skills.rest
joeseesun
joeseesunCOMMUNITY
Explore all skills by this author →
𝕏@vista8GitHub

content-parser

Extracts and normalizes content from URLs via the MarsWave content extraction API.

335|37|Updated Jul 18, 2026
Search Tags:#markdown#api#web scraping#twitter#content extraction#url parsing#youtube transcript
One-click install
npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill content-parser-joeseesun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: content-parser
Source: https://github.com/joeseesun/qiaomu-cut-skill/tree/main/vendor/marswaveai-skills/content-parser
Command: npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill content-parser-joeseesun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manually copying content from web pages, videos, tweets, and documents is slow and inconsistent. This Skill turns any supported URL into clean, structured markdown content with metadata, ready for downstream use in other generation workflows. ## Core Features & Use Cases - Multi-Platform Extraction: Parses YouTube and Bilibili transcripts, Twitter/X profiles and tweets, WeChat articles, PDF/DOCX documents, images, and general web articles through one API. - Configurable Options: Optionally generate summaries, cap content length, or control how many tweets to fetch (1-100) from a Twitter/X profile. - Structured Output: Saves extracted content as a markdown file plus the full raw API response as JSON in the current working directory. - Use Case: Paste a Wikipedia or WeChat article URL and receive a clean markdown file with title, author, publish date, and references, ready to feed into a podcast or TTS generation skill. ## Quick Start Ask the agent to parse a URL, for example: extract the content from https://en.wikipedia.org/wiki/Topology and save it to the current directory.

Frequently Asked Questions about content-parser

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

FAQPage Schema
How do I extract content from a URL with an API?▼

Submit a POST request to the /v1/content/extract endpoint with the URL in the source.uri field, then poll the returned taskId until the status is completed. The response includes the extracted text, metadata, and references.

What platforms does URL content extraction support?▼

Supported sources include YouTube and Bilibili video transcripts, Twitter/X profiles and single tweets, WeChat public articles, direct PDF and DOCX file URLs, images, and general web articles. Paywalled or JavaScript-heavy pages may extract partially.

How do I fetch a specific number of tweets from a Twitter profile?▼

Pass the profile URL and set options.twitter.count between 1 and 100 in the extraction request body. The default is 20 tweets if the option is omitted.

What API key is required for the MarsWave content extraction API?▼

A LISTENHUB_API_KEY environment variable in the format lh_sk_... is required, sent as a Bearer token in the Authorization header. Keys are obtained from listenhub.ai and require a Pro plan.

Why does content extraction fail for some URLs?▼

Extraction fails when content is paywalled, requires login, relies heavily on JavaScript rendering, or the platform blocks automated access. The API returns a failed status with a failCode such as EXTRACT_FAILED and an error message.

Related Skills

Explore More Content & Communication Skills→
talesofaitalesofai
1

bing-image-search

Extract and validate direct image URLs from Bing image search results.

Official
Advanced
augustsclaugustscl
2

podcast-script-generator

Convert structured podcast notes into presenter-style video scripts.

Community
Intermediate
quaid-appquaid-app
3

quaid-enrich

Store raw API responses and extract structured facts into compiled_truth and timelines.

Official
Advanced
danielrosehilldanielrosehill

scrape-authenticated

Captures paywalled web pages by driving the user's logged-in Chrome via bb-browser.

Community
Intermediate