Defuddle logo

Defuddle

CommunityPopular
AgriciDaniel
defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

Overview

PublisherAgriciDaniel
Repositoryclaude-obsidian
Skill namedefuddle
Stars
15K
Forks
1.5K
Bundled files
Instructions only
LicenseMIT
Links
  • 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 AgriciDaniel on GitHub. Read the source before you install it.

Installation

Install the Defuddle 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.
  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/AgriciDaniel/claude-obsidian.git /tmp/claude-obsidian
mkdir -p .claude/skills
cp -r /tmp/claude-obsidian/skills/defuddle .claude/skills/defuddle
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Defuddle 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 Defuddle 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 Defuddle 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.

Defuddle

Treat Defuddle as an optional external extractor, not an internal capability. Cleaning, raw capture, and wiki ingestion are separate operations.

Resolve the installed product root from this skill's own location, never from the selected vault or process working directory:

bash
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"

Every ../wiki/references/ link in this file resolves the same way, relative to this skill's own directory under $PRODUCT_ROOT, never relative to the selected vault's wiki/ directory.

If a separately installed kepano/obsidian-skills defuddle skill is available, prefer it for current CLI flags. Retain the privacy, consent, and transaction rules in this skill.

Safety contract

  • Accept remote inputs only as HTTPS URLs.
  • Reject credentials in URLs, fragments, private or local hosts, non-public IP addresses, control characters, and sensitive query parameters.
  • Never interpolate a URL into a shell string. Pass it as one argv element.
  • Treat redirects to a different host as denied until that host is explicitly approved.
  • State that the URL and request metadata will leave the machine. Network access requires explicit consent in the current request or a separate confirmation.
  • Do not install a cleaner, execute a placeholder runner, or silently switch to another network fetcher.
  • Do not claim a fixed token reduction or extraction quality. Inspect the actual output.

Plan first

Create an inert URL plan. This validates the URL and executes no network call:

bash
python3 "$CORE" capture external-plan url "HTTPS_URL"

Report the normalized host, network egress, redirect policy, optional external dependency, and execute: false. Then inspect whether this package can find a configured Defuddle executable:

bash
python3 "$CORE" contracts --verify --capability defuddle --vault VAULT

An available state means no executable was found; stop with the inert plan. A configured state means the executable was discovered, but this package has no bundled behavioral verifier for it. Show that state and reason, identify the resolved executable path, and require manual review of its provenance, version, and exact argv before execution. Never relabel configured as verified.

When unavailable or when manual review is declined, offer these honest fallbacks: let the user install/configure an external runner, accept a local HTML or Markdown file in inbox/, or leave the URL queued for later. Do not claim that content was cleaned, captured, or ingested.

Execute after consent

After network consent, configured-state detection, and manual executable review, invoke the approved executable with an argv equivalent to:

text
defuddle parse HTTPS_URL --md

Capture bounded stdout in a temporary draft outside shared vault state. Fail closed on a non-zero exit, empty output, unexpected binary output, an unapproved redirect, or a response that is clearly an authentication/error page. Preserve headings, links, code fences, tables, quotations, and source wording; do not invent missing content.

Preview the cleaned Markdown and report extraction limitations. If the user asked only to read or analyze it, keep the result transient.

Optional raw capture

When the user asks to retain the cleaned source:

  1. Resolve the user vault.
  2. Hash the exact cleaned bytes with SHA-256.
  3. Draft a new immutable payload such as .raw/captured/<sha256>.md and, when provenance metadata is needed, a new create-only sidecar with the normalized URL, retrieval date, extractor name and version, and content hash.
  4. Use expected_hashes: null and mode: create. If that content-addressed payload already exists with the same bytes, report a no-op; never overwrite it.
  5. Build, inspect, and apply one claude-obsidian.transaction.v1 capture bundle as described in operation-transactions.md.

Do not create wiki pages, update indexes, assess claims, or mark the source as ingested. Invoke wiki-ingest as a distinct requested operation if the user wants the captured payload incorporated into the knowledge base.

Frequently asked questions

What does the Defuddle AI skill do?

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

Why use Defuddle on TypingMind?

Because you install it once and use it with any model. Defuddle 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 Defuddle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgriciDaniel/claude-obsidian/tree/main/skills/defuddle. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Defuddle?

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 Defuddle?

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

Is the Defuddle AI skill free?

Yes. It is published on GitHub by AgriciDaniel under the MIT license. 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.

View all

Set up your own AI workspace now

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