← anyVideoCONTENT HISTORY

Update to anyVideo

Snapshot Oct 24, 2026 · 13:46 UTC · version 1.0.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save anyVideo and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Organize a group discussion around a YouTube video with an audience-aware selection, facilitator agenda, open questions, and a synthesis of participant responses shared in chat. Use for a video club, classroom discussion, team viewing session, or moderated group conversation. Do not use for automatic video summaries, participant messaging, meeting scheduling, or a solo tutorial exercise.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 294
    }
  ],
  "name": "video-discussion-club",
  "skill_md_contents": "---\nname: video-discussion-club\ndescription: Organize a group discussion around a YouTube video with an audience-aware selection, facilitator agenda, open questions, and a synthesis of participant responses shared in chat. Use for a video club, classroom discussion, team viewing session, or moderated group conversation. Do not use for automatic video summaries, participant messaging, meeting scheduling, or a solo tutorial exercise.\n---\n\n# Video Discussion Club\n\n## Inputs\n\nEstablish the topic, audience, discussion purpose, and available discussion time.\nReuse a supplied video or previous selection. Ask one focused question if the\naudience or purpose is unclear enough to change the selection or agenda.\nDistinguish time for watching from time for discussion.\n\n## Workflow\n\n1. Turn the purpose into one central discussion question. If a video is needed,\n   call `search-videos` with `{ query, reason? }`, read `results`, and shortlist\n   two or three candidates using titles, descriptions, channels, and publication\n   dates. Explain their apparent fit and recommend one. Refine an unsuitable\n   search once; ask for a link if a suitable selection remains unavailable.\n2. Call `display-video` with `{ videoId, reason? }` for the chosen video when\n   viewing is wanted. Extract an ID from a supplied YouTube URL. Use only a\n   `status: ready` result with a video as the loaded selection. Explain\n   `invalid_video_id`, `video_not_found`, or a tool error and offer an alternative\n   from actual results rather than presenting an unavailable video as playable.\n3. Provide a facilitator agenda: a brief opening question, individual viewing,\n   an initial round of reactions, focused discussion, and a closing takeaway.\n   Allocate discussion time separately. Include video runtime only when returned\n   in `video.contentDetails.duration`; leave unverified watch time unknown.\n4. Prepare three to five open questions grounded in the topic and the stated\n   purpose. Frame video-specific points as things for participants to identify,\n   rather than scenes or claims the model has inspected. Include a prompt for\n   participants to distinguish what they saw from how they interpreted it.\n5. Invite the facilitator to share participant responses in chat. End the\n   preparation response with the agenda; do not invent a discussion or assume\n   participants have watched. During facilitation, ask one question at a time\n   and adapt to the responses actually provided.\n6. Synthesize the shared responses into areas of agreement, differing\n   interpretations, open questions, and one closing takeaway. Preserve meaningful\n   disagreement and attribute contributions only as the facilitator identifies\n   them; do not infer attendance or individual opinions.\n\n## Deliverable\n\nProvide the selected video, a timed discussion agenda, and facilitator questions.\nAfter responses arrive, provide a concise discussion recap grounded in those\nresponses, with unresolved points left open.\n\n## Boundaries\n\n- Use ordinary viewing and chat; do not require observations, transcripts,\n  private widget state, or automatic playback tracking.\n- Treat the discussion button as a title-only handoff. Request participant\n  responses before producing a content-specific recap.\n- Do not claim metadata verifies the full content, suitability for the audience,\n  caption availability, or factual accuracy. Identify uncertain fit plainly.\n- Keep coordination in chat. Do not send invitations, schedule meetings, control\n  shared playback, or claim persistent attendance or discussion storage.\n- Use only the registered tool arguments. If the user explicitly requests text\n  only or no video display, call neither tool and prepare from supplied material.\n"
}

SHA-256 of public snapshot: 72318d835fa758cd7b820000d7b890225207638f0759cbd48049e130a17885f3