← HiggsfieldCONTENT HISTORY

Update to Higgsfield

Snapshot Oct 24, 2026 · 12:40 UTC · version 2.2.1

WHAT CHANGED

Declared capabilities changed

Full description — Now says: videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made...

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

Save Higgsfield and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 22:02 UTC

videos, branded content, and websites with Higgsfield in ChatGPT. Start with an idea, product photo, or reference image, then choose from Viral and Marketing Studio presets, creative recipes, or image and video models. Refine your result...

After

Oct 24, 2026 · 12:40 UTC

videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life. • Generate images and videos from t...

Long description

Before

Sep 30, 2026 · 22:02 UTC

videos, branded content, and websites with Higgsfield in ChatGPT. Start with an idea, product photo, or reference image, then choose from Viral and Marketing Studio presets, creative recipes, or image and video models. Refine your result...

After

Oct 24, 2026 · 12:40 UTC

videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life. • Generate images and videos from t...

Declared skills

Before

Sep 30, 2026 · 22:02 UTC

[{"description":"Create ordered independent edits from one supplied 4-30 second video with Ad Multiplier while preserving motion, timing, audio, and untargeted text. Activate for \"ad multiplier\", \"multiply my video or ad\", or several...

After

Oct 24, 2026 · 12:40 UTC

[{"description":"Resolve and route Higgsfield slash commands. Activate for a command invocation such as /ugc-video, /faceless-video, /ad-multiplier or /hero-shot, including a bare command, an unfamiliar command in Higgsfield context, or ...

Is template instance

Before

Sep 30, 2026 · 22:02 UTC

Not present

After

Oct 24, 2026 · 12:40 UTC

false

Compare saved observations

Download comparison JSON
Full technical diff · 12 changed fields

added /is_template_instance

BEFORE
Field was absent
AFTER
false

removed /release/app_manifest/apps/app-6a3293e129088191abf0875820e839da

BEFORE
{
  "id": "asdk_app_6a3293e129088191abf0875820e839da",
  "required": true
}
AFTER
Field is absent

added /release/app_manifest/apps/higgsfield

BEFORE
Field was absent
AFTER
{
  "id": "asdk_app_6a3293e129088191abf0875820e839da",
  "required": true
}

changed /release/description

BEFORE
"Create images, videos, branded content, and websites with Higgsfield in ChatGPT. Start with an idea, product photo, or reference image, then choose from Viral and Marketing Studio presets, creative recipes, or image and video models. Refine your results through conversation.\n\nWith Higgsfield, you can:\n\n• Browse Viral presets with /effects and Marketing Studio presets with /product, /motion, or /marketing-studio. Explore creative recipes and named workflows such as /hero-shot, /reel-cover, and /genjutsu.\n\n• Generate images and videos from text or reference images. Turn a product photo into image ads in different styles, short video ads with different hooks, or a complete set of promotional content.\n\n• Create UGC product videos, reviews, unboxings, tutorials, fashion try-ons, faceless explainers, and episodes with a consistent AI presenter. Write scripts, generate narration, and add subtitles.\n\n• Use Ad Multiplier to create targeted variations of an existing video, or edit footage with animated text, layouts, transitions, motion graphics, and effects.\n\n• Build and deploy websites, web apps, and browser games. Refine the design and update your hosted project through chat.\n\nConnect your Higgsfield account to get started."
AFTER
"Create images, videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life.\n\nWith Higgsfield, you can:\n\n• Generate images and videos from text or references. Explore different styles, create variations and animate still images.\n\n• Turn product photos into promotional visuals and short video ads. Try different looks and hooks with Marketing Studio.\n\n• Browse Viral effects and Marketing Studio presets with /effects, /product, /motion or /marketing-studio. Use creative commands such as /hero-shot and /reel-cover to start a specific workflow.\n\n• Use Genjutsu to transfer motion from a reference video or replace a subject or object in an existing clip using reference images.\n\n• Create an AI Influencer character, refine its appearance and use it as a reference for generated content.\n\n• Generate voiceovers from your text and choose a narration voice.\n\nConnect your Higgsfield account to get started."

