Update to EmpirioLabs AI
Snapshot Nov 16, 2026 · 00:09 UTC · version 1.0.13
Collection source: downloaded plugin package.
Instructions updated for ai-photo-editor
Skill instructions — Now says: 5. Reply with the link to the edited image and one line on what changed. Show the file through its link only. Write no image or video element in the reply,...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Nov 15, 2026 · 06:36 UTC
5. Reply with the link to the edited image and one line on what changed.
Nov 16, 2026 · 00:09 UTC
5. Reply with the link to the edited image and one line on what changed. 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...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -8,6 +8,6 @@ 2. Choose an image-edit model: call `list_models` with `endpoint` set to `/v1/images/edits`, unless the user names a model. 3. Call `edit_image` with the `model`, the instruction as `prompt` and the link as `image`. 4. If the result is still generating, call `get_job` with the job id, and again until the image is ready. Never start the same edit twice. -5. Reply with the link to the edited image and one line on what changed. +5. Reply with the link to the edited image and one line on what changed. 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. If the user has no link to the image, ask for one: the tool reads images from links.
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: ai-photo-editor\ndescription: Edit an existing image from a link. Use when the user supplies an image and wants something changed, added or removed, a new background or a new style.\n---\n# Edit an image\n\n1. You need the image as an `https` link and an instruction that says what to change and what to keep.\n2. Choose an image-edit model: call `list_models` with `endpoint` set to `/v1/images/edits`, unless the user names a model.\n3. Call `edit_image` with the `model`, the instruction as `prompt` and the link as `image`.\n4. If the result is still generating, call `get_job` with the job id, and again until the image is ready. Never start the same edit twice.\n5. Reply with the link to the edited image and one line on what changed.\n\nIf the user has no link to the image, ask for one: the tool reads images from links.\n"
"---\nname: ai-photo-editor\ndescription: Edit an existing image from a link. Use when the user supplies an image and wants something changed, added or removed, a new background or a new style.\n---\n# Edit an image\n\n1. You need the image as an `https` link and an instruction that says what to change and what to keep.\n2. Choose an image-edit model: call `list_models` with `endpoint` set to `/v1/images/edits`, unless the user names a model.\n3. Call `edit_image` with the `model`, the instruction as `prompt` and the link as `image`.\n4. If the result is still generating, call `get_job` with the job id, and again until the image is ready. Never start the same edit twice.\n5. Reply with the link to the edited image and one line on what changed. 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\nIf the user has no link to the image, ask for one: the tool reads images from links.\n"
Full snapshot data
{
"description": "Edit an existing image from a link. Use when the user supplies an image and wants something changed, added or removed, a new background or a new style.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 219
}
],
"name": "ai-photo-editor",
"skill_md_contents": "---\nname: ai-photo-editor\ndescription: Edit an existing image from a link. Use when the user supplies an image and wants something changed, added or removed, a new background or a new style.\n---\n# Edit an image\n\n1. You need the image as an `https` link and an instruction that says what to change and what to keep.\n2. Choose an image-edit model: call `list_models` with `endpoint` set to `/v1/images/edits`, unless the user names a model.\n3. Call `edit_image` with the `model`, the instruction as `prompt` and the link as `image`.\n4. If the result is still generating, call `get_job` with the job id, and again until the image is ready. Never start the same edit twice.\n5. Reply with the link to the edited image and one line on what changed. 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\nIf the user has no link to the image, ask for one: the tool reads images from links.\n"
}SHA-256 of public snapshot: db7b3be7e864ff873ffdbc9f5e499114462db35b7b276e17d6ac7739d7639ddc