agentleFS
GrowingGoldGrowingGold/super-skills-kit/skills/media/media-studio/SKILL.md

media-studio

Skill1 starsChanged 4 days agoMITView on GitHub

Make any image, banner, video, GIF, 3D or generative-art asset. AI image and video via Higgsfield (GPT Image 2.6, Nano Banana, Soul, Seedream, Seedance 2.5, Kling, Veo, Marketing Studio), OpenAI GPT Image or Gemini. Product photoshoots (studio, lifestyle, Pinterest pin, hero, carousel, ad pack, virtual try-on, restyle), marketplace listing images and A+ modules, UGC and unboxing ad videos, product 360 turntables and reveals, character face lock, outfit plates and character sheets (Banana Pro), cinematic scene plates, Soul ID, Virality Predictor, GLB from photos. Also blog hero, OG and social images, mockups, banners and display ads, Remotion and Hyperframes video, demo recordings, p5.js generative art, Slack GIFs, upscale and WebP. Use for: generate an image, make a video, animate this photo, remove background, inpaint, product photo, Amazon listing images, turntable, Higgsfield, Seedance, B-roll, talking head, GIF, enhance a screenshot. Logos go to brand-studio.

  • Pipes a download into a shell
  • Reads credentials
  • Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 7 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Frame the job: Write down: deliverable, placement (platform and exact px from references/platform-specs.md), new or edit, one asset or a …

    line 49
  2. Very specific:

    Load context before inventing anything: Read .agents/product-marketing.md or .claude/product-marketing.md if present [image, video], the …

    line 54
  3. Distinctive:

    Validate like a reviewer: Check subject, style, composition, text spelled right (zoom in), edit invariants held, real-product fidelity …

    line 85
  4. Distinctive:

    Gemini direct: only when the user wants Google billing or a Gemini-only feature.

    line 113
  5. Distinctive:

    Use the bundled scripts as they are: no edits to them and no one-off SDK runners [imagegen].

    line 161
  6. Very specific:

    Always state aspect ratio or px (on Higgsfield as the --aspect_ratio flag, not prompt text) and a style word ("clean commercial …

    line 176
  7. Distinctive:

    Ask once, before any billable call or batch:

    line 187
  8. Very specific:

    Run with --wait (one command, blocks, prints the URL).

    line 213
  9. Distinctive:

    Every local path in a media flag is uploaded to Higgsfield.

    line 215
  10. Very specific:

    Keep the original as a sibling (name-original.png).

    line 268
  11. Very specific:

    Write the algorithmic philosophy (named movement, 4-6 paragraphs) as .md.

    line 303
  12. Very specific:

    Read templates/viewer.html and build on it: seed section (display, prev/next, random, jump) and actions (regenerate, reset) stay.

    line 304
  13. Distinctive:

    Use the API or CLI route (scripts, Higgsfield CLI, Chrome headless, Playwright MCP) before clicking through a web UI.

    line 378
  14. Very specific:

    Keep keys in one credentials file outside any repo.

    line 380
  15. Distinctive:

    If a member folder is missing (not installed), work from this file alone.

    line 413

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Media Studio

One entry point for every image, banner, video, GIF, 3D and generative-art task. It merges sixteen skills: the Higgsfield suite (one credit pool for most image, video, audio and 3D models, plus product and marketplace enhancers), OpenAI and Gemini image scripts, fal, two marketing-production guides (image, video), banner design, Remotion rules, a photoreal character prompt director, a product-360 video guide, p5.js art, Slack GIFs and image enhancement. Load this file first, pick a mode, run the unified workflow, and open a member or reference file only when a route names it. members/<name>/ points at the original skill folder; <skill> in commands means this skill's absolute folder, ~/.claude/skill-library/media/media-studio.