changed /release/id

BEFORE
"pluginrel_8c6fad6c8b4c8191aa01848571c267d9"
AFTER
"pluginrel_31580f19fc94819190985b39dca907cd"

changed /release/interface/composer_icon_url

BEFORE
null
AFTER
"https://files.openai.com/content?id=file_00000000435c8211ab418f536d7cd6be"

changed /release/interface/logo_url

BEFORE
"https://files.openai.com/content?id=file_00000000d2fc81f6922d7a69b2579a06"
AFTER
"https://files.openai.com/content?id=file_000000005ef08211b72d60d7cc29342a"

changed /release/interface/logo_url_dark

BEFORE
"https://files.openai.com/content?id=file_0000000067a081f5b3ef671cffafae08"
AFTER
null

changed /release/interface/long_description

BEFORE
"Create images, videos, branded content, and websites with Higgsfield in ChatGPT. Start with an idea, product photo, or reference image, then choose from Viral and Marketing Studio presets, creative recipes, or image and video models. Refine your results through conversation.\n\nWith Higgsfield, you can:\n\n• Browse Viral presets with /effects and Marketing Studio presets with /product, /motion, or /marketing-studio. Explore creative recipes and named workflows such as /hero-shot, /reel-cover, and /genjutsu.\n\n• Generate images and videos from text or reference images. Turn a product photo into image ads in different styles, short video ads with different hooks, or a complete set of promotional content.\n\n• Create UGC product videos, reviews, unboxings, tutorials, fashion try-ons, faceless explainers, and episodes with a consistent AI presenter. Write scripts, generate narration, and add subtitles.\n\n• Use Ad Multiplier to create targeted variations of an existing video, or edit footage with animated text, layouts, transitions, motion graphics, and effects.\n\n• Build and deploy websites, web apps, and browser games. Refine the design and update your hosted project through chat.\n\nConnect your Higgsfield account to get started."
AFTER
"Create images, videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life.\n\nWith Higgsfield, you can:\n\n• Generate images and videos from text or references. Explore different styles, create variations and animate still images.\n\n• Turn product photos into promotional visuals and short video ads. Try different looks and hooks with Marketing Studio.\n\n• Browse Viral effects and Marketing Studio presets with /effects, /product, /motion or /marketing-studio. Use creative commands such as /hero-shot and /reel-cover to start a specific workflow.\n\n• Use Genjutsu to transfer motion from a reference video or replace a subject or object in an existing clip using reference images.\n\n• Create an AI Influencer character, refine its appearance and use it as a reference for generated content.\n\n• Generate voiceovers from your text and choose a narration voice.\n\nConnect your Higgsfield account to get started."

changed /release/interface/screenshot_urls

BEFORE
[
  "https://files.openai.com/content?id=file_00000000aa9c82119f1f67f09cff1a19",
  "https://files.openai.com/content?id=file_000000009efc8211bf7a75ded58cb9cc",
  "https://files.openai.com/content?id=file_0000000041c48211bb5e729d4056f358"
]
AFTER
[]

