wiki-extract
Skill0 starsChanged 4 months agoMITView on GitHub
Index and routing for source-specific vault extractors (wiki-extract-*). Use to pick which extractor or reference applies to a URL, file, or intent.
- Reads credentials
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- wiki-extract-annasSkill
- wiki-extract-crunchbaseSkill
- wiki-extract-ebookSkill
- wiki-extract-ecommerceSkill
- wiki-extract-githubSkill
- wiki-extract-linkedinSkill
- wiki-extract-newsletterSkill
- wiki-extract-patentsSkill
- wiki-extract-paywallSkill
- wiki-extract-podcastSkill
- wiki-extract-wikipediaSkill
- wiki-extract-youtubeSkill
- wiki-fetchSkill
- wiki-ingestSkill
- wiki-learnSkill
- wiki-lintSkill
- wiki-maintainerSkill
- wiki-onboardSkill
- wiki-pipelineSkill
- wiki-querySkill
- wiki-raw-prepareSkill
- wiki-research-academicSkill
- wiki-research-deepSkill
- wiki-research-feedsSkill
- wiki-research-loopSkill
- wiki-research-newsSkill
- wiki-researchSkill
- wiki-research-socialSkill
- wiki-research-webSkill
- wiki-retroSkill
- wiki-session-memorySkill
- wiki-setupSkill
- wiki-statusSkill
- wiki-upgradeSkill
The file
Files
Wiki extract — index
Vault extractors live as separate wiki-extract-* skills (frontmatter for discovery) plus matching skills/references/wiki-extract-*.md files (full procedures, commands, troubleshooting).
Prefer orchestration skills first: wiki-research and wiki-research-web already route URLs and intents to the right extractor. Use this index when you need the routing table without opening the research skills.
Routing (intent / pattern → skill)
| Intent or URL pattern | Skill | Full procedure |
youtube.com, youtu.be | wiki-extract-youtube | wiki-extract-youtube.md |
| 403 / paywall / Medium / bypass | wiki-extract-paywall | wiki-extract-paywall.md |
Local .epub, .pdf, .mobi, … | wiki-extract-ebook | wiki-extract-ebook.md |
| Anna's Archive, book/paper search | wiki-extract-annas | wiki-extract-annas.md |
| Amazon, eBay, Etsy, Shopify, auctions | wiki-extract-ecommerce | wiki-extract-ecommerce.md |
github.com/... repo, issue, PR | wiki-extract-github | wiki-extract-github.md |
| Substack, Beehiiv, Ghost, Buttondown | wiki-extract-newsletter | wiki-extract-newsletter.md |
linkedin.com/... | wiki-extract-linkedin | wiki-extract-linkedin.md |
crunchbase.com/... | wiki-extract-crunchbase | wiki-extract-crunchbase.md |
*.wikipedia.org/wiki/... | wiki-extract-wikipedia | wiki-extract-wikipedia.md |
| Google Patents, Espacenet, USPTO | wiki-extract-patents | wiki-extract-patents.md |
| Podcast RSS, episode pages | wiki-extract-podcast | wiki-extract-podcast.md |
Environment variables
API keys and optional tools: docs/ENV.md, .env.example, and skills/references/preflight.md (integration table).
Related
- wiki-research / wiki-research-web — primary routing and fetch orchestration
skills/wiki-research/references/approaches.md— URL-level decision tree
Smoke check
CLI and Prompt: Spot-check one reference (e.g. wiki-extract-youtube.md) for terminal lines and Claude Code skill invocation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.