Skip to content
TrustedSkillsbeta
Back to all skills

Websh

Checked
openprose·vlatest·other·MIT

Websh extracts structured data from websites into a usable format, streamlining information gathering and analysis for efficiency.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

Installs under a different name. Its SKILL.md names it open-prose, not the name it is listed under, so the command below uses that name.
  1. 1

    Run this in your project

    terminal
    $ npx skills add openprose/prose --skill open-prose -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

openprose

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned openprose/prose at 770cebc9e0.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
770cebc9e0
Manifest
skills/open-prose/SKILL.md
Scanned
60 files, 6,040 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

Websh is a unique "shell for the web," allowing an AI agent to interact with websites as if they were filesystems. It enables navigation and data extraction from webpages using familiar shell commands like cd, ls, grep, and cat. The skill caches webpage content locally, providing instant access and enabling programmatic querying of information on the internet.

When to use it

  • When you want to "browse" or navigate URLs using shell-like commands.
  • To extract specific text content from a webpage.
  • To filter webpage content based on patterns (e.g., searching for keywords).
  • When programmatically querying and analyzing data found on websites.
  • If the user explicitly asks for a "shell for the web" or similar terminology.

Key capabilities

  • URL Navigation: cd <url> to change directories and fetch webpage content.
  • Listing Content: ls [selector] to list links or elements within a page.
  • Content Extraction: cat <selector> to extract text from specific elements.
  • Filtering: grep <pattern> to filter content based on text patterns.
  • History & Bookmarks: Maintains command history and allows saving locations as bookmarks.
  • Intent Inference: Understands natural language commands and variations of formal shell syntax.

Example prompts

Tips & gotchas

  • Websh prioritizes user intent; it will attempt to execute commands even if they aren’t perfectly formatted, avoiding error messages.
  • The skill caches webpages locally for faster access. Use refresh to re-fetch the current page.
  • Refer to the commands.md file for a complete list of available commands and their usage.