Pick the mode

Task looks likeModeWhat to do / open
Photo, illustration, texture, sprite, concept art or scene from a promptAI-IMAGEWorkflow 1-9; model table in Core rules; recipes by use-case slug in members/imagegen/references/sample-prompts.md
Change an existing image: background swap, object removal, cut-out, relight, style transfer, compositeAI-EDITSame as AI-IMAGE plus the invariant rules; members/imagegen/references/prompting.md
Brand product visual from the user's real product photo: studio, lifestyle, Pinterest pin, hero, carousel, ad pack, try-on, surreal, seasonal restylePRODUCT-PHOTOhiggsfield product-photoshoot create --mode <mode>; modes and questions in references/higgsfield.md
Marketplace listing set: main image, secondary images, infographic, A+ modulesMARKETPLACE-CARDShiggsfield marketplace-cards create --scope ...; marketplace rules in references/platform-specs.md
AI ad video: UGC, unboxing, tutorial, review, try-on, TV spot; branded ad image from a format templateAD-VIDEOHiggsfield Marketing Studio / DTC ads in references/higgsfield.md; ad strategy from ads-and-measurement
Product turntable, 360 spin, reveal, beauty shot, hero product videoPRODUCT-360references/product-360.md, then Seedance via Higgsfield
Original recurring character (mascot, model, lifter): face lock, outfit plate, character sheet, outfit swapCHARACTERreferences/higgsfield-prompt-craft.md pipeline; verbatim templates in members/banana-pro-director-30/SKILL.md
Photoreal cinematic still or environment plate, often the start frame for a videoSCENE-PLATEPrompt-craft reference, "Scene plates" section
Train a face identity for consistent images and videoSOUL-IDmembers/higgsfield-soul-id/SKILL.md + photo guide; consent and paid plan first (house rules)
Score a finished video's hook, attention and retentionVIDEO-SCOREHiggsfield Virality Predictor (brain_activity); A/B tests stay in conversion-lab
Real 3D mesh (GLB) of a product from photos3D-ASSETHiggsfield multi_image_to_3d; a "3D-looking picture" is AI-IMAGE
Blog hero, OG preview, social post, profile or listing banner, email headerMARKETING-IMAGECompose in HTML/CSS, AI only for the background; sizes in references/platform-specs.md; OG and per-placement workflows in members/image/SKILL.md
Banner set (social cover, display ads, web hero, print) in several art directionsBANNERmembers/banner-design/SKILL.md steps; 22 styles + print specs in members/banner-design/references/banner-sizes-and-styles.md
Show the real product UI (feature shot, store screenshots, directory gallery)REAL-SCREENSHOTCapture real screens (Playwright MCP or Chrome headless), frame and annotate in HTML. Never AI-generate UI [image]
Make an existing image sharper, larger, smaller or web-readyENHANCELocal pipeline in Core rules > Enhance and optimize. Paid AI upscalers only after the user says yes
Templated, data-driven or batch video, motion graphics, captionsPROGRAMMATIC-VIDEOHyperframes vs Remotion rule below; Remotion topics in members/remotion-video-creation/rules/<topic>.md
Repeatable demo video of a web app flowDEMO-RECORDINGmembers/video/references/product-demo-recording.md (Playwright, visible cursor, subtitles, local-app gotchas)
AI footage, B-roll, image-to-video, AI avatar presenter, reframe a video to 9:16AI-VIDEOHiggsfield Seedance 2.5 by default (model table below); prompts in members/video/references/ai-video-prompting.md; reframe / draw_to_video workflows. Paid: ask the user
"Make it like this reference video"EDIT-ANATOMYBeat-sheet method in members/video/references/edit-anatomy.md; copy the editing grammar, never the footage
Generative art, flow field, particles, "art from code", seed galleryGENERATIVE-ARTmembers/algorithmic-art/SKILL.md, start from members/algorithmic-art/templates/viewer.html
Static poster, print piece or art PNG/PDF driven by a design philosophyPOSTERBuilt-in anthropic-skills:canvas-design
Animated GIF, Slack emoji, reaction GIFGIFFree first: members/slack-gif-creator/SKILL.md + its core/ helpers; paid AI GIF: gpt_image_2_6 --output_format gif
Voice-over, music, sound effectsAUDIOHiggsfield seed_audio (paid, ask the user); ElevenLabs not set up; members/fal-ai-media/SKILL.md audio section for options
Logo, brand mark, palette, icon systemelsewherebrand-studio (AI only for logo concepts)
Ad strategy, ad copy, platform ad policyelsewhereads-and-measurement; this skill only makes the visual

Unified workflow

  1. Frame the job. Write down: deliverable, placement (platform and exact px from references/platform-specs.md), new or edit, one asset or a set, preview-only or project-bound, and the exact on-image text. Label every input image by role: reference, edit target, or insert/style input [imagegen decision tree + image intake]. Ask the user only for true blockers (missing copy, platform, or the real product photo); otherwise default (3 options for banners [banner-design]) and state assumptions.
  2. Load context before inventing anything. Read .agents/product-marketing.md or .claude/product-marketing.md if present [image, video], the project's brand source (docs/brand-guidelines.md, design tokens, Tailwind theme) and existing assets. Use only supplied or verified brand rules; never invent a palette, slogan or logo use [banner-design].
  3. Choose the cheapest route that meets the need. Climb this ladder and stop at the first rung that works [merged from imagegen "when not to use", image approach table, banner-design visual sources]:
    1. existing or supplied asset (licensed);
    2. code-native: HTML/CSS, SVG, canvas, p5.js, Pillow; best for shapes, icons, diagrams, type-led banners and anything that must match repo assets;
    3. real capture: screenshots or screen recordings for anything showing the product UI; real product photos;
    4. AI generation or editing (paid). Use it for photos, illustrations, textures, lifestyle scenes, B-roll, product scenes built FROM the real product photo, and video. Text, logos and CTAs never live inside generated pixels when the asset is HTML-composed: they are overlaid in HTML/CSS so they stay sharp, editable and accessible [banner-design, image].
  4. If AI: pick the route and model with "Which generator and model" below: a Higgsfield enhancer command for product and marketplace work, a Higgsfield model id for everything else, OpenAI or Gemini direct only for the listed cases. Inside the CHARACTER pipeline, use the director's models [banana-pro-director-30]. Check current ids before promising one: they drift fast [fal-ai-media, higgsfield-generate].
  5. Write the prompt for the route [imagegen, higgsfield-generate, banana-pro-director-30, seedance-product-360]: direct model calls use the shared schema (40-80 words for stills, under about 200 tokens for any Higgsfield model); enhancer commands (product-photoshoot, marketplace-cards) get a short intent line, never a hand-written prompt; character and scene work follows the prompt-craft reference; video describes motion, not the start frame. Match augmentation to specificity: a detailed prompt is only normalized; a generic one gets composition, lighting and intended-use hints, never new objects, brands, slogans or palettes [imagegen].
  6. Gate the spend. Free checks first: OpenAI/Gemini script --dry-run; Higgsfield account status (plan, balance) and generate cost <id> <flags> / generate cost workflow / --cost-only. Then ask the user once per batch with route, model, count, size, quality and the estimate (credits or $), folding any open choices into labeled options and, for characters, the pre-prompt check bullets. Draft at count 1, low quality or the cheap model; scale only the winner [fal-ai-media, image cost tips, higgsfield]. Never auto-retry an uncertain billable call [imagen, higgsfield dtc-ads].
  7. Compose and export. Overlay copy, logo and CTA in HTML/CSS using the banner rules; capture at exact px with Chrome headless or Playwright at 2x scale after a 3-5 s font/image wait [design social-photos, banner-design]. Video overlays and sound go in post (Remotion, Hyperframes, CapCut, ffmpeg) [video, product-360 corrected].
  8. Validate like a reviewer. Check subject, style, composition, text spelled right (zoom in), edit invariants held, real-product fidelity (print, logo, colorway, cut), identity held across a set, safe-zone crop at real display size, contrast >= 4.5:1, file size within platform limit [imagegen, banner-design, image, banana-pro-director-30]. Iterate with one change at a time and repeat the invariants in every edit round [imagegen].
  9. Optimize and deliver. Download Higgsfield result URLs; web assets get the optimization checklist [image]. Save finals into the project's asset folder by its convention, never overwrite (write hero-v2.png), keep only selected finals, put drafts in the scratchpad. Report path (and source URL), final prompt or intent line, route/model/settings, and the real cost (balance before vs after for credits) [imagegen, higgsfield].

