← EmpirioLabs AICONTENT HISTORY

Update to EmpirioLabs AI

Snapshot Nov 16, 2026 · 00:09 UTC · version 1.0.13

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for image-to-video

Skill instructions — Now says: 5. Reply with the video link and the model. Show the file through its link only. Write no image or video element in the reply, not even an empty one (no...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save EmpirioLabs AI and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Nov 15, 2026 · 06:36 UTC

5. Reply with the video link and the model.

After

Nov 16, 2026 · 00:09 UTC

5. Reply with the video link and the model. 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 empt...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -8,6 +8,6 @@
 2. Describe the motion in one prompt: what moves, how the camera moves and what stays still.
 3. Call `generate_video` with the `prompt` and the link as `image`. When the user names no model, follow what the `model` input's own description says to use.
 4. Call `get_job` with the job id, and again until the video is ready. Never start the same video twice.
-5. Reply with the video link and the model.
+5. Reply with the video link and the model. 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.
 
 To make the picture first, call `generate_image`, then animate the link it returns.
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: image-to-video\ndescription: Turn a still image into a moving video. Use when the user wants to animate a photo, a drawing, a product shot or an image the app just made.\n---\n# Animate an image\n\n1. Get the image as an `https` link. An image this app generated already has one.\n2. Describe the motion in one prompt: what moves, how the camera moves and what stays still.\n3. Call `generate_video` with the `prompt` and the link as `image`. When the user names no model, follow what the `model` input's own description says to use.\n4. Call `get_job` with the job id, and again until the video is ready. Never start the same video twice.\n5. Reply with the video link and the model.\n\nTo make the picture first, call `generate_image`, then animate the link it returns.\n"
AFTER
"---\nname: image-to-video\ndescription: Turn a still image into a moving video. Use when the user wants to animate a photo, a drawing, a product shot or an image the app just made.\n---\n# Animate an image\n\n1. Get the image as an `https` link. An image this app generated already has one.\n2. Describe the motion in one prompt: what moves, how the camera moves and what stays still.\n3. Call `generate_video` with the `prompt` and the link as `image`. When the user names no model, follow what the `model` input's own description says to use.\n4. Call `get_job` with the job id, and again until the video is ready. Never start the same video twice.\n5. Reply with the video link and the model. 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\nTo make the picture first, call `generate_image`, then animate the link it returns.\n"
Full snapshot data
{
  "description": "Turn a still image into a moving video. Use when the user wants to animate a photo, a drawing, a product shot or an image the app just made.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 204
    }
  ],
  "name": "image-to-video",
  "skill_md_contents": "---\nname: image-to-video\ndescription: Turn a still image into a moving video. Use when the user wants to animate a photo, a drawing, a product shot or an image the app just made.\n---\n# Animate an image\n\n1. Get the image as an `https` link. An image this app generated already has one.\n2. Describe the motion in one prompt: what moves, how the camera moves and what stays still.\n3. Call `generate_video` with the `prompt` and the link as `image`. When the user names no model, follow what the `model` input's own description says to use.\n4. Call `get_job` with the job id, and again until the video is ready. Never start the same video twice.\n5. Reply with the video link and the model. 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\nTo make the picture first, call `generate_image`, then animate the link it returns.\n"
}

SHA-256 of public snapshot: 91ee3b259820beae5947396f3c2329ebd5d30033e24e6ba583e57ff554f423c0