supabase-automation
Automate Supabase database queries, table management, project administration, storage, edge functions, and SQL execution via Rube MCP (Composio). Always search tools first for current schemas.
64
47%
Does it follow best practices?
Impact
95%
1.75xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/supabase-automation/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description does a good job listing specific Supabase capabilities and naming the tooling mechanism, making it distinctive and specific. However, it lacks an explicit 'Use when...' clause that would help Claude know exactly when to select this skill, and it could benefit from more natural user-facing trigger terms beyond the technical domain vocabulary.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Supabase databases, managing Supabase tables, running SQL on Supabase, or working with Supabase storage/edge functions.'
Include more natural trigger term variations users might say, such as 'create table', 'run query', 'RLS policies', 'Supabase buckets', 'deploy edge function', or 'Supabase project settings'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: database queries, table management, project administration, storage, edge functions, and SQL execution. Also specifies the tooling (Rube MCP/Composio) and a procedural note about searching tools first. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with a list of capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the domain terms. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes good keywords like 'Supabase', 'database queries', 'SQL execution', 'storage', 'edge functions', but misses common user variations like 'create table', 'run query', 'deploy function', 'bucket', or 'RLS policies'. The term 'Rube MCP (Composio)' is technical jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Supabase specifically, with the additional qualifier of using Rube MCP (Composio). This creates a distinct niche that is unlikely to conflict with generic database skills or other cloud platform skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is comprehensive in coverage of Supabase operations but suffers from significant verbosity and redundancy — the same pitfalls and parameter details are repeated multiple times across sections. It provides good structural organization with numbered workflows and clear tool sequences, but lacks concrete invocation examples and validation steps for destructive operations. The entire content is crammed into one monolithic file when much of the reference material should be split out.
Suggestions
Eliminate redundancy by consolidating pitfalls and parameter details into a single reference section (or separate file) instead of repeating them in Core Workflows, Known Pitfalls, Common Patterns, and Quick Reference.
Add at least one concrete example showing a complete tool invocation with sample parameters and expected response shape (e.g., a SUPABASE_SELECT_FROM_TABLE call with specific filters and the returned data structure).
Add explicit validation steps for write operations: after RUN_SQL_QUERY for INSERT/UPDATE/DELETE, include a step to verify affected rows or re-query to confirm the change.
Split the detailed parameter documentation (PostgREST operators, all key parameters per tool) and the quick reference table into a separate REFERENCE.md file, keeping SKILL.md as a concise workflow guide.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose and repetitive. Pitfalls and parameters are duplicated across the 'Core Workflows' sections, the 'Known Pitfalls' section, the 'Common Patterns' section, and the 'Quick Reference' table. The same information about project_ref format, array syntax, case-sensitive identifiers, and error codes appears 2-3 times. Much of the parameter documentation (PostgREST operators, filter syntax) is reference material Claude could discover via RUBE_SEARCH_TOOLS, which the skill itself says to always call first. | 1 / 3 |
Actionability | The skill provides specific tool names, parameter names, and key values, which is concrete guidance. However, there are no executable examples showing actual tool invocations with sample parameters and expected outputs. The guidance is descriptive ('call this tool with these params') rather than showing a concrete example call and response, which would make it fully actionable. | 2 / 3 |
Workflow Clarity | The workflows are clearly sequenced with numbered steps and labeled prerequisites/required/optional annotations. However, for database write operations (INSERT/UPDATE/DELETE via RUN_SQL_QUERY), there are no explicit validation checkpoints or feedback loops — no 'verify the write succeeded' or 'check affected row count' steps. Given these are destructive database operations, the missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files and no references to external documents. All parameter details, pitfalls, patterns, and the full quick reference table are inlined in a single massive file. The extensive parameter documentation and pitfalls sections should be split into separate reference files, with the SKILL.md serving as a concise overview. | 1 / 3 |
Total | 6 / 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
- davepoon/buildwithclaude
- Commit
c911a92
- 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.