Video runs the same frame -> context -> route -> gate -> validate loop: script first (problem -> solution -> CTA), then pick programmatic, AI footage (Seedance), Marketing Studio ad, avatar or screen recording with the video approach table, captions always, and export per platform aspect [video]. Image-to-video from an approved still (a scene plate or a product photo) is the most controllable path [fal-ai-media, banana-pro-director-30].

Core rules and checklists

Which generator and model [new: higgsfield-generate catalog + image tree + the user's setup]

  1. The ladder in workflow step 3 comes first: code, screenshots and real photos beat any generator.
  2. Higgsfield is the default paid route for images, video, audio and 3D when higgsfield account status shows credits: one credit pool for most model families, a free cost estimate, product and marketplace enhancers, and the CLI is installed. The user is on the free plan, so the pool is small: check the balance before promising a batch.
  3. OpenAI direct (image_gen.py) when Higgsfield is out of credits or logged out, when the job needs a transparent background, a mask inpaint, input_fidelity or the script's JSONL batch, or when the user asks. Always pass --model gpt-image-2.5-sunburst (OpenAI's named replacement per the image member; -flare is the other variant) after checking OpenAI's models/deprecations page, since Higgsfield already serves GPT Image 2.6 and a newer direct id may exist. Never rely on the script default gpt-image-1.5 (retires 2026-12-01); gpt-image-1 retired 2026-10-23, so any note naming it is stale. The key is exported, so a real call bills the user's OpenAI account at once.
  4. Gemini direct only when the user wants Google billing or a Gemini-only feature; the Nano Banana models are on Higgsfield.
  5. fal stays off: Higgsfield covers the same families (Nano Banana, Seedance, Kling, Veo) plus audio. Ideogram, Midjourney, Runway, HeyGen: recommend only.
JobHiggsfield route (id or command)Fallback / note
Brand product visual from the real product photoproduct-photoshoot create --mode <mode> --image <photo>OpenAI edit with the photo
Marketplace listing setmarketplace-cards create --scope main|product-images|aplus|full-setHTML composition over real photos
General image, design, UI mock, short text in pixels, editsgpt_image_2_6OpenAI direct gpt-image-2.5-sunburst
Animated GIF or SVG from a promptgpt_image_2_6 --output_format gif|svgGIF: Pillow builder is free
Cartoon or illustrated mascot, heavy texturenano_banana_flash (Nano Banana 2)Gemini direct
New original photoreal person (UGC, editorial, fashion)text2image_soul_v2--soul-id for a trained identity
Cinematic still, concept moodsoul_cinematic
Character pipeline (face lock, outfit, 3-panel sheet, outfit swap)nano_banana_pro; GPT Image for chest-up detail; soul_cinematic for cheap face explorationprompt-craft reference
One-shot face sheet or face edit from reference photosseedream_v5_pro
Environment, no peoplesoul_location
Vector, icon, logo conceptrecraft_v4_1 --model_type vectorfinals in brand-studio
Same person or look across many imagestrained Soul + text2image_soul_v2, or nano_banana_pro with reference imagesFlux multi-reference (fal, off)
Style transfer, typography remix, a look unlike the defaults (when named)Flux 2.0 / Flux Kontext MaxIdeogram (best text-in-image) and Midjourney: not set up
Cheap drafts (only when cheaper/faster is wanted)z_image, nano_banana_2_lite
Video: default (motion, image-to-video, multi-shot, 4-30 s, up to 1080p)seedance_2_5
Video: native 4K (4-15 s)seedance_2_0say why you switched
Video: cheaper or faster (only when asked)kling3_0_turbo, Veo 3.1 Lite, Seedance 1.5 Pro
Ad video (UGC, unboxing, tutorial, review, try-on, TV spot)marketing_studio_video
Branded ad imagemarketing-studio dtc-ads generate --format-id or marketing_studio_image
Reframe a video / edit it from a sketched frameworkflow reframe / draw_to_video
Sound effect, ambience, voice-style, music bedseed_audioElevenLabs not set up
GLB mesh from 1-4 product photosmulti_image_to_3d --should_texture true
Score a finished videobrain_activity

Gotchas [higgsfield-generate]: nano_banana_2 is an alias for Nano Banana PRO; Flare is its own id, never --variant; prompt-only models (Z Image, Recraft, Soul Cast, Soul Location) reject media flags; Cinema Studio ids are missing from model list (use model get); never pick an older model because its schema looks simpler; a model the user names stays for follow-ups. Cost: credits vary with model, resolution, duration and count. The members only rank them: GPT Image costs more than Banana Pro; Z Image, Nano Banana 2 Lite, Kling 3.0 Turbo, Veo 3.1 Lite and Seedance 1.5 Pro are the budget picks. Never quote a number from memory: run the cost command. Commands, params, modes and errors: references/higgsfield.md.

