Update to Unblocked

{
  "name": "unblocked-context-get-urls-mcp",
  "description": "Loads full content for known pull request, issue, document, message, and public web URLs with the context_get_urls MCP tool. Use when the user supplies URLs or a prior search returns URLs that need full-text review. Use context_research when the URL is not known. Do not use for local files or private network URLs.\n",
  "included_files": [],
  "skill_md_contents": "---\nname: unblocked-context-get-urls-mcp\ndescription: >\n  Loads full content for known pull request, issue, document, message, and public\n  web URLs with the context_get_urls MCP tool. Use when the user supplies URLs or\n  a prior search returns URLs that need full-text review. Use context_research\n  when the URL is not known. Do not use for local files or private network URLs.\n---\n\n# Unblocked URL retrieval for MCP\n\nUse `context_get_urls` when you already know which documents to load. The tool\ncan resolve content through configured private connectors and public web pages.\n\n## Tool use\n\nCall the `context_get_urls` MCP tool directly. Pass `urls` as an array.\n\nIf the tool is not available, tell the user that Unblocked is not configured in\nthis environment. Do not use a generic web fetch for private GitHub, Jira,\nLinear, Slack, Notion, or other connector content.\n\n## When to use it\n\nUse this skill when:\n\n- The user provides one or more URLs to summarize or analyze.\n- `context_research` returns URLs and the snippets are not enough.\n- A known pull request, issue, document, or message must be checked again.\n- Several related source URLs need one combined review.\n\nUse `context_research` when you must find the URL first.\n\n## Input\n\n| Parameter | Required | Use |\n|:---|:---|:---|\n| `urls` | Yes | An array of complete `http://` or `https://` URLs. |\n\nGood inputs include direct links to pull requests, issues, Slack threads,\nConfluence or Notion pages, and public web pages.\n\nDo not pass:\n\n- `localhost` or `127.0.0.1`\n- Private network addresses\n- `file://` URLs\n- URLs without an `http://` or `https://` scheme\n- Session URLs that depend on browser cookies\n\n## Check support\n\nConnector support differs by organization. Inspect the live\n`context_get_urls` tool description when you need to confirm supported URL\npatterns. If a URL does not match a listed pattern, tell the user that its\nconnector or organization might not be configured.\n\n## Batch related URLs\n\nSend a related set of URLs in one call. A batch of about 5 to 10 URLs is a good\ndefault. Split larger or unrelated sets to reduce timeouts and oversized output.\n\nKeep the original URL with each finding. This makes the source easy to check and\ncites the correct item when a batch contains similar documents.\n\n## Work with results\n\n- Check for empty content, login pages, and authorization errors before you use\n  the result as evidence.\n- Treat issue and pull request status as live at retrieval time.\n- Do not assume pull request content includes the full diff.\n- Use local repository tools when the task needs code changes or exact diff\n  inspection.\n- State which URL failed and why when only part of a batch resolves.\n\n## Limits\n\n- Skip retrieval when the available snippet already answers the question.\n- Do not use this tool for local files or private network resources.\n- Do not guess at content when a connector is missing or authorization fails.\n"
}