changed /release/skills

BEFORE
[
  {
    "description": "Create ordered independent edits from one supplied 4-30 second video with Ad Multiplier while preserving motion, timing, audio, and untargeted text. Activate for \"ad multiplier\", \"multiply my video or ad\", or several edits of one clip that replace, add, remove, or change people, products, objects, clothing, backgrounds, attributes, or targeted text. Do not use for ordinary generation, Marketing Studio presets, simple edits, out-of-range sources, or Cartesian asset combinations.",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ad-multiplier to create multiple edited versions of this source video.",
      "display_name": "Ad Multiplier",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "hierarchy",
      "short_description": "Create scalable edits from one source video"
    },
    "name": "ad-multiplier",
    "plugin_release_skill_id": "pluginrsk_6aad6e7f653081919bc276916d4f38cb"
  },
  {
    "description": "Produce a complete channel episode with one consistent AI presenter, supporting visuals and a measured final edit. Activate when the current request authorizes that complete episode. An earlier episode plan does not make a later standalone avatar greeting, test take or short clip an episode request. Exclude clip-only generation, faceless video, product UGC, script-only writing and publishing existing footage.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ai-host-video to create a complete hosted episode from my script or topic.",
      "display_name": "AI Host Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "chat",
      "short_description": "Create complete episodes with a consistent AI host"
    },
    "name": "ai-host-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e80031081918ca43dcfd018afae"
  },
  {
    "description": "Use only when the user asks to produce a finished multi-scene narrator-led\nvideo and explicitly requests a faceless channel, YouTube automation, narrated\nexplainer/story/education, documentary, Picture Story, narrated stills,\nframe-by-frame story, storybook or myth retelling, or kids song video. Topic alone is never enough: a generic video of/about something,\nincluding a historical topic, uses ordinary video generation. Do not use for\nbrowsing or listing faceless presets: call get_faceless_channel_presets directly\nwithout loading this skill. Also exclude planning or ideas, single clips, silent animation, image-to-video, footage\nedits, ads, product demos, UGC, or any video with a visible on-camera presenter\nor talking head. This workflow requires a consistent\nnon-photoreal style, reusable assets, narrator voiceover, and burned subtitles.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $faceless-video to create a complete faceless video from topic to final stitched result.",
      "display_name": "Faceless Video",
      "icon_large_url": "https://files.openai.com/content?id=file_000000004cc08211969d4b1c4687aa2f",
      "icon_small_url": "https://files.openai.com/content?id=file_00000000ca708211bb7730ae99672cab",
      "iconography": "bolt",
      "short_description": "Create complete narrator-led channel videos"
    },
    "name": "faceless-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e80e1308191a47708d00e78a2ad"
  },
  {
    "description": "Resolve and execute named Higgsfield presets and slash commands, or browse Viral and Marketing Studio preset galleries. Resolve a named preset before loading production workflows suggested by its name, including cover or unboxing workflows; only returned instructions can request those helpers. Also route named /MODEL_NAME invocations. Ordinary model questions, media generation and Marketing Studio brand-kit records use direct tools. Mentioning Higgsfield alone, quoted/translated commands and explicitly negated commands are not invocations.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $higgsfield to find and follow the named preset or command.",
      "display_name": "Higgsfield Presets",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "radar",
      "short_description": "Find presets, workflows, and setup instructions"
    },
    "name": "higgsfield",
    "plugin_release_skill_id": "pluginrsk_6aad6e81837881918ece333c87439c8a"
  },
  {
    "description": "Design concrete motion tracks for native Higgsedit compositions: frame choreography, timed text entrances, shared timelines and counters. Use for authoring how a native composition animates. General animation ideas, UI advice and CSS or JavaScript snippets do not activate this skill. Use video-editing for project assembly, footage edits and rendering.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $motion-craft to design native animation for my Higgsedit composition.",
      "display_name": "Motion Craft",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "bolt",