Providers on the user's machine [imagegen, imagen, fal-ai-media, image, higgsfield-*]

ProviderStatusBest atHow to run
HiggsfieldCLI via Homebrew; log in once with higgsfield auth login; higgsfield account status (free) confirmsmost image and video models, product/marketplace enhancers, Marketing Studio ads, Soul ID, audio, 3D, video scoringhiggsfield generate create <id> --prompt "..." --wait after generate cost; never the vendor curl | sh installer
OpenAI GPT ImageOPENAI_API_KEY set in the shell; openai SDK on python3.12transparent background, masks, edits with up to 16 input images, n=1-10, JSONL batchpython3.12 <skill>/members/imagegen/scripts/image_gen.py generate --model gpt-image-2.5-sunburst --size 1536x1024 --quality low --out <path> --dry-run (also edit, generate-batch; sizes 1024x1024, 1536x1024, 1024x1536, auto); drop --dry-run after the user's OK
Google Gemini image (Nano Banana)GEMINI_API_KEY kept in a credentials file, not exportednative editing, multi-image referencepython3.12 <skill>/members/imagen/scripts/generate_image.py --model <id> --size 2K "<prompt>" <new>.png (1K, 2K, 4K), key exported for that one command only; helper uses generateContent
fal.ainot set up: no key, no MCPsame families as HiggsfieldOff; recommend only if Higgsfield lacks a model the user needs
Ideogram, Recraft direct, Runway, HeyGen, ElevenLabsnot set upIdeogram text-in-image, Runway motion control, HeyGen avatars (has MCP), ElevenLabs voiceRecommend with the install/signup step; the user decides

Use the bundled scripts as they are: no edits to them and no one-off SDK runners [imagegen].

Prompt schema (direct model calls) [imagegen + image]

Use case: <slug: photorealistic-natural | product-mockup | ui-mockup | infographic-diagram | logo-brand |
           illustration-story | stylized-concept | historical-scene | text-localization | identity-preserve |
           precise-object-edit | lighting-weather | background-extraction | style-transfer | compositing | sketch-to-render>
Asset type: <where it will be used, px>
Primary request: <one line>
Input images: <Image 1: role; Image 2: role>
Scene/backdrop | Subject | Style/medium | Composition/framing | Lighting/mood | Color palette | Materials/textures
Text (verbatim): "<exact text>"
Constraints: <change only X; keep Y unchanged>   Avoid: <no logos, no watermark, no extra text>
  • Order: scene -> subject -> details -> constraints. Name the intended use; it sets polish level [imagegen].
  • Always state aspect ratio or px (on Higgsfield as the --aspect_ratio flag, not prompt text) and a style word ("clean commercial photography", "flat illustration", "3D render").
  • Photoreal: camera language (lens, depth of field, light direction). Leave negative space where copy will sit.
  • Text in pixels: 3-5 words max, quoted verbatim, tricky words spelled letter by letter; anything longer goes in an overlay [imagegen, image]. Logo placement by prompt is unreliable: add logos in post [image].
  • Multi-image input: refer to images by index and say what each contributes. Reuse a seed when iterating [fal-ai-media].
  • Image-to-image: describe the change, not the input; phrase positively ("tack sharp", not "no blur") [higgsfield-generate].
  • For batches: test 3-4 style prompts, pick the winner, save that exact prompt as the template, feed the winner back as a style reference, then vary only the subject [image batch workflow].

Paid-call request and delivery report [imagegen report + fal cost check + imagen data rules + higgsfield cost]

Ask once, before any billable call or batch:

Paid generation request: <route> <model or command/mode>, <n> output(s) at <size/res/duration>, quality <...>
Estimated cost: <N credits from `generate cost` (balance B) | $ from provider pricing | unknown until a count-1 run>
Uploads: <files that go to the provider, or none>. Prompt has no private data.
Why AI and not code/screenshot/photo: <one line>. Draft first at <cheap setting>, final only for the pick.
Options (defaults marked): <labeled choices, if any>. OK?

Deliver with: final file path(s), px and source URL, the final prompt or intent line, route/model/settings, real cost, what was checked (text, invariants, product fidelity, crop), and any assumption made.

Never AI-generate these [image, video]

Product UI (hallucinated interfaces), real locations people know, logos as finals, paragraphs of text, and the product being sold from text alone. A product image or video is AI-made only when conditioned on the user's real product photo or design file (PRODUCT-PHOTO, MARKETPLACE-CARDS, PRODUCT-360, AI-EDIT composite).

