defuddle
/defuddle
Turn an article URL into a clean, vault-ready markdown note with the defuddle CLI, stripping ads, navigation and comments and cutting 40-60% of tokens versus a raw fetch. Prefer it over a raw web fetch whenever the task is reading or ingesting a normal web article. Triggers: "/defuddle <url>", "clean import this page".
- Author
- tonydzi ↗
- Repository
- second-brain-starter-kit ↗
- Licence
- MIT
- Last repository change
- 24.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 1
- URLs in SKILL.md
- 7
No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.
What it does and when to use it
Turn an article URL into a clean, vault-ready markdown note with the defuddle CLI, stripping ads, navigation and comments and cutting 40-60% of tokens versus a raw fetch. Prefer it over a raw web fetch whenever the task is reading or ingesting a normal web article. Triggers: "/defuddle <url>", "clean import this page".
Triggers from the description
Original author description
Turn an article URL into a clean, vault-ready markdown note with the defuddle CLI, stripping ads, navigation and comments and cutting 40-60% of tokens versus a raw fetch. Prefer it over a raw web fetch whenever the task is reading or ingesting a normal web article. Triggers: "/defuddle <url>", "clean import this page".
How it works
- Commands
- The "article into the vault" flow
- ⚠️ Gotchas (verified by a live /tt run, 2026-07-04)
- When NOT to use defuddle
SKILL.md preview
---
name: defuddle
description: >-
Turn an article URL into a clean, vault-ready markdown note with the defuddle CLI, stripping
ads, navigation and comments and cutting 40-60% of tokens versus a raw fetch. Prefer it over a
raw web fetch whenever the task is reading or ingesting a normal web article. Triggers:
"/defuddle <url>", "clean import this page".
license: MIT
---
# /defuddle — clean web→markdown
The `defuddle` CLI (by kepano, MIT, v0.19.1) is installed globally via npm. Node is the only dependency.
## Commands
```bash
# article → clean markdown on stdout
defuddle parse <url> --markdown
# with frontmatter (title/author/published/domain) — for the vault
defuddle parse <url> --markdown --frontmatter
# straight to a file
defuddle parse <url> --markdown --frontmatter --output "<path>.md"
```
## The "article into the vault" flow
1. `defuddle parse <url> --markdown --frontmatter` → draft.
2. Then the standard ingest: a vault note (provenance `origin: external`!), reindex, ≥1 inbound link (rules `always-archive-artifacts-to-vault`, `no-orphan-notes-rule`).
## ⚠️ Gotchas (verified by a live /tt run, 2026-07-04)
- **exit code = 0 even on failure** ("Error: fetch failed" is printed, but the code says success). In scripts, check stdout for `^Error:`, NOT the exit code.
- Empty input → a cryptic destructure error (also exit 0).
- The CLI is machine-local: on another machine run `npm install -g defuddle` first (node required). The skill syncs across the cluster; the binary does not.
## When NOT to use defuddle
A `.md` URL → fetch it directly; JS-heavy SPAs, paywalls, logins → a regular web fetch or live-browser automation.
<!--kit-footer-->
---
**Like this skill?** It is part of [second-brain-starter-kit](https://github.com/tonydzi/second-brain-starter-kit): the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with `npx skills add tonydzi/second-brain-starter-kit`. Everything is open source and free, so take what you need.
Flagships worth a look on their own: [secondop-panel](https://github.com/tonydzi/secondop-panel) (a second opinion from a panel of external models), [claude-memory-tidy](https://github.com/tonydzi/claude-memory-tidy) (stop your agent's memory from rotting), [telegram-mcp-kit](https://github.com/tonydzi/telegram-mcp-kit) (your own Telegram over MCP in about 15 minutes).
Author: **Anton Dziatkovskii**, Palo Alto AI Research Lab. Telegram [@tonydzi](https://t.me/tonydzi) - WhatsApp [+1 341 222 9178](https://wa.me/13412229178) - X [@Tony_Stef_](https://x.com/Tony_Stef_)
**Engineers: want to test-drive this setup?** Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · tonydzi/second-brain-starter-kit | 100 | MIT |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| pantheon-org/tekhne | 100 | MIT |
| galyarderlabs/galyarder-framework | 100 | MIT |
| galyarderlabs/galyarder-framework | 100 | MIT |
| LiHongwei-cn/lihongwei-cn | 100 | MIT |
| yeaight7/agent-powerups | 100 | Apache-2.0 |
| pinkpixel-dev/skills-collection-1 | 100 | Apache-2.0 |
| agricidaniel/claude-obsidian | 95 | MIT |
Database snapshot: 13.11.2026 · package version f0b4e495a827 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100baoyu-url-to-markdown
Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle… - 100baoyu-url-to-markdown
Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle… - 100web-to-markdown
Convert a web URL into cleaned Markdown with deterministic routing. Use when Codex needs to read article-like content from links and should apply source-aware fetch strategies: default to r.jina.ai for general pages (including X/Twitter), use defuddle.md for YouTube links, and… - 100web-read
Extract clean, readable markdown from a web page with the Defuddle CLI — strips nav, ads, and boilerplate to cut tokens versus WebFetch. Use when given a URL to read or analyze (docs, articles, blogs, changelogs, RFCs). Do NOT use for .md or JSON/API URLs — use WebFetch directly. - 95knap
Render Markdown from templates and structured data using Knap CLI. Use when the user asks to apply a Knap template, turn JSON or CSV data into notes, batch-generate Markdown files, or format Defuddle output into a note. - 100blog-post
This skill should be used when the user shares a blog/article URL (Medium, Substack, personal blog, news/long-form post) and asks to "download this blog post", "save this article", "archive this post with images", "clip this medium article", or otherwise wants a self-contained…