      "short_description": "Design native motion for Higgsedit compositions"
    },
    "name": "motion-craft",
    "plugin_release_skill_id": "pluginrsk_6aad6e82159c81919fbb43ef4e7429a3"
  },
  {
    "description": "Produce duration-constrained voice takes or a photo-based presenter overlay on an existing video. Use for explicit narrator invocation, numbered takes fitted to fixed video windows, a locked-voice story read with explicitly requested duration/pause measurement and retries, or compositing a consenting person as the narrator in a supplied video. Story length, a chosen voice or asking for one audio file does not imply timing and retry requirements. Exclude ordinary TTS, unconstrained voiceovers and story/audiobook reads, voice cloning, generic dubbing, music and native speech in a newly generated UGC video.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $narrator to produce fitted narration or place my consenting presenter into my video.",
      "display_name": "Narrator",
      "icon_large_url": "https://files.openai.com/content?id=file_00000000ee608211963280de98de279d",
      "icon_small_url": "https://files.openai.com/content?id=file_000000006ed88211a06e82fd0c97767c",
      "iconography": "chat",
      "short_description": "Create fitted narration or an on-screen narrator"
    },
    "name": "narrator",
    "plugin_release_skill_id": "pluginrsk_6aad6e82e12c81918794002b2f6e7ced"
  },
  {
    "description": "Use only when the current requested output is a video with speech captions permanently burned into its pixels, including restyling those captions or an explicit caption-burning step in a production workflow. Translating or correcting subtitle words is a text task and must not activate this skill, even in a conversation about a captioned video. Exclude transcription, SRT/VTT files, soft subtitle tracks and video analysis. Missing video is an intake gap only after the user has requested burned-in video output.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $subtitles to add clean, Whisper-timed captions to this video.",
      "display_name": "Subtitles",
      "icon_large_url": "https://files.openai.com/content?id=file_0000000037c88211b9668820aedcff78",
      "icon_small_url": "https://files.openai.com/content?id=file_000000000274821190a438e0c0962489",
      "iconography": "pdf",
      "short_description": "Burn accurate, styled video captions"
    },
    "name": "subtitles",
    "plugin_release_skill_id": "pluginrsk_6aad6e8449608191b848f29bd9338c50"
  },
  {
    "description": "Create or revise finished YouTube/Instagram thumbnails and video cover images. Require a request to make or change the image; critique, readability analysis, title ideas and channel planning alone stay text. Named Higgsfield presets are resolved by higgsfield first: do not load this workflow merely because a slash token names a cover. For presets, load it only when the resolved instructions request it. Exclude generic images, complete videos, video edits and title cards within footage.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $thumbnail-generation to create a finished YouTube thumbnail for my video.",
      "display_name": "Thumbnail Generation",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "radar",
      "short_description": "Create polished YouTube and Instagram covers"
    },
    "name": "thumbnail-generation",
    "plugin_release_skill_id": "pluginrsk_6aad6e84dffc8191b9f87b477ea8afa3"
  },
  {
    "description": "Produce a finished product-only UGC video with off-screen voiceover; a person may appear only as auxiliary hands, cropped body, or POV. Require UGC or casual creator-style intent together with product-only, no creator on camera, no talking head, or product-as-hero framing. Product-only or faceless framing alone does not qualify a generic commercial. Exclude silent or no-narration requests even when labeled UGC; use ordinary video generation instead. Its off-screen voice is native Seedance audio: do not activate narrator or call separate audio-generation tools. Missing product or duration is an intake gap. Do not use for creator-led reviews, unboxings, tutorials, try-ons, SaaS or website walkthroughs, generic ads, scripts, or footage edits.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-product-video to create a finished product-only UGC video from this product.",
      "display_name": "UGC Product Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Create product-only UGC videos"
    },
    "name": "ugc-product-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e85779c8191a3f3e496e7a4c75a"
  },
  {
