agentleFS
itqanlabitqanlab/agent-toolkit/.agents/skills/higgsfield-studio-product-photoshoot/SKILL.md

higgsfield-studio-product-photoshoot

Skill1 starsChanged 4 days agoMITView on GitHub

Make brand-quality product photos with Higgsfield: studio, lifestyle, Pinterest pins, hero banners, carousels, ad packs and try-ons. Triggers: 'product photo', 'studio shot of my product', 'lifestyle image of this bottle', 'make a Pinterest pin', 'hero banner for my site', 'ad creative pack', 'model wearing my product', 'restyle this photo for Christmas'. Part of Higgsfield Studio: each shoot is planned and priced for free before any image is made, never paid for twice, and written to a ledger. Needs Node 18+ and the higgsfield command line tool.

The file

Show its rules and text

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Put --max N (a little above the price), --tag and --why "..." on every paid job.

    line 42
  2. Very specific:

    Ask before spending more than about 10 credits, or 10% of what is left.

    line 43
  3. Distinctive:

    Before any other command:

    line 63
  4. Very specific:

    If higgsfield is not on $PATH, install it:

    line 65
  5. Very specific:

    If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and …

    line 69
  6. Distinctive:

    Ask at most 4 short questions before submitting.

    line 75
  7. Distinctive:

    Never write the gpt_image_2 prompt yourself — backend assembles it.

    line 77
  8. Distinctive:

    Ask 3–4 short questions before submitting.

    line 118
  9. Distinctive:

    If not, describe the product — category, packaging, color, distinctive features.

    line 138
  10. Distinctive:

    After answers → return to the relevant Type A–E.

    line 166
  11. Very specific:

    Use 2k for every product-photoshoot job.

    line 221
  12. Distinctive:

    Does not write gpt_image_2 prompts directly.

    line 236
  13. Very specific:

    Does not auto-pick a different image-gen model.

    line 237
  14. Very specific:

    Does not replace higgsfield-generate Marketing Studio for branded video / avatar workflows.

    line 238
  15. Very specific:

    Does not replace higgsfield-generate for raw text-to-image without a product or brand context.

    line 239

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Higgsfield Product Photoshoot

Higgsfield writes the final image prompt from a mode and a short intent, then renders each image. The guard plans the shoot first with Higgsfield's free --enhance-only step and prices every planned image, so the user sees the full price before anything is made.

What it costs

Each image is a gpt_image_2 render at 2k, quoted at 6.5 credits on 2026-10-12. A --count 2 shoot was quoted at 13. --count 5 is about 33 credits. Start with --count 1, show it, then make more.

node ../higgsfield-studio/scripts/hf.mjs photoshoot --mode lifestyle_scene --prompt "cold-brew bottle on a sunlit kitchen counter" --image bottle.jpg --count 1 --dry
node ../higgsfield-studio/scripts/hf.mjs photoshoot --mode lifestyle_scene --prompt "cold-brew bottle on a sunlit kitchen counter" --image bottle.jpg --count 1 --max 8 --out shoot/ --tag launch --why "first lifestyle shot"

Before anything else

sh ../higgsfield-studio/scripts/setup-deps.sh --check
node ../higgsfield-studio/scripts/hf.mjs check

The first checks Node and the higgsfield tool, and sh ../higgsfield-studio/scripts/setup-deps.sh installs what is missing after asking. The second checks the sign-in. If Higgsfield is not signed in, the user signs in once with higgsfield auth login, which opens the browser. Never print the sign-in token or open the CLI's credential file.

Spending credits

This skill is part of the Higgsfield Studio plugin. Every paid command runs through the main skill's guard, node ../higgsfield-studio/scripts/hf.mjs. It asks Higgsfield for the price before running, refuses above --max or below the reserve, never pays twice for the same request, and writes what each job really cost to .higgsfield/ledger.jsonl in the project. The full rules are in ../higgsfield-studio/SKILL.md. The short form:

  • Price first with --dry, using every parameter the real job will use. Tell the user the total for anything over about 5 credits.
  • Put --max N (a little above the price), --tag and --why "..." on every paid job.
  • Ask before spending more than about 10 credits, or 10% of what is left. node ../higgsfield-studio/scripts/hf.mjs account shows the balance.
  • Anything outward or not undoable goes through act and needs --yes. Say what will happen and wait for the user's yes before adding it.
  • Report in plain words, in the user's language: where the file is, what it cost, what is left. No JSON or job ids unless asked.

Free commands, such as lists, model get, presets and uploads, can run as node ../higgsfield-studio/scripts/hf.mjs run <command> or as higgsfield <command> directly.

Updates

This skill is versioned with its plugin. Its version is metadata.version in the header of this file. The plugin's history, for every skill in it, is in ../higgsfield-studio/CHANGELOG.md. To check for a newer version, open the address on its Latest: line and compare the top version with this one. Read every entry in between and tell the user what changed before anything is updated.

Higgsfield's guide

Everything below is Higgsfield's official guide for this task, with its paid and outward commands already pointed at node ../higgsfield-studio/scripts/hf.mjs. The rules above win where the two differ.

Product Photoshoot

Brand-image generation via the node ../higgsfield-studio/scripts/hf.mjs photoshoot command. The CLI calls a backend prompt enhancer that holds mode-specific photography vocabulary and structural templates, then submits to gpt_image_2 and returns image URLs.

Step 0 — Bootstrap

Before any other command:

  1. If higgsfield is not on $PATH, install it:
    sh ../higgsfield-studio/scripts/setup-deps.sh
  2. If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.

