Semantic Landmark Evidence Auditor

ARIA Label Accessibility Auditor

junipr/aria-label-accessibility-auditor

Audit accessible-name signals from visible text, ARIA attributes, labels, alt text, and titles in public HTML.

Check public HTML pages for basic accessibility signals: language, headings, image alt text, form labels, link text, ARIA landmarks, risks, and evidence.

Semantic Scholar Search Scraper

powerai/semantic-scholar-search-scraper

Scrape academic papers from Semantic Scholar by keyword search, with automatic pagination and comprehensive research data extraction.

Heading Outline Evidence Auditor

gifted_wagon/heading-outline-evidence-auditor

Extract H1-H6 structure, text, anchors, order gaps, duplicate headings, and accessible outline evidence for public pages.

Semantic Scholar Paper Search

ryanclinton/semantic-scholar-search

Search and extract academic research papers from Semantic Scholar's database of over 200 million publications.

"Enrich public GitHub repository URLs with stars, forks, topics, license, activity, owner metadata, release data, and lead-scoring signals. Built for B2B lead generation, devtools research, and competitive intelligence."

Semantic Changelog Generator

fiery_dream/semantic-changelog-generator

Generate beautiful changelogs from git commits using Conventional Commits. Automatic semantic versioning, categorized changes, and professional release notes. Simpler alternative to semantic-release.

Semantic Scholar Scraper

parseforge/semantic-scholar-scraper

Scrapes academic papers from Semantic Scholar search results. Returns each paper as a flat row with title, authors, year, citations, venue, and abstract. Supports year and PDF filters.

Xiaohongshu Topic Semantic & Content Opportunity Radar

scrupulous_buckler/xiaohongshu-topic-semantic-content-opportunity-radar

Turn RedNote topic searches into related terms, semantic clusters, trend velocity, brand penetration, top and latest content, and evidence-linked content whitespace.

AI Website & PDF Extractor — RAG JSON

pagelytix/Pagelytix

Extract structured, AI-ready JSON from websites and PDFs including clean text, metadata, schema, DOM elements, semantic sections, links, social media links, and chunks for LLMs, RAG pipelines, embeddings, and semantic search.