qa-detect-content-patterns

Scan visible web page text for typos, untranslated keys, and readability issues.

Updated May 22, 2026
One-click install
npx skills add https://github.com/Luqman-Ud-Din/blackbox-qa-agent --skill qa-detect-content-patterns
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa-detect-content-patterns
Source: https://github.com/Luqman-Ud-Din/blackbox-qa-agent/tree/main/skills/qa-detect-content-patterns
Command: npx skills add https://github.com/Luqman-Ud-Din/blackbox-qa-agent --skill qa-detect-content-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of inconsistent, low-quality, or obviously broken on-screen content by deterministically scanning visible text for common copy defects that are hard to trust to a purely generative review.

Core Features & Use Cases

  • Deterministic content QA: Flags typos, pluralization issues, untranslated keys, HTML entities, markdown literals, mojibake, placeholder text, developer markers, long sentences, and weak CTA copy.
  • Candidate extraction for deeper review: Surfaces homophone and suspicious spelling candidates for a second-layer judgment pass so content QA stays both broad and reliable.
  • Readability and consistency checks: Detects doubled words, spacing issues, mixed spelling variants, and brand casing inconsistencies across visible page text.
  • Use case: Run this on product pages, dashboards, forms, and localized UIs before release to catch user-facing text defects that would otherwise leak into production.

Quick Start

Use the qa-detect-content-patterns skill to scan the current page for visible content defects and return a deterministic list of findings.

Frequently Asked Questions about qa-detect-content-patterns

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

FAQPage Schema
How do I scan my web page DOM for untranslated keys and placeholder leaks?

To scan web page DOM for untranslated keys and placeholder leaks, inspect visible text deterministically with lang-aware filtering. This process flags raw translation markers, developer placeholders, and HTML entities that leaked into user-facing interfaces before release.

What is the best way to automate copy review for localized UI text at scale?

Automating copy review for localized UI text at scale requires deterministic DOM text inspection combined with brand whitelisting. This approach catches mojibake, untranslated keys, and mixed spelling variants across product pages and dashboards reliably.

Can I detect readability problems and weak CTA copy using deterministic content QA?

Deterministic content QA detects readability problems and weak CTA copy by scanning visible page text for long sentences, doubled words, and spacing issues. It ensures text quality is validated without relying on purely generative review.

How do I extract suspicious spelling and homophone candidates for follow-up review?

Extract suspicious spelling and homophone candidates for follow-up review by applying bounded candidate extraction during DOM scanning. This surfaces potentially misspelled words for a second-layer judgment pass, keeping content QA broad yet reliable.

Does content QA work with brand whitelisting and lang-aware filtering for localized screens?

Content QA works effectively with brand whitelisting and lang-aware filtering for localized screens. This combination ignores approved brand casing terms while deterministically isolating untranslated keys and mojibake in user-facing interfaces.

Why should I use deterministic DOM scanning instead of generative review for content defects?

Deterministic DOM scanning is preferred over generative review for content defects because it reliably flags exact copy inconsistencies, typos, and markdown literals. It provides bounded, verifiable results rather than unpredictable AI-generated judgments.