Real product in AI imagery [image + higgsfield product members + seedance-product-360]

  • Pass the real product photo or the design file every time (--image); text-only product renders never ship.
  • Compare each output with the real product: print artwork position, scale, colors and spelling; logo; colorway; garment cut and fit; proportions. Prints and small text are where models drift most: reject drifted ones rather than fixing in prose.
  • Marketplace images: check the target marketplace's current rules before upload (Amazon main image: pure white, product about 85% of the frame); a full-set is 13 jobs, so cost it as 13.
  • Label AI-made content where TikTok, Meta or Amazon require it.

Higgsfield job rules [higgsfield-generate, product-photoshoot, marketplace-cards, soul-id]

  • Run with --wait (one command, blocks, prints the URL); --json only for chaining. Timeouts may still bill: check higgsfield generate list --json before any rerun.
  • Every local path in a media flag is uploaded to Higgsfield. Product/brand-kit import from a URL: the user's own store or site only.
  • Enhancer commands own their prompt: pass a short intent; never call gpt_image_2 directly for product shots (worse output) and never paste the enhanced prompt back.
  • Marketing Studio: an ad reference video OR hook/setting blocks, never both; --hook_id/--setting_id only on ugc, ugc_how_to, ugc_unboxing, product_review, ugc_virtual_try_on; arrays as @file.json; DTC ads need a format the user picks; custom avatars only from consented faces.
  • Discovery: run the unfiltered higgsfield model list --json / workflow list before saying a model or feature is missing.

Character and scene prompt craft [banana-pro-director-30; full guide in references/higgsfield-prompt-craft.md]

  • Order: existing-or-new check -> text spec -> Mode 0 face lock -> Mode 1 base outfit plate -> Mode 2A 3-panel sheet (headless front, rear, tight chest-up face) -> Mode 3 scene plates on request; Mode 4 detail and Mode 5 outfit swap on explicit request. Never skip or combine steps: every later image anchors to the locked face.
  • Reference plates (Modes 0, 1, 2, 5) close with the flat grade: one even 18% gray value, shadowless matched-fill light, zero cast shadow, true skin and fabric color, baseline black camisole or ribbed tank for face locks. Gray, because video models amplify high-contrast edges; flat, because baked shadows get inherited by every later generation.
  • References carry identity and geometry: one short visual handle per subject, words spent on composition, pose, light and the close; under about 2,500 characters with strong references.
  • Scene plates: five unlabeled DP-prose paragraphs, resolution-aware detail (drop what the lens couldn't resolve), positional words instead of coordinates, the cinema-stack close with "photographed not generated".
  • Universal: no character names or ages, flattering realism (fine even skin, never blemished), closed-lip default expression, no negative-prompt blocks, aspect ratio only as a flag.

Product 360 and reveal video [seedance-product-360, corrected; full guide in references/product-360.md]

  • Beats: 2 s hook matched to the category's energy -> hero angle -> rotation (slow 10-15 s, medium 5-8 s, fast 2-4 s per 360) -> 2-3 macro details (2-5 s total) -> optional context -> finale on the hero angle.
  • Product fills 50-80% of the frame; product-to-background contrast at least 3:1; light per category and material table.
  • Seedance limits: 2.5 = 4-30 s up to 1080p; 2.0 = 4-15 s up to 4K. Longer stories are several shots (start/end frames from the same shoot) joined in the edit. One shot per prompt, under about 200 tokens; the long template is a planning sheet.
  • Names, specs, prices and CTA are overlays in post; sound is native Seedance 2.0 audio, seed_audio, or music in the edit.

Layout rules for banners, social and OG images [banner-design + design social-photos]

  • Safe zone: critical content in the central 70-80%; nothing within 50-100 px of edges; YouTube channel art keeps content inside 1546 x 423 of 2560 x 1440; Meta/Instagram central 80% (UI chrome).
  • 3-zone hierarchy: top = logo or value prop, middle = message + visual, bottom = CTA.
  • One CTA, high contrast, bottom-right, >= 44 px tall, action verb (Get, Start, Claim, Shop).
  • Max 2 typefaces; body >= 16 px, headline >= 32 px; contrast >= 4.5:1; ads <= 7 words a line and 3 lines.
  • Text share: paid social ads under 20% of the canvas; social covers about 60/40 image to text.
  • Print: 300 DPI (150 for large format), CMYK, 3-5 mm bleed, headlines 70 pt+ for 3-5 m viewing.
  • File names: project convention first; otherwise assets/banners/<campaign>/<style>-<w>x<h>.png, date prefix YYMMDD- for time-bound campaigns [banner-design].

Export (free, local) [design social-photos, banner-design]

CHROME="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
"$CHROME" --headless --disable-gpu --hide-scrollbars --force-device-scale-factor=2 \
  --window-size=1200,630 --virtual-time-budget=5000 --screenshot=og.png "file:///abs/path/og.html"

Then confirm pixel size (sips -g pixelWidth -g pixelHeight og.png) and that fonts loaded. With 2x scale the file is 2400 x 1260: downscale to the platform size if it has a hard limit. Playwright MCP (browser_resize + browser_take_screenshot) is the alternative when the page needs interaction first.

