Awesome-omni-skill WebText

Fetch a web page (single URL) and return readable plain text extracted from HTML.

install

source · Clone the upstream repo

git clone https://github.com/diegosouzapw/awesome-omni-skill

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/development/webtext" ~/.claude/skills/diegosouzapw-awesome-omni-skill-webtext && rm -rf "$T"

manifest: skills/development/webtext/SKILL.md

source content

Use this skill when the user wants the plain text of a referenced web page.

How to run:

Use the Exec Tool to run the Python script in this skill folder.
The script prints a JSON object to stdout: { url, chars, text }

Install deps (once, on the host):

python -m pip install -r "{baseDir}/requirements.txt"

Command template (Windows-friendly):

python "{baseDir}/WebText.py" --url "<URL>" --max-chars 20000 --timeout-ms 15000

Return the JSON stdout to the user. If the request fails (HTTP error, timeout, unsupported content-type), return the error message.