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.
67
51%
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-related capabilities and is clearly distinguishable from other skills due to its platform-specific focus. However, it lacks an explicit 'Use when...' clause that would help Claude know exactly when to select this skill, and could benefit from more natural user-facing trigger terms beyond the technical nomenclature.
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 and edge functions.'
Include more natural trigger term variations users might say, such as 'create table', 'run query', 'Supabase project', 'RLS', 'row level security', 'storage bucket', or 'deploy edge function'.
| 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 includes 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 (Supabase). 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/row level security'. The term 'Rube MCP (Composio)' is technical jargon unlikely to appear in user requests. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Supabase specifically, with distinct triggers like 'Supabase', 'edge functions', and 'Composio'. This is unlikely to conflict with generic database or SQL skills due to the platform-specific focus. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%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 covering Supabase operations via Rube MCP but suffers significantly from verbosity and repetition—pitfalls and parameter details are duplicated across sections. It provides good workflow sequencing but lacks validation checkpoints for destructive database operations and concrete executable examples of tool invocations. The content would benefit greatly from splitting detailed parameter references and pitfalls into separate files.
Suggestions
Eliminate duplicated pitfalls by consolidating them into a single 'Known Pitfalls' section and removing inline repetitions from each workflow section.
Add concrete tool invocation examples showing actual parameter values (e.g., a sample RUBE_SEARCH_TOOLS call followed by a SUPABASE_SELECT_FROM_TABLE call with realistic parameters).
Add explicit validation steps for write workflows: verify schema before writes, use read_only:true SELECT to confirm results after mutations, and include error recovery guidance.
Move detailed parameter lists (filter operators, all key parameters per tool) into a separate REFERENCE.md file and keep only the most essential parameters inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose and repetitive. Pitfalls are duplicated across the 'Core Workflows' sections and again in the 'Known Pitfalls' section. Parameter details that Claude could discover via RUBE_SEARCH_TOOLS are exhaustively listed inline. The document also appears to contain corrupted/duplicated content (the rubric itself is embedded multiple times within the skill content). | 1 / 3 |
Actionability | The skill provides specific tool names, parameter names, and clear tool sequences for each workflow, which is concrete guidance. However, there are no executable code examples or copy-paste ready invocations showing actual tool calls with sample parameters, and the guidance remains at the level of describing what tools to call rather than showing exact invocation patterns. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps and labeled prerequisites/required/optional annotations. However, for database write operations (destructive SQL via RUN_SQL_QUERY), there are no explicit validation checkpoints or feedback loops (e.g., verify schema before write, confirm results after write, rollback on error). The rubric requires this to cap at 2. | 2 / 3 |
Progressive Disclosure | The content has good section structure with headers and a quick reference table, and links to external toolkit docs. However, the massive amount of inline parameter details, filter operators, and repeated pitfalls sections should be split into separate reference files rather than kept in the main SKILL.md, making it a monolithic document that could benefit from better content splitting. | 2 / 3 |
Total | 7 / 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
7cc63f3
- 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.