Enhance and optimize [image + image-enhancer, made concrete]

  • Measure first: dimensions, format, file size, what is wrong (blur, noise, artifacts, too large).
  • Keep the original as a sibling (name-original.png); write name-enhanced.png. Tune for the intended use (web, slides, print). Folders: loop the same steps per file and report size and dimensions before vs after.
  • Screenshots: re-capture at 2x device scale instead of upscaling; upscaling adds no real detail.
  • Photos/graphics (Pillow is on python3.12): upscale at most 2x with Image.LANCZOS, then ImageFilter.UnsharpMask(radius=2, percent=80-150, threshold=3); MedianFilter(3) only on visibly noisy photos.
  • Format: WebP default (photos and graphics), AVIF for max compression, PNG for transparency and UI text, SVG for logos and icons, JPEG as fallback. cwebp -q 80 in.png -o out.webp is installed; sips -Z <px> resizes.
  • Web checklist: quality 75-85 for photos, near-lossless for screenshots; hero under 200 KB; resize to display size; explicit width/height (no layout shift); loading="lazy" below the fold; descriptive alt text; CDN auto-format.
  • OG/social preview: 1200 x 630 plus og:image, og:image:width, og:image:height, twitter:card=summary_large_image, twitter:image; for many pages generate per-page OG images with @vercel/og / Satori [image].

Video [video + remotion-video-creation + higgsfield-generate]

  • Prompt = subject + action + camera move + style + mood; name the camera move (dolly, pan, static, pull back). Image-to-video is more controllable than text-to-video [fal-ai-media]. No readable text from AI video: overlay it.
  • Seedance 2.5 modes: t2v (prompt only, no media), omni_reference (any references incl. --start-image / --end-image), video_edit, video_extension. Reframe an existing clip with the reframe workflow instead of regenerating it [higgsfield-generate].
  • Captions always (most social video plays muted). Aspect: 9:16 social, 16:9 YouTube/site, 1:1 or 4:5 feed.
  • Hyperframes vs Remotion: plain HTML/CSS + GSAP, short templated clips, no React project -> Hyperframes (one HTML file per composition: root data-composition-id, data-duration, data-width, data-height; clips class="clip" with data-start, data-duration, data-track-index; paused GSAP timeline registered in window.__timelines). React project, spring physics, rich captions, 3D/Lottie, or Lambda batch rendering -> Remotion.
  • Remotion hard rules: every animation comes from useCurrentFrame(); write timings in seconds times fps from useVideoConfig(); CSS transitions/animations and Tailwind animate-* classes do not render; reference public/ files with staticFile(); premount every <Sequence>; composition props must be JSON-serializable. Open the matching rules/*.md (captions, audio, fonts, transitions, charts, 3d, measuring-text) before writing that part.
  • Pin tool versions in commands (npx hyperframes@<version>, npx create-video@<version>) and say in one line what gets installed. Remotion's license is free only below a company-size limit: check remotion.dev/license before commercial use.
  • Avatars: Marketing Studio UGC presenters (Higgsfield, set up), HeyGen (best lip-sync, MCP, not set up) or Synthesia (corporate). Not for founder-authentic content or UI walkthroughs.
  • Repurposing chain: clean up (Descript) -> auto-clip (Opus Clip) -> captions/styling (CapCut) -> schedule. Virality Predictor can score the cut's hook before posting; it is an attention proxy, not a sales result.

Generative art [algorithmic-art]

  1. Write the algorithmic philosophy (named movement, 4-6 paragraphs) as .md; weave in one quiet conceptual reference.
  2. Read templates/viewer.html and build on it: seed section (display, prev/next, random, jump) and actions (regenerate, reset) stay; algorithm, params object and parameter controls change.
  3. Seeded everything (randomSeed(seed); noiseSeed(seed)); same seed must give identical output; params are quantities, scales, probabilities, ratios, angles, thresholds. Thoughtful palettes, real-time performance.
  4. Single self-contained HTML; p5.js from cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js (allowed by the Artifact page policy).
  5. Published as an Artifact, the page cannot start downloads: drop the Download PNG button or use the artifact file hand-off capability (artifact-capabilities skill). In a local HTML file the button works.

GIFs [slack-gif-creator]

  • Slack: emoji 128 x 128 (under 3 s), message GIF 480 x 480; 10-30 fps; 48-128 colors.
  • Build frames with Pillow primitives through core.gif_builder.GIFBuilder; ease motion with core.easing.interpolate (ease_out, bounce_out, back_out, elastic_out); check with core.validators.is_slack_ready.
  • Make it look crafted: lines width >= 2, gradient backgrounds, layered shapes, glows, contrasting outlines; no emoji fonts.
  • Motion recipes in the member: shake, pulse/heartbeat, bounce, spin/wobble, fade, slide with overshoot, zoom, particle burst; combine two for richer loops.
  • Optimize only when asked: fewer frames, fewer colors, smaller size, remove_duplicates=True, optimize_for_emoji=True.
  • Setup: Pillow is on python3.12; imageio and numpy are not, so install them pinned into a scratchpad venv and say so. Import the helpers with sys.path.insert(0, "<abs path of members/slack-gif-creator>"); run from the scratchpad.
  • Photoreal or illustrated animated GIFs the builder can't draw: gpt_image_2_6 --output_format gif (paid), then validate size and colors with the same validators.

