skills.rest
wagnerra23
wagnerra23COMMUNITY
Explore all skills by this author →
GitHub

pr-ui-judge-manual

Evaluate GitHub pull request UI quality against Constituição UI v2.

Updated May 14, 2024
Search Tags:#semantic review#github pull request#pr ui judge#constitution ui v2#laravel ui testing#llm-based validation
One-click install
npx skills add https://github.com/wagnerra23/oimpresso.com --skill pr-ui-judge-manual
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pr-ui-judge-manual
Source: https://github.com/wagnerra23/oimpresso.com/tree/main/.claude/skills/pr-ui-judge-manual
Command: npx skills add https://github.com/wagnerra23/oimpresso.com --skill pr-ui-judge-manual

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of getting trustworthy, semantic UI quality feedback on a specific GitHub PR without turning on the full CI workflow budget every time.

Core Features & Use Cases

  • Manual UI judge invocation: Run the canônico command to evaluate a PR against Constituição UI v2 when Wagner asks for PR scoring, semantic review, or a slash-invoke request.
  • Semantic, not just syntactic, validation: Detect UI violations like drawer modal layering, custom slot invention, PT-01 layout breaches even when components look correct, duplicated shortcuts, and wrong semantic copy tone.
  • Actionable review outputs: Produce a JSON scoring payload with verdict and structured lists of violations and suggestions; optionally post comments or run in strict CI-like mode.

Quick Start

Run the judge on PR 1438 and post the results as a PR comment.

Frequently Asked Questions about pr-ui-judge-manual

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a semantic UI review on a GitHub pull request without enabling CI?▼

Run a semantic UI review on a GitHub pull request by executing the php artisan ui:judge-pr command with the target PR number. This evaluates the PR against Constituição UI v2 and outputs a verdict without activating the full CI workflow budget.

What kind of UI violations does an LLM-based semantic PR review detect?▼

An LLM-based semantic PR review detects UI violations including drawer modal layering issues, custom slot invention, PT-01 layout breaches, duplicated shortcuts, and incorrect semantic copy tone, even when components appear syntactically correct.

How do I post a semantic UI scoring result as a comment on a GitHub PR?▼

Post semantic UI scoring results as a GitHub PR comment by running the php artisan ui:judge-pr command with the PR number and enabling the optional flag for posting comments to the repository.

Does manual UI judge execution support strict verdict behavior for CI-like validation?▼

Manual UI judge execution supports strict verdict behavior through an optional command flag. This allows the semantic review to enforce CI-like validation rules against Constituição UI v2 during an ad-hoc run.

Can I save the semantic UI review output as a JSON scoring payload?▼

Save the semantic UI review output as a JSON scoring payload by using the optional save flag when executing the php artisan ui:judge-pr command. The resulting file contains the verdict alongside structured lists of violations and suggestions.

Related Skills

Explore More Software Engineering Skills→
RaiderIORaiderIO
66

seeder-save

Integrate new models and child relations into the mapping:save Artisan command.

Official
Intermediate
yiminllinyiminllin
1

pr-address-comments

Triage unresolved GitHub PR review comments and draft in-thread replies.

Community
Intermediate
changgengluchanggenglu

laravel-coding-standard

Enforce Laravel coding standards for naming, arrays, validation, and enums.

Community
Intermediate
luisgustavooliveiraluisgustavooliveira

land-and-deploy

Automate pull request merge, CI, deploy, and canary health checks.

Community
Advanced