defuddlelisted

# /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 one of 100 in [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 Alt