TypingMindTypingMindThe best frontend for AI
Webarchive logo

Webarchive

Community
robrohan
webarchive

Extract .webarchive files (saved from Safari) into plain HTML/assets using the WebArchiveExtractor CLI. Use when the user wants to unarchive, extract, or convert a .webarchive file.

Overview

Publisherrobrohan
RepositoryWebArchiveExtractor
Skill namewebarchive
Stars
346
Forks
60
Bundled files
Instructions only
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by robrohan on GitHub. Read the source before you install it.

Installation

Install the Webarchive AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/robrohan/WebArchiveExtractor/tree/master/skills/webarchive
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/robrohan/WebArchiveExtractor.git /tmp/WebArchiveExtractor
mkdir -p .claude/skills
cp -r /tmp/WebArchiveExtractor/skills/webarchive .claude/skills/webarchive
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Webarchive in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Webarchive on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Webarchive is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

The user wants to extract a .webarchive file using WebArchiveExtractor.

If arguments were provided ($ARGUMENTS), use them to infer the input file and optionally the output directory or URL prepend. Otherwise, ask the user for the path to the .webarchive file.

How to run WebArchiveExtractor

/Applications/WebArchiveExtractor.app/Contents/MacOS/WebArchiveExtractor [-h] [-o <OutputDirectory>] [-p <URLPrepend>] -i <WebArchiveFile>

Options:

  • -i <WebArchiveFile> — required — path to the .webarchive file
  • -o <OutputDirectory> — directory to write extracted files into (optional; defaults to a directory named after the archive next to it)
  • -p <URLPrepend> — URI prefix to prepend to all asset URLs in the extracted HTML (optional; useful when serving the result from a subdirectory)

Shorthand (no flag):

WebArchiveExtractor website.webarchive

A positional argument is treated as the -i value.

Prerequisites

The app must be installed at /Applications/WebArchiveExtractor.app. Check with:

sh
test -x /Applications/WebArchiveExtractor.app/Contents/MacOS/WebArchiveExtractor && echo "found" || echo "not installed"

If not found, tell the user to build and install from source (xcodebuild -project WebArchiveExtractor.xcodeproj) or drag a release build to /Applications.

To use WebArchiveExtractor without the full path, the user can add it to PATH:

sh
export PATH="$PATH:/Applications/WebArchiveExtractor.app/Contents/MacOS/"

Or create a symlink:

sh
ln -s /Applications/WebArchiveExtractor.app/Contents/MacOS/WebArchiveExtractor ~/.local/bin/WebArchiveExtractor

Steps

  1. Check the binary exists using the test command above. If not found, stop and direct the user to install the app.
  2. Determine the input .webarchive file from $ARGUMENTS or ask the user.
  3. Determine the output directory:
    • If the user explicitly provided one in $ARGUMENTS, use that.
    • Otherwise, default to ~/Downloads/<archive-name> (where <archive-name> is the input filename without the .webarchive extension).
    • If the user asks why ~/Downloads is the default, explain: macOS sandboxes the WebArchiveExtractor app, which restricts which directories the CLI can write to. The ~/Downloads folder is one of the few locations reliably accessible, so it's used as the default to avoid silent failures.
  4. Determine (optional) URL prepend from $ARGUMENTS or ask if needed.
  5. Run the extractor using the Bash tool: 
    sh
    /Applications/WebArchiveExtractor.app/Contents/MacOS/WebArchiveExtractor -i "<input>" -o "<output>" [-p "<prepend>"]
  6. If successful, list the output directory contents with ls and summarise:
    • The output directory path
    • How many files were extracted
    • The main HTML file name (if identifiable)
  7. Offer to open the extracted HTML in the browser with open <file>.

Notes

  • .webarchive is a macOS-specific binary plist format used by Safari's "Save As Web Archive" feature.
  • The CLI and the GUI app are the same binary — running with -i suppresses the GUI.
  • Running with no arguments launches the GUI instead of extracting anything.

Frequently asked questions

What does the Webarchive AI skill do?

Extract .webarchive files (saved from Safari) into plain HTML/assets using the WebArchiveExtractor CLI. Use when the user wants to unarchive, extract, or convert a .webarchive file.

Why use Webarchive on TypingMind?

Because you install it once and use it with any model. Webarchive is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Webarchive in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/robrohan/WebArchiveExtractor/tree/master/skills/webarchive. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Webarchive?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Webarchive?

As many as you like. As long as a model supports skills, you can use Webarchive with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Webarchive AI skill free?

It is published on GitHub by robrohan. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Openclaw Ci Limits

openclaw
OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

82.2K
391K
1 files
View
openclaw logo

Openclaw Debugging

openclaw
OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

82.2K
391K
1 files
View
openclaw logo

Openclaw Docker E2e Authoring

openclaw
OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

82.2K
391K
Instructions
View
openclaw logo

Openclaw Ghsa Maintainer

openclaw
OrganizationPopular

Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.

82.2K
391K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