What problem does it solve? Web pages often fail to fetch due to 403/429 errors, Cloudflare interstitials, paywalls, or bot detection, leaving you without the content you need. This Skill recovers copies of blocked pages from third-party archive and rendering services instead of giving up or looping on the same URL. ## Core Features & Use Cases - Fallback Ladder: Tries recovery routes cheapest-first — Wayback Machine, archive.today domain rotation, Jina Reader (with JINA_API_KEY), then an API-first pivot to /api/, /graphql, or RSS endpoints. - Fake-Success Detection: Validates every recovered body with byte floors, interstitial-title rejection, and redirect-stub detection so dead Google Cache pages, AMP stubs, and rate-limit HTML are never mistaken for real content. - Provenance Discipline: Labels every result as snapshot or live so archived copies are always cited with their timestamp and never presented as current data. - Use Case: A news article returns a paywall or Cloudflare "Just a moment..." page. Run the bundled script to pull the archived copy from Wayback or archive.today, with its snapshot date preserved for citation. ## Quick Start Ask the agent to recover the blocked article at a given URL using the blocked-page-recovery script and report which route succeeded with its provenance.