    "description": "Produce a finished brand-authorized UGC-style talking-head video in which one consenting adult or generated adult creator demonstrates a product or delivers user-supplied copy. Use for explicit UGC, creator-video, TikTok-style product showcase, or review-style requests that can be rendered without fabricated experience or endorsement; a product is optional, while a missing duration is an intake gap. Do not use for testimonials, impersonation, product-only ads without an on-camera speaker, off-screen voiceover, unboxing-led videos, step-by-step tutorials, try-ons, SaaS or website walkthroughs, generic ads, script-only requests, or edits of existing footage.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-review-video to create a brand-authorized talking-head UGC product demonstration.",
      "display_name": "UGC Review Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "chat",
      "short_description": "Create truthful talking-head UGC demos"
    },
    "name": "ugc-review-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e86110481919b1173ebd82b4b58"
  },
  {
    "description": "Produce a finished UGC try-on video where one consenting adult or generated adult creator wears and poses with a garment, footwear item, bag, jewelry piece, or wearable accessory while showing fit and texture. Use when try-on, wearing, OOTD, fit-check, or video-of-me-wearing intent is explicit. Do not load this skill for a text-only script, outline, shot list, or advice, even if it mentions UGC, OOTD, or try-on; those requests need writing, not the video-production workflow. Missing product, duration, or creator input is an intake gap. Do not use for reviews without a try-on, unboxings, tutorials, product-only ads, SaaS walkthroughs, generic ads, or footage edits.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-try-on-video to create a finished UGC try-on video for this wearable product.",
      "display_name": "UGC Try-On Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "heart",
      "short_description": "Create creator-led UGC try-on videos"
    },
    "name": "ugc-try-on-video",
    "plugin_release_skill_id": "pluginrsk_6aad75a671848191b6e957b594fe149d"
  },
  {
    "description": "Produce a UGC tutorial where one visible creator demonstrates realistic step-by-step use of a specific product and every step has a baked \"Step N — Heading\" label. Use when tutorial, how-to, or step-by-step intent and creator/UGC framing are explicit. Missing product or duration is an intake gap. Do not use for ordinary reviews, unboxings, try-ons, product-only ads, SaaS walkthroughs, generic ads, scripts, or footage edits.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-tutorial-video to create a finished step-by-step UGC tutorial for this product.",
      "display_name": "UGC Tutorial Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "hierarchy",
      "short_description": "Create step-by-step UGC tutorial videos"
    },
    "name": "ugc-tutorial-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e873ba881919d66e818cb081478"
  },
  {
    "description": "Produce a creator-led UGC unboxing video: a visible creator opens a package and reacts to its reveal. Require both the creator-led format and an unboxing, haul or PR-drop arc. Opening a package, showing its contents or focusing on packaging alone does not request a creator performance; use ordinary video generation for a product-only reveal. Exclude scripts, still images, footage edits and other UGC formats. Named preset commands such as /unboxing use the Higgsfield preset resolver. Missing assets after a valid format match are intake gaps.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-unboxing-video to create a finished UGC unboxing video for this product.",
      "display_name": "UGC Unboxing Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Create creator-led UGC unboxing videos"
    },
    "name": "ugc-unboxing-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e87d8588191a16e92111b71580b"
  },
  {
    "description": "Produce a finished creator-led UGC video about a website, web app, online service, store, or product page, using real captured screenshots while a talking-head creator narrates. Use for SaaS UGC, site tours, app tours, or requests where the supplied page must appear. Do not load this skill for text-only scripts, outlines, or walkthrough plans, even if they mention UGC or SaaS; do not use it merely as a scriptwriting reference. Missing URL or duration is an intake gap. Do not use for product-only ads, unboxings, tutorials, try-ons, website editing, generated UI, scripts, or footage edits.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $ugc-website-video to create a finished UGC video about this website.",
      "display_name": "UGC Website Video",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "cursor",
      "short_description": "Create UGC videos from live websites"
    },
    "name": "ugc-website-video",
    "plugin_release_skill_id": "pluginrsk_6aad6e8867bc8191bc2c1df46fb3d9ef"
  },
  {
