agentsclimarketplace

Unopim code review

Skill unopim/agent-skills/skills/unopim-code-review

Agent skills for UnoPim — domain-specific context for AI agents (Claude Code, Cursor, Windsurf) working in an UnoPim PIM codebase. Install: npx skills add unopim/agent-skills

Install
npx -y skills add unopim/agent-skills --skill unopim-code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 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.

What its author says it does

Copied from the file, not written here

Code review for UnoPim. Activates when reviewing code changes, checking standards compliance, flagging violations, or performing PR reviews; or when the user mentions review, standards, conventions, best practices, violations, or code quality.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.4 KB, 695 tokens by cl100k_base, as published. Nobody here has run it

UnoPim Code Review

Review code changes against UnoPim coding standards and conventions.

Critical Violations to Flag

Backend PHP Code

Consult the unopim-backend-dev skill for detailed standards. Flag these violations:

Architecture & Structure:

  • Missing Concord proxy model for new Eloquent models
  • Repository not extending Webkul\Core\Eloquent\Repository
  • Code placed outside the correct packages/Webkul/{Package}/src/ directory
  • Missing interface/contract for new models
  • Direct new Model() instantiation instead of using repository pattern

Naming & Conventions:

  • Class names not in PascalCase
  • Methods/variables not in camelCase
  • Event names not following {domain}.{entity}.{action}.{before|after} pattern
  • Route names not following dot-separated convention
  • Missing namespace declaration

Documentation:

  • Missing docblocks on public/protected methods
  • Missing @param/@return annotations
  • Verbose docblocks (keep concise, one line ideal)
  • Inline comments that narrate what the code does (the code already says it — delete them)
  • Multi-line comment blocks / essays inside a method body (move a genuine why to the PHPDoc, one line)
  • Section-divider comments inside methods (// Views, // Credentials, // ----)

Data Integrity:

  • Missing validation before data modification
  • Using $guarded = [] on models
  • Missing CSRF protection on POST/PUT/DELETE routes
  • Unsanitized user input in queries
  • Missing ACL checks on admin routes

Testing:

  • No tests for new functionality
  • Tests missing beforeEach login setup
  • Missing database assertions (assertDatabaseHas/assertDatabaseMissing)
  • Test not following Pest it()/describe() pattern

Service Provider:

  • Missing route loading in boot()
  • Missing config merges in register() (menu, acl, importers, exporters)
  • Missing migration loading
  • Missing translation/view namespace registration

Frontend Code

  • Missing <x-admin:: component usage (using raw HTML instead)
  • Vue components not following project patterns
  • Missing translations (@lang() / trans())
  • Hardcoded strings in UI — including dropdown placeholder <option> text, title="" tooltips, JS alert/error messages, and "Loading…" / "No results" status text. Every user-visible string must be a translation key (see unopim-backend-dev/coding-conventions.md → "Translations" section)
  • Translation key added to en_US/app.php only — must propagate to all 32 other locales with natural translations (not English copies); verify with php artisan unopim:translations:check showing 100% per locale

Review Approach

  1. Scan for critical violations listed above
  2. Cite specific skill files when flagging issues
  3. Provide correct examples from the skill documentation
  4. Group related issues for clarity
  5. Be constructive — explain why the standard exists

Output Format

For each violation found:

[Issue Type]: [Specific problem]
Location: [File path and line number]
Standard: [Link to relevant skill file]
Fix: [Brief explanation or example]

Gives 0 of the 12 instructions most code review skills give in 695 tokens

Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06

  • push back with technical reasoning if wrongin 60 of 610, across 24 files
  • ask for clarification on unclear itemsin 51 of 610, across 16 files
  • fix critical issues immediatelyin 45 of 610, across 29 files
  • implement one item at a timein 45 of 610, across 11 files
  • group findings by severityin 44 of 610, across 43 files
  • verify feedback against the codebasein 42 of 610, across 8 files
  • dispatch a code reviewer subagentin 39 of 610, across 23 files
  • fix important issues before proceedingin 37 of 610, across 22 files
  • test each fix individuallyin 35 of 610, across 7 files
  • reply in github comment threadsin 33 of 610, across 5 files
  • check for security vulnerabilitiesin 31 of 610, across 27 files
  • factualize corrections without over-explainingin 30 of 610, across 2 files

Said here and by no other author read

  • Use repositories instead of direct model instantiation
  • Place code inside the correct package directory
  • Write class names in PascalCase
  • Keep docblocks concise
  • Delete inline comments narrating code logic
  • Validate data before modification

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.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.