Update to Context.dev

{
  "name": "context-dev",
  "description": "Use Context.dev for tasks that need live public-web or document data: web search; scraping known URLs to Markdown, HTML, or images; sitemap discovery and crawling; schema-based extraction; PDF and Office parsing; company logos, colors, socials, and industry; website style guides, fonts, screenshots, monitoring, or large URL batches. Trigger even when Context.dev is not named. Do not trigger for questions answerable from supplied text, private account data, or tasks that need no web or file retrieval.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 512
    }
  ],
  "skill_md_contents": "---\nname: context-dev\ndescription: \"Use Context.dev for tasks that need live public-web or document data: web search; scraping known URLs to Markdown, HTML, or images; sitemap discovery and crawling; schema-based extraction; PDF and Office parsing; company logos, colors, socials, and industry; website style guides, fonts, screenshots, monitoring, or large URL batches. Trigger even when Context.dev is not named. Do not trigger for questions answerable from supplied text, private account data, or tasks that need no web or file retrieval.\"\n---\n\n# Context.dev\n\nUse the connected Context.dev tools to retrieve current public web and file data. Prefer the smallest tool that directly produces the requested result.\n\n## Choose the right tool\n\n- Use `web-search` when the user needs current information and does not provide the exact source URL.\n- Use `web-scrape-markdown` to read, summarize, or analyze one known URL.\n- Use `web-scrape-html` only when raw DOM structure, attributes, scripts, or markup are required.\n- Use `web-scrape-images` to discover image assets and `web-screenshot` for a rendered page image.\n- Use `web-scrape-sitemap` to discover or search a site's URLs without fetching every page body.\n- Use `web-crawl` for a focused set of linked pages when results are needed synchronously.\n- Use `web-extract` when the user wants structured fields such as products, pricing, jobs, locations, or company facts.\n- Use `parse-document` for PDFs, presentations, spreadsheets, documents, images, code, data, and text files.\n- Use `get-brand` for a visual brand profile from a domain. Use `brand-retrieve-unified` for raw structured brand data or lookups by name, email, ticker, ISIN, transaction descriptor, or direct URL.\n- Use `web-styleguide` and `web-fonts` to inspect a site's visual system and typography.\n- Use `web-naics` or `web-sic` for industry classification.\n- Use the monitor tools for recurring change detection. Use the batch tools for large asynchronous jobs or many URLs.\n\n## Work effectively\n\n1. When the exact URL is known, use the corresponding scrape or extract tool instead of searching first.\n2. For current facts, use live web tools and retain the source URLs in the answer.\n3. For structured extraction, define the narrowest schema that matches the user's requested fields. Do not invent missing values.\n4. For large jobs, call `submit-batch`, then use `get-batch` and `get-batch-results`. A successful submission is not a completed job.\n5. For monitor requests, inspect existing monitors when useful and confirm the intended target, schedule, and change criteria before creating or changing one.\n6. Treat browser actions, monitor mutations, and batch mutations as side-effectful. Only perform them when the user has clearly requested that action.\n7. If authentication fails, tell the user to connect or reconnect Context.dev through OAuth. Do not fabricate results or silently substitute stale data.\n\n## Match common requests\n\nInvoke Context.dev for requests such as:\n\n- \"find the latest official announcements about this company\"\n- \"summarize this page\" or \"turn this URL into Markdown\"\n- \"extract every pricing plan as JSON\"\n- \"parse this research paper or presentation\"\n- \"get this company's logo, colors, socials, and industry\"\n- \"find all documentation pages about authentication\"\n- \"watch this page for meaningful pricing changes\"\n- \"scrape these hundreds of URLs and give me the results\"\n\nDo not invoke Context.dev when the answer is already present in user-provided content, the task concerns private workspace data from another connected service, or no public web or file retrieval is required.\n"
}