When members disagree

BetweenConflictRule
imagegen vs Claude Code realityimagegen prefers a built-in image_gen tool and allows its CLI only "when explicitly asked"Claude Code has no built-in image tool, so the CLI is the OpenAI path. "Explicitly asked" becomes "the user approved this paid call"
imagegen script vs OpenAI retirementsscript defaults to gpt-image-1.5 (retires 2026-12-01); fal-ai-media's note still offers gpt-image-1 (retired 2026-10-23)Always pass --model gpt-image-2.5-sunburst after checking OpenAI's page; treat any gpt-image-1 mention as stale
higgsfield-generate vs the user's spend rulevendor: don't pre-estimate cost or offer cheaper models unless askedKeep the quality default model, but always run the free cost check and ask once per batch; offer the cheap draft as an option, never swap silently
higgsfield-generate vs product-photoshoot vs banana-pro vs the user's autonomy ruleone question at a time / up to 4 labeled questions / a pre-prompt check every prompt / ask only blockersOne message: defaults as labeled options + pre-prompt bullets (references first) + the cost line. Skip it for small tweaks on an approved prompt
product members vs "never AI-generate the product"product-photoshoot, marketplace-cards and product-360 generate the productAllowed only when conditioned on the real product photo; verify against the real product; text-only product renders never ship
higgsfield-generate auto-pick vs banana-pro-director-30vendor: character sheets -> Seedream 5.0 Pro, Nano Banana Pro only when named; director: Banana Pro for face lock and sheetsInside the director pipeline its models count as named (its prompts are written for them); one-shot face sheets from photos -> seedream_v5_pro
banana-pro-director-30 internal"cinema stack closes Modes 0-5" vs "flat grade, no exceptions"; Mode 4 beauty lighting; 6-panel three-point light; Mode 0 "white background"Every reference plate gets the flat 18% gray grade; the cinema stack only on finished stills (Mode 3 prose, Mode 4 as a deliverable, white-card stills)
banana-pro-director-30 internal"no @image tags" vs the locked Mode 5 prompt using @image1/@image2Mode 5 is the one exception; pass the outfit reference first and prove the order on a count-1 run
banana-pro-director-30 vs higgsfield prompt safetyreal brand names allowed vs avoid trademarks (ip_detected)the user's own brands fine; third-party names only when the user asks; otherwise use original designs
seedance-product-360 vs media-studio video rulestext overlays and 20-28 s single prompts inside Seedance; Seedance "5-60 s"Overlays in post; one shot per prompt under ~200 tokens; respect 4-30 s (2.5) and 4-15 s (2.0)
seedance-product-360 vs evidenceray tracing, particle systems, text animation, "Higgsfield logo fine on Amazon"Dropped as unsourced; platform rules checked on the platform
higgsfield delivery vs imagegen deliveryURLs only, no ids vs local path, prompt, provider, costBoth: URL + downloaded local file + model + credits spent; no enhanced prompt unless asked
higgsfield bootstrap vs the user's security rulesrun the vendor curl-pipe-sh installer when the CLI is missinginstall the CLI from Homebrew; never run the installer; upgrades only with the user's OK
product-photoshoot vs prompt schema"never write the GPT Image 2 prompt yourself" vs the shared schemaSchema for direct model calls; enhancer commands take a short intent line
banner-design vs imagegenbanner: generated visuals carry no text; imagegen: quote exact text in the promptHTML-composed assets: no text in pixels. Flat raster pieces where text must be baked in (poster, sticker): 3-5 words, verbatim, use a text-strong model, verify spelling
image vs brand-studio's design member vs Recraft on Higgsfieldimage: AI logos are poor; design: generate logos with Gemini in 55 stylesAI makes logo concepts only (paid, ask); finals are hand-built SVG in brand-studio
imagegen vs imageimagegen: do not add details the user did not imply; image: always add style, lighting, aspectAlways add format and style words; add creative content (objects, brands, palettes) only if implied
algorithmic-art vs the user's brandskeep Anthropic colors and fonts in the viewerKeep the template's structure and controls; for the user's brand work, swap the UI colors/fonts for the project's tokens. Keep Anthropic styling for neutral exploration
video vs remotion-video-creationHyperframes "recommended for agents" vs Remotion rulesChoose by the rule in Core rules > Video; don't port an existing Remotion project to Hyperframes
banner-design vs the user's autonomy rulegather 6 answers via questions firstAsk only blockers; default the rest and list assumptions in the delivery
imagegen vs banner-design vs brandoutput paths output/imagegen/ vs assets/banners/<campaign>/ vs brand asset namingProject convention first; then the asset-type default; drafts in the scratchpad
fal-ai-media vs reality"unified media via fal MCP"fal is not set up and Higgsfield covers its models; recommend only if a model is missing
image-enhancer vs honestypromises "upscaled to 4K, enhanced clarity"Upscaling adds no detail; re-capture when possible and report what was actually done
code-drawn site imagery vs AI photos/videobanana-pro and seedance notes favour code-drawn scenes; Higgsfield allows AI imageryFollow the user's brand: code-drawn scenes can stay the signature, AI hero loops, lifestyle, try-on and 360 are allowed, each batch cost-checked

Combine with

  • Built-in skills: anthropic-skills:canvas-design (posters, static art), anthropic-skills:algorithmic-art (same as the member), artifact-design before publishing any page, artifact-capabilities for file hand-off or stored picks, frontend-design:frontend-design for type-led banners, dataviz when an image carries a chart.
  • Superpowers: superpowers:brainstorming before a new visual direction, campaign or recurring character; superpowers:dispatching-parallel-agents for large variant sets (one agent per size or style; paid jobs still go through one approval); superpowers:verification-before-completion before "done".
  • Agent prompts (~/.claude/skill-library/agents/voltagent/): 06-developer-experience/visual-asset-generator.md (asset checklist for app icons, favicons, OG, social banners; skip its npm install -g prompt-to-asset step, that package is unreviewed), 01-core-development/ui-designer.md (visual polish of composed assets), 01-core-development/frontend-developer.md (Remotion or Hyperframes builds), 08-business-product/content-marketer.md (what the asset should say and where it goes), 05-data-ai/prompt-engineer.md (tighten a long prompt template under the ~200-token limit).
  • Other super-skills: brand-studio (logo, palette, tokens), ads-and-measurement (ad creative strategy and ad specs), copy-and-content (headlines on the asset), conversion-lab (hero image placement, A/B tests of creatives), commerce-pro (uploading product media and listings to Shopify or marketplaces).

