backend-dev
Coding practices for backend development in Atomic CRM. Use when deciding whether backend logic is needed, or when creating/modifying database migrations, views, triggers, RLS policies, edge functions, or custom dataProvider methods that call Supabase APIs.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is a strong skill description that clearly defines its scope (backend development for Atomic CRM), lists specific concrete actions (migrations, views, triggers, RLS policies, edge functions, dataProvider methods), and includes an explicit 'Use when' clause with natural trigger terms. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: database migrations, views, triggers, RLS policies, edge functions, and custom dataProvider methods that call Supabase APIs. These are all concrete, identifiable backend development tasks. | 3 / 3 |
Completeness | Clearly answers both what ('Coding practices for backend development in Atomic CRM') and when ('Use when deciding whether backend logic is needed, or when creating/modifying database migrations, views, triggers, RLS policies, edge functions, or custom dataProvider methods that call Supabase APIs'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'backend', 'database migrations', 'views', 'triggers', 'RLS policies', 'edge functions', 'dataProvider', 'Supabase'. These are terms a developer working on this stack would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: backend development specifically for Atomic CRM using Supabase. The combination of project name, technology stack, and specific backend artifacts (RLS policies, edge functions, dataProvider methods) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-scoped skill that efficiently communicates the project's backend architecture decisions and conventions without over-explaining. Its main weaknesses are the lack of executable code examples (especially for edge functions and migrations) and missing validation/verification steps for database operations. Adding a concrete edge function example and a migration workflow with validation checkpoints would significantly improve it.
Suggestions
Add a concrete, executable edge function example showing the full middleware chain pattern (CORS → authenticate → handler) so Claude can copy-paste and adapt.
Include a step-by-step migration workflow with validation checkpoints, e.g., create migration → apply → verify RLS policies → verify trigger attachment.
Add a brief code snippet showing the custom dataProvider method pattern with httpClient for edge function calls.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every sentence carries new, non-obvious information specific to this project's architecture. No explanation of what Supabase, PostgREST, or RLS are—assumes Claude knows. The content is lean and dense with project-specific decisions. | 3 / 3 |
Actionability | Provides concrete patterns (e.g., httpClient URL format, specific migration reference, shared utils path, middleware chain pattern) but lacks executable code examples. The edge function conventions and dataProvider integration are described rather than demonstrated with copy-paste ready snippets. | 2 / 3 |
Workflow Clarity | The decision tree (frontend-only vs view vs edge function) is clear, but there are no explicit validation steps. For database migrations and RLS policies—destructive/batch operations—there's no validate-then-proceed workflow or error recovery guidance. | 2 / 3 |
Progressive Disclosure | References a specific migration (20260108160722) and shared utility files, but doesn't link to any supporting documents. With no bundle files, the skill could benefit from linking to an edge function template or migration example file rather than keeping everything inline. | 2 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- marmelab/atomic-crm
- Commit
bc8fc09
- 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.