{"id":97614,"plugin_id":"plugin_asdk_app_6abd51b0891c81918954286cdd388fa3","kind":"skill","collection_source":"plugin_package","comparison_source":"plugin_package","observed_at":"2026-11-16T00:09:55.808Z","digest":"a6961a31872a99edf80a2d5cb2360b66cbae1576f0f0bf22413705fb158b0d23","against":97034,"payload":{"description":"Turn an idea into a short narrated video. Writes a script, makes a still for the opening shot, animates it and records the narration. Use for explainers, ads, stories and social posts.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":237}],"name":"story-to-video","skill_md_contents":"---\nname: story-to-video\ndescription: Turn an idea into a short narrated video. Writes a script, makes a still for the opening shot, animates it and records the narration. Use for explainers, ads, stories and social posts.\n---\n# Story to video\n\n1. Write a script of two to four sentences and one visual description of the opening shot. Show both and adjust them if the user asks.\n2. Make the opening still: call `generate_image` with the visual description as `prompt`.\n3. Animate it: call `generate_video` with the still's link as `image` and a prompt for the motion. Call `get_job` with the job id, and again until the clip is ready.\n4. Record the narration: choose a speech model with `list_models` (set `endpoint` to `/v1/audio/speech`), choose a voice with `list_voices`, and call `text_to_speech` with the script as `input`.\n5. Reply with the three links in order, the still, the clip and the narration, each with one line on what it is. Show the file through its link only. Write no image or video element in the reply, not even an empty one (no AsyncImage, no AsyncVideo): such an element shows media found by a search or an empty frame, never the generated file.\n\nRun the steps one after another and never the same step twice. When a step is refused, stop and say what the tool reported.\n"},"changes":[{"path":"/skill_md_contents","type":"changed","before":"---\nname: story-to-video\ndescription: Turn an idea into a short narrated video. Writes a script, makes a still for the opening shot, animates it and records the narration. Use for explainers, ads, stories and social posts.\n---\n# Story to video\n\n1. Write a script of two to four sentences and one visual description of the opening shot. Show both and adjust them if the user asks.\n2. Make the opening still: call `generate_image` with the visual description as `prompt`.\n3. Animate it: call `generate_video` with the still's link as `image` and a prompt for the motion. Call `get_job` with the job id, and again until the clip is ready.\n4. Record the narration: choose a speech model with `list_models` (set `endpoint` to `/v1/audio/speech`), choose a voice with `list_voices`, and call `text_to_speech` with the script as `input`.\n5. Reply with the three links in order, the still, the clip and the narration, each with one line on what it is.\n\nRun the steps one after another and never the same step twice. When a step is refused, stop and say what the tool reported.\n","after":"---\nname: story-to-video\ndescription: Turn an idea into a short narrated video. Writes a script, makes a still for the opening shot, animates it and records the narration. Use for explainers, ads, stories and social posts.\n---\n# Story to video\n\n1. Write a script of two to four sentences and one visual description of the opening shot. Show both and adjust them if the user asks.\n2. Make the opening still: call `generate_image` with the visual description as `prompt`.\n3. Animate it: call `generate_video` with the still's link as `image` and a prompt for the motion. Call `get_job` with the job id, and again until the clip is ready.\n4. Record the narration: choose a speech model with `list_models` (set `endpoint` to `/v1/audio/speech`), choose a voice with `list_voices`, and call `text_to_speech` with the script as `input`.\n5. Reply with the three links in order, the still, the clip and the narration, each with one line on what it is. Show the file through its link only. Write no image or video element in the reply, not even an empty one (no AsyncImage, no AsyncVideo): such an element shows media found by a search or an empty frame, never the generated file.\n\nRun the steps one after another and never the same step twice. When a step is refused, stop and say what the tool reported.\n"}],"summary":"Fields changed: 1. /skill_md_contents.","summary_kind":"deterministic","summary_metadata":{}}