agentsclimarketplace
Sign in

Trafilatura research

Skill fullREFIT/skills/skills/trafilatura-research

Use Trafilatura for fast extraction of clean article text, metadata, and Markdown from web pages. Best for research corpora, article cleanup, and preparing sources for summaries or retrieval.From its SKILL.md

Install
npx -y skills add fullREFIT/skills --skill trafilatura-research

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

2 things to look at

  • 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 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 file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. 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

1.4 KB, 236 tokens by cl100k_base, as published. Nobody here has run it

Trafilatura Research Extraction

When to use

Use this skill when the task needs clean article text, metadata, or Markdown from public pages, especially for research briefs, corpora, and source cleanup.

Workflow

  1. Check whether trafilatura is installed with scripts/trafilatura_check.py.
  2. Use known URLs from search, last30days, GitHub, or user-provided sources.
  3. Extract main text and metadata.
  4. Preserve the source URL and extraction date.
  5. If extraction fails or returns boilerplate, try Crawl4AI or Firecrawl next.

Strengths

  • Fast and lightweight.
  • Good article extraction quality.
  • Works from Python or CLI.
  • Useful for batch-cleaning research sources.

Caveats

  • Not a browser automation tool.
  • Not a full crawler orchestration framework.
  • Less suitable for app-like pages, heavy JavaScript, or login-gated pages.

Bad output

  • Treating the extracted text as complete without checking for missing sections.
  • Using it for dynamic UI scraping when a browser tool is required.
  • Dropping URLs or metadata from research notes.

What ships with it: 3 files

1.1 KB alongside SKILL.md, 1 of them executable

references/

scripts/

Keep looking

Skills are one crate of 326,758. 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.