoints or feedback loops — for example, after 'supabase db push' there's no verification step, and the diff workflow says 'review generated SQL' but doesn't specify what to check for or what to do if issues are found. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content (~300 lines) covering CLI setup, migrations, RLS, Edge Functions, Storage, CI/CD, and anti-patterns all in one file with no bundle files to offload detail. The Edge Functions section, Storage section, CI/CD template, and detailed RLS patterns could each be separate referenced files. The mention of 'see framework-specific skills' for ORM migrations is the only reference to external content. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
7e5f7a2
- 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.