agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/defuddle/SKILL.md

defuddle

Skill6 starsChanged 2 months agoMITView on GitHub

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".

  • Installs packages

62 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, knap and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • lucasmaher-hashSkill

    knap

    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.

    Also in 4 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 3 projects that use this

  • az9713Skill

    vault-health

    Audit vault health: unresolved links, orphan notes, dead-end files, missing frontmatter, structural gaps. Produces an actionable report note with prioritized fix suggestions. Use when wanting to clean up, organize, or assess the current state of the vault.

    Also in 3 projects that use this

  • +2 more from Clay-HHK

The file

Create a free account to mount
Files
SKILL.md

/defuddle — clean web→markdown

The defuddle CLI (by kepano, MIT, v0.19.1) is installed globally via npm. Node is the only dependency.

Commands

# 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 one of 100 in 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 (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free