What problem does it solve? Web fetches frequently fail with 403/429 errors, paywalls, Cloudflare interstitials, or bot-detection walls, leaving you without the content you need. This Skill recovers copies of blocked pages from third-party archives and rendering services instead of retrying the same blocked URL. ## Core Features & Use Cases - Ordered recovery ladder: Tries Wayback Machine first, then archive.today domain rotation, then Jina Reader (when JINA_API_KEY is set), with an API-first pivot and real browser as last resorts. - Fake-success detection: Validates every response body against byte floors, interstitial titles, and redirect stubs so dead ends like Google Cache and AMP caches are never mistaken for real content. - Provenance tracking: Labels every result as a dated snapshot or live render so citations correctly reflect whether content is archived or current. - Use Case: A news article returns a paywall. Run the bundled script with the URL to get the first genuine archived copy, its snapshot timestamp, and guidance on how to cite it. ## Quick Start Ask the agent to recover the blocked article at a given URL using the recovery script and report which archive route succeeded with its snapshot date.
