Backend change
Use when implementing any server-side change in the Laravel app — a controller, service, model, migration, queued job, command, or business rule. Enforces the project's structure, safety, and testing gates.From its SKILL.md
npx -y skills add yousefkadah/laravel-ai-kit --skill backend-changeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, 270 tokens by cl100k_base, as published. Nobody here has run it
Backend change
Before writing
- Read a sibling file in the same area and mirror its structure/naming/idioms.
- Check for an existing service/helper to reuse before adding one.
- For Laravel facts (APIs, signatures, schema), consult Boost — don't guess.
- If the change is more than a small edit, propose a short plan first.
While writing
-
declare(strict_types=1), typed params + return types, promoted constructor props. - Validate in Form Requests; authorize in Policies.
- No N+1 — eager-load. Push slow/external work to queued jobs.
- Multi-tenant: scope every query. A cross-tenant read/write is a security bug, not a nit.
- Use
php artisan make:*for new files. Never run migrations/destructive commands without approval.
Before done
- Add/update tests (happy path + a failure path); run them; paste evidence.
- Run the formatter (
vendor/bin/pint --dirty). - Self-review against
.ai/code-review.md. No secrets in the diff. - Keep the diff tight — no unrelated reformatting.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most data backend skills give in 270 tokens
Counted across 229 of the 229 authors here whose files we hold, read 2026-08-07
- Separate business logic into service layersin 22 of 229, across 15 files
- Retry failures with exponential backoffin 21 of 229, across 14 files
- Select only needed database columnsin 20 of 229, across 13 files
- Abstract data access into repository classesin 19 of 229, across 12 files
- Use centralized error handlersin 17 of 229, across 10 files
- Use AsNoTracking for read-only queriesin 16 of 229, across 4 files
- Use async/await for all I/O operationsin 16 of 229, across 5 files
- Implement structured loggingin 15 of 229, across 4 files
- Use dependency injection for all servicesin 14 of 229, across 2 files
- Use resource-based URLs for REST APIsin 13 of 229, across 7 files
- Invalidate cache after data changesin 13 of 229, across 9 files
- Use a dependency injection containerin 12 of 229, across 4 files
Said here and by no other author read
- mirror structure of a sibling file
- check for existing services before adding
- consult Boost for Laravel facts
- propose a plan for large changes
- declare strict types and typed signatures
- validate in form requests and policies
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.