Summary
Turns web pages into Obsidian notes with automatic project routing. If you run it from inside a git repo or project directory, it drops the page straight into that project's references folder. Otherwise it lands in misc and gets organized later. Built with real trust boundaries: web content is treated as untrusted data, not instructions, so it won't execute commands or follow prompt injections found in scraped pages. Uses defuddle if available to strip ads and navigation bloat before ingestion. Tracks provenance on claims (extracted vs. inferred), checks for duplicates, and handles paywalls gracefully with stubs. Good for building a personal wiki that mirrors your actual work without manual filing.
Install to Claude Code
npx -y skills add ar9av/obsidian-wiki --skill ingest-url --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
