Update to Kapa

{
  "description": "Set up a Kapa Discourse source so a public forum is ingested. Use when the user wants Kapa to answer from their Discourse community forum.",
  "included_files": [],
  "name": "kapa-setup-discourse",
  "skill_md_contents": "---\nname: kapa-setup-discourse\ndescription: Set up a Kapa Discourse source so a public forum is ingested. Use when the user wants Kapa to answer from their Discourse community forum.\n---\n\n# Set up Discourse\n\nThe simplest community source: a public forum needs no credential at all.\n\n## 1. Create the source\n\n`create_discourse_source` with `project` and `name`. Keep the returned id.\n\n## 2. Check the forum and list what it holds\n\n`validate_discourse_url` with `url` confirms the forum is reachable\nanonymously. A failure means it is login-walled, and there is no credential\nhere to fix that.\n\n`list_discourse_categories` and `list_discourse_tags` then show the real\noptions to offer the user. An empty tag list means the forum has tagging\nturned off, so filter by category instead.\n\n## 3. Configure it\n\n`set_discourse_config` with `source_discourse` and `url`, the base URL of the\nforum, such as `https://forum.acme.com`.\n\nAsk which parts of the forum to read. `match_categories` and `match_tags`\ntake what the user picks, and leaving both out reads every topic. Use\n`list_discourse_categories` and `list_discourse_tags` to show them the real\noptions.\n\nPass categories by **name or slug**, never by numeric id. An id matches\nnothing, and ingestion then drops the category filter and reads the whole\nforum.\n\n## Getting good answers out of it\n\nForum threads contain wrong answers as well as right ones, so ask the user\nhow to handle that:\n\n- `include_solved_only`: keep only topics with an accepted answer, or take\n  every topic. Check first whether their forum marks solutions at all, since\n  this filter leaves nothing on a forum that does not.\n\n## When it ingests nothing\n\nThe forum is not public, or `include_solved_only` is on for a forum that does\nnot mark accepted answers.\n\n## Finish the job\n\nSaving the configuration starts ingestion. There is no separate publish step,\nso once the config saves the source is live.\n\nThen call `list_sources` with `project_id` to confirm what the project holds.\n\n## Shared Kapa workflow rules\n\nTools act as the connected user with that user's project permissions. Resolve the intended project and use only authorized data. Do not invent credentials, source IDs, filters, or tool results. Check the available tool schema before passing arguments.\n\nExplain and obtain approval for ingestion and its quota cost before saving a configuration that starts ingestion or calling `start_crawl`; existing explicit approval for that exact action is sufficient. Ask the user to choose source scope and filters. Validate credentials and discover accessible content before saving. Keep credentials out of visible results, logs, and exported artifacts. Use a secure credential input if the host provides one.\n\nFor a web source, preview the exact configuration and inspect the extracted article content before ingestion. Report queued, running, failed, and completed states accurately. If uncertain about Kapa behavior, use `search_kapa_docs` when available.\n"
}