    "description": "Edit footage and motion graphics with Higgsedit.\nActivate only for a requested edit or graphics deliverable:\ncuts, soundtrack changes, overlays and animated title cards.\nDo not activate when the user only asks to analyze, summarize, describe,\ncritique or review a video, including scene-by-scene breakdowns.\nTimeline inspection is supporting work for a requested edit, not a standalone\nactivation trigger. Exclude standalone still cards, image-to-video photo\nanimation without native composition, generative restyling,\ntranscription and subtitle text work. For speech-caption burning, use subtitles.\nObject replacements or targeted clip variants use ad-multiplier.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $video-editing to edit my supplied footage and render the finished video.",
      "display_name": "Video Editing",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "pen",
      "short_description": "Edit footage and native motion graphics with Higgsedit"
    },
    "name": "video-editing",
    "plugin_release_skill_id": "pluginrsk_6aad6e891d608191895df3f3507ad79e"
  },
  {
    "description": "Build and publish a complete website, web app or browser game on Higgsfield, or edit/redeploy an existing Higgsfield-hosted site. Use when the requested deliverable is that hosted product or a change to it. Components, snippets and fixes for a user's existing local codebase remain repository work; mentioning React, a website or a UI element does not request a hosted build. Exclude copywriting, external-site review, standalone media and read-only site administration. After a valid activation, collect missing product type and scope.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $website-builder to build and deploy a live website for my product.",
      "display_name": "Website Builder",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "code",
      "short_description": "Build and ship live websites, apps, and games"
    },
    "name": "website-builder",
    "plugin_release_skill_id": "pluginrsk_6aad6e89bf808191b8c6c85d2661b9e7"
  },
  {
    "description": "Write a complete YouTube script with a full spoken body in one of six genres: business/finance, tech review, commentary, documentary, true crime or explainer. Includes hook options, timestamps, production cues and a retention map. Use for full scripts, not hook-only requests, ad copy or finished video production; ai-host-video may call this skill for its script-writing stage.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $youtube-script to write a complete YouTube script from my topic and target duration.",
      "display_name": "YouTube Script",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "pdf",
      "short_description": "Write complete genre-specific YouTube scripts"
    },
    "name": "youtube-script",
    "plugin_release_skill_id": "pluginrsk_6aad6e8a51208191a83b33797ea8f175"
  }
]
AFTER
[
  {
    "description": "Resolve and route Higgsfield slash commands. Activate for a command invocation such as /ugc-video, /faceless-video, /ad-multiplier or /hero-shot, including a bare command, an unfamiliar command in Higgsfield context, or a command with missing media inputs. Resolve the route before asking for inputs or starting a generic workflow. Also use for named Higgsfield presets, preset or command browsing, and requests to open, connect or work in Higgsfield Video Editor/Katana, even without a slash. Exclude unrelated apps' commands, URL paths, quoted or translated commands, explicitly negated invocations, and ordinary media requests without a preset or command. Browsing does not authorize generation.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $higgsfield to resolve my slash command or find a Higgsfield preset.",
      "display_name": "Higgsfield",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "bolt",
      "short_description": "Route Higgsfield slash commands and presets"
    },
    "name": "higgsfield",
    "plugin_release_skill_id": "pluginrsk_6ad38d7bc03c8191a35a253cfb2100da"
  },
  {
    "description": "Build and publish a complete website, web app or browser game on Higgsfield, or edit/redeploy an existing Higgsfield-hosted site. Use when the requested deliverable is that hosted product or a change to it. Components, snippets and fixes for a user's existing local codebase remain repository work; mentioning React, a website or a UI element does not request a hosted build. Exclude copywriting, external-site review, standalone media and read-only site administration. After a valid activation, collect missing product type and scope.\n",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $website-builder to build and deploy a live website for my product.",
      "display_name": "Website Builder",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "code",
      "short_description": "Build and ship live websites, apps, and games"
    },
    "name": "website-builder",
    "plugin_release_skill_id": "pluginrsk_6ad38d7be5e88191b8c1e3d19486ec96"
  }
]