House rules (the user)

  • Paid generators ask first: Higgsfield credits (every job, incl. Virality Predictor and Soul training), OpenAI images, Gemini, fal, ElevenLabs, HeyGen, Runway and any AI upscaler. One question per batch with route, model, count, settings and the estimate; the dry run, account status and generate cost are free.
  • Use the API or CLI route (scripts, Higgsfield CLI, Chrome headless, Playwright MCP) before clicking through a web UI; if a browser is truly needed, say why in one line.
  • Keep keys in one credentials file outside any repo; export GEMINI_API_KEY only for the one command that needs it; never print or paste a key and never open ~/.config/higgsfield/.
  • Uploads to Higgsfield (product photos, design files, faces, videos, product or brand URLs) only for files the user approved for that batch; URL imports only from the user's own store or site.
  • Faces: Soul ID, face locks, custom avatars and outfit swaps use only the user's own face with their say-so or a person's clear written OK; never recreate a real person's likeness. Soul training needs a paid Higgsfield plan (check the plan with higgsfield account status).
  • Anything that publishes, posts or uploads an asset to a live store, marketplace, site or social account asks the user first; label AI-made content where TikTok, Meta or Amazon require it and check marketplace image rules before a listing upload.
  • Store and conversion work: every visual must help a visitor buy. Real product imagery near the buy button, no explainer graphics; cost-check each batch.
  • Installing a new tool (fal MCP, Hyperframes, imageio, a Higgsfield upgrade) means a reviewed source, a pinned version and one line telling the user; no curl-pipe-bash installers. Members without an upstream license are for personal use only; never republish their text.

Members

MemberBest atPath
imagegenOpenAI GPT Image CLI (generate/edit/batch, masks, transparency), use-case taxonomy, prompt schema, invariant-first editing, save-path hygienemembers/imagegen/SKILL.md, references/{prompting,sample-prompts,cli,image-api}.md, scripts/image_gen.py
imagenGemini image helper (stdlib only, PNG validation, no auto-retry of billable calls)members/imagen/SKILL.md, scripts/generate_image.py
fal-ai-mediaOne API for image, video and audio models; seeds; cost estimation; model discoverymembers/fal-ai-media/SKILL.md
imageMarketing image production: model-choice tree, placement workflows (hero, social, mockups, banners), web optimization, OG tags, OpenAI retirement datesmembers/image/SKILL.md, members/image/references/ai-image-prompting.md
banner-designMulti-option banner process, 22 art directions, safe zones, CTA and type rules, print specs, export namingmembers/banner-design/SKILL.md, members/banner-design/references/banner-sizes-and-styles.md
videoVideo approach choice (programmatic, AI, avatar, repurpose), AI video model table, edit-anatomy beat sheet, scripted demo recordingmembers/video/SKILL.md, references/{ai-video-prompting,edit-anatomy,product-demo-recording}.md
remotion-video-creation28 Remotion rule files (animation, sequencing, captions, audio, fonts, transitions, 3D, charts)members/remotion-video-creation/SKILL.md, rules/*.md
algorithmic-artPhilosophy-first p5.js generative art with seeded variation and an interactive viewer templatemembers/algorithmic-art/SKILL.md, templates/viewer.html
slack-gif-creatorSlack GIF limits, GIFBuilder, easing, validators, animation recipesmembers/slack-gif-creator/SKILL.md, core/*.py
image-enhancerEnhancement intent (screenshots for docs, social, slides; keep originals); the concrete method is in Core rulesmembers/image-enhancer/SKILL.md
higgsfield-generateHiggsfield CLI: model catalog and auto-picks, media flags, cost commands, Marketing Studio ads, DTC ads, brand kits, workflows, Virality Predictor, 3D, audio, errorsmembers/higgsfield-generate/SKILL.md, references/{model-catalog,media-inputs,workflows,marketing-*,prompt-engineering,troubleshooting}.md; merged in references/higgsfield.md
higgsfield-product-photoshoot10 product-photo modes with a backend prompt enhancer, mode tie-breakers, short labeled interviewmembers/higgsfield-product-photoshoot/SKILL.md
higgsfield-marketplace-cardsMarketplace main, secondary and A+ image sets by scope or asset listmembers/higgsfield-marketplace-cards/SKILL.md
higgsfield-soul-idFace identity training: photo rules, variants, use with Soul modelsmembers/higgsfield-soul-id/SKILL.md, references/{photo-guide,troubleshooting}.md
banana-pro-director-30Photoreal character pipeline (face lock, outfit plates, 3-panel sheets, outfit swap), flat-grade reference plates, cinema-prose scene plates, anti-AI-look render rulesmembers/banana-pro-director-30/SKILL.md; merged in references/higgsfield-prompt-craft.md
seedance-product-360Product video craft: hooks, hero angles, light per category and material, rotation and camera library, multi-angle photo plans, overlay timing, review checklistmembers/seedance-product-360/SKILL.md; corrected and merged in references/product-360.md

If a member folder is missing (not installed), work from this file alone.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.