changed /release/version

BEFORE
"2.1.0"
AFTER
"2.2.1"
Full snapshot data
{
  "canonical_app_id": "asdk_app_6a3293e129088191abf0875820e839da",
  "connector_id": "asdk_app_6a3293e129088191abf0875820e839da",
  "created_at": "2026-06-23T03:46:33.565074Z",
  "discoverability": "LISTED",
  "id": "plugin_asdk_app_6a3293e129088191abf0875820e839da",
  "is_template": false,
  "is_template_instance": false,
  "name": "app-6a3293e129088191abf0875820e839da",
  "release": {
    "app_ids": [
      "asdk_app_6a3293e129088191abf0875820e839da"
    ],
    "app_manifest": {
      "apps": {
        "higgsfield": {
          "id": "asdk_app_6a3293e129088191abf0875820e839da",
          "required": true
        }
      }
    },
    "app_templates": [],
    "description": "Create images, videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life.\n\nWith Higgsfield, you can:\n\n• Generate images and videos from text or references. Explore different styles, create variations and animate still images.\n\n• Turn product photos into promotional visuals and short video ads. Try different looks and hooks with Marketing Studio.\n\n• Browse Viral effects and Marketing Studio presets with /effects, /product, /motion or /marketing-studio. Use creative commands such as /hero-shot and /reel-cover to start a specific workflow.\n\n• Use Genjutsu to transfer motion from a reference video or replace a subject or object in an existing clip using reference images.\n\n• Create an AI Influencer character, refine its appearance and use it as a reference for generated content.\n\n• Generate voiceovers from your text and choose a narration voice.\n\nConnect your Higgsfield account to get started.",
    "display_name": "Higgsfield",
    "id": "pluginrel_31580f19fc94819190985b39dca907cd",
    "interface": {
      "brand_color": null,
      "capabilities": [],
      "category": "Creativity",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_00000000435c8211ab418f536d7cd6be",
      "default_prompt": "Create 4 image ads for my product in different styles",
      "default_prompts": [
        "Create 4 image ads for my product in different styles",
        "Generate 3 short video ads for my brand with different hooks",
        "Turn my product photo into a set of promotional images and videos"
      ],
      "developer_name": "Higgsfield AI, Inc.",
      "logo_url": "https://files.openai.com/content?id=file_000000005ef08211b72d60d7cc29342a",
      "logo_url_dark": null,
      "long_description": "Create images, videos and product ads with Higgsfield in ChatGPT. Start with an idea, a product photo or reference media, then use image and video models, ready-made presets and creative commands to bring it to life.\n\nWith Higgsfield, you can:\n\n• Generate images and videos from text or references. Explore different styles, create variations and animate still images.\n\n• Turn product photos into promotional visuals and short video ads. Try different looks and hooks with Marketing Studio.\n\n• Browse Viral effects and Marketing Studio presets with /effects, /product, /motion or /marketing-studio. Use creative commands such as /hero-shot and /reel-cover to start a specific workflow.\n\n• Use Genjutsu to transfer motion from a reference video or replace a subject or object in an existing clip using reference images.\n\n• Create an AI Influencer character, refine its appearance and use it as a reference for generated content.\n\n• Generate voiceovers from your text and choose a narration voice.\n\nConnect your Higgsfield account to get started.",
      "plugin_category_id": "creativity",
      "privacy_policy_url": "https://higgsfield.ai/privacy-policy",
      "screenshot_urls": [],
      "short_description": "Every image and video model",
      "terms_of_service_url": "https://higgsfield.ai/terms-of-use-agreement",
      "website_url": "https://higgsfield.ai"
    },
    "keywords": [],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Resolve and route Higgsfield slash commands. Activate for a command invocation such as /ugc-video, /faceless-video, /ad-multiplier or /hero-shot, including a bare command, an unfamiliar command in Higgsfield context, or a command with missing media inputs. Resolve the route before asking for inputs or starting a generic workflow. Also use for named Higgsfield presets, preset or command browsing, and requests to open, connect or work in Higgsfield Video Editor/Katana, even without a slash. Exclude unrelated apps' commands, URL paths, quoted or translated commands, explicitly negated invocations, and ordinary media requests without a preset or command. Browsing does not authorize generation.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $higgsfield to resolve my slash command or find a Higgsfield preset.",
          "display_name": "Higgsfield",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "bolt",
          "short_description": "Route Higgsfield slash commands and presets"
        },
        "name": "higgsfield",
        "plugin_release_skill_id": "pluginrsk_6ad38d7bc03c8191a35a253cfb2100da"
      },
      {
        "description": "Build and publish a complete website, web app or browser game on Higgsfield, or edit/redeploy an existing Higgsfield-hosted site. Use when the requested deliverable is that hosted product or a change to it. Components, snippets and fixes for a user's existing local codebase remain repository work; mentioning React, a website or a UI element does not request a hosted build. Exclude copywriting, external-site review, standalone media and read-only site administration. After a valid activation, collect missing product type and scope.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $website-builder to build and deploy a live website for my product.",
          "display_name": "Website Builder",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Build and ship live websites, apps, and games"
        },
        "name": "website-builder",
        "plugin_release_skill_id": "pluginrsk_6ad38d7be5e88191b8c1e3d19486ec96"
      }
    ],
    "version": "2.2.1"
  },
  "scope": "GLOBAL",
  "status": "ENABLED"
}

SHA-256 of public snapshot: a9cb3d2f8b834711a7153593a437382cfe7e32663af00c2abee958bfe9207516