UX Rules

  1. Be concise. Print only image URLs in the final reply.
  2. Detect language, respond in it. Mode names and CLI flags stay English.
  3. Ask at most 4 short questions before submitting. Use labeled options, never open-ended.
  4. Skip questions whose answer is obvious from context (uploaded image, prior turn, brand memory).
  5. Never write the gpt_image_2 prompt yourself — backend assembles it.
  6. Polling is silent. Wait until URLs are ready, then deliver.

Modes

ModeWhen user wants…
product_shotProduct on neutral / studio / catalog background
lifestyle_sceneProduct in real-world environment, hands, action, atmosphere
closeup_product_with_personTight crop with hands / partial face — beauty application, holding, demonstrating
moodboard_pinVertical 2:3 Pinterest-native aesthetic, moodboard feel
hero_bannerWide-format website / email / campaign header
social_carousel3–10 connected slides for IG / LinkedIn / Facebook
ad_creative_packCoordinated pack of static ad variants for Meta / TikTok / Pinterest / Google Ads
virtual_model_tryoutProduct worn or used by an AI-rendered model
conceptual_productSurreal / CGI-style / levitating / splash / sculptural product
restyleTransform an existing image's aesthetic, mood, or seasonal context

Mode selection

Pick by intent, not surface keyword. When two modes could apply, prefer the more specific one.

  • product + neutral / clean / white / studio / catalog / Shopify → product_shot
  • product + scene / in use / kitchen / outdoor / cafe / gym → lifestyle_scene
  • hands holding / face with product / beauty application / demonstrating → closeup_product_with_person
  • Pinterest, pin, vertical pin → moodboard_pin
  • hero, banner, website header, landing page, email header, wide format → hero_banner
  • carousel, slide post, multi-slide, swipeable → social_carousel
  • ads, ad pack, paid social, Meta / TikTok / Pinterest ads → ad_creative_pack
  • model wearing, virtual try-on, on body, fashion shoot, lookbook → virtual_model_tryout
  • levitating, floating, splash, frozen motion, surreal, CGI, sculptural → conceptual_product
  • modify EXISTING image's aesthetic, mood, season — without changing subject → restyle

Tie-breakers:

  • "Pinterest pin of my product on a kitchen counter" → moodboard_pin (Pinterest is the platform)
  • "Hero banner showing my product in use" → hero_banner (banner format wins)
  • "Carousel of my product in different scenes" → social_carousel (multi-slide wins)
  • "Closeup of person applying my serum" → closeup_product_with_person (specific genre wins)

Pre-generation interview

Ask 3–4 short questions before submitting. Always labeled options, never open-ended. Skip a question whose answer is obvious from context.

Type A — uploaded a product photo, "make me images / photoshoots"

  1. How many? [1 / 3 / 5]
  2. What style/mood? [Clean studio / Lifestyle / Conceptual / With a model / Other]
  3. Where will you use them? [Shopify / Instagram / Pinterest / Paid ads / Website hero]
  4. Brand colors to match? (skip if obvious)

Type B — uploaded a product photo, named a use case

E.g. "make ads for my product", "make a Pinterest pin", "make a hero banner". Mode is obvious. Ask only the gaps:

  1. How many? (if multi-output mode)
  2. What's the offer / mood / hook?
  3. Anything in particular to emphasize?

Type C — text only, no product photo

  1. Can you upload a product photo? (preferred — much higher fidelity)
  2. If not, describe the product — category, packaging, color, distinctive features.
  3. What style? (same options as Type A)
  4. Where will you use it?

Type D — uploaded existing image, "redo / change vibe / different version"

→ restyle

  1. What aesthetic? [Clean girl / Cottagecore / Quiet luxury / Dark academia / Y2K / Other]
  2. Seasonal context? [Christmas / Valentine's / Halloween / Black Friday / None]
  3. What to preserve, what to change? (only if ambiguous)

Type E — model wearing a product (fashion, accessories)

→ virtual_model_tryout

  1. Model archetype? (suggest 2–3 based on brand audience)
  2. Environment? [Studio clean / Outdoor natural / Street style / Editorial / Home cozy]
  3. Framing? [Full body / Three-quarter / Waist up / Closeup on product area]

Type F — vague request, unclear subject

E.g. "make me something cool for my brand".

  1. What product or topic?
  2. Goal? [Sell on a marketplace / Build awareness / Run paid ads / Update website]
  3. Upload a reference image?

After answers → return to the relevant Type A–E.

Generation

Single command. Backend assembles the final prompt and submits to gpt_image_2. URLs print on stdout.

node ../higgsfield-studio/scripts/hf.mjs photoshoot \
  --mode <mode> \
  --prompt "<short user-intent description from interview answers>" \
  [--image <path-or-upload-id>]... \
  [--count <1-10>] \
  [--aspect_ratio <override>]

Examples:

node ../higgsfield-studio/scripts/hf.mjs photoshoot \
  --mode lifestyle_scene \
  --prompt "bottle of cold-brew on a sunlit kitchen counter, IG feed" \
  --image bottle.jpg \
  --count 3
node ../higgsfield-studio/scripts/hf.mjs photoshoot \
  --mode moodboard_pin \
  --prompt "vertical pin for my candle brand, cottagecore mood" \
  --image candle.jpg
node ../higgsfield-studio/scripts/hf.mjs photoshoot \
  --mode restyle \
  --prompt "Christmas version, quiet-luxury aesthetic" \
  --image existing-shot.jpg

Image inputs

--image accepts a local file path (auto-uploaded) OR an existing upload UUID. Repeat the flag for multiple references.

Multi-variant

--count 3 returns 3 distinct image URLs. Backend asks the enhancer to vary preset, lighting, angle, and palette across variants — they will not be paraphrased copies of one another.

For social_carousel and ad_creative_pack, count = number of slides / variants in the pack. Backend locks the visual system across all slides automatically.

Aspect ratio

Backend picks a sensible default per mode. Override with --aspect_ratio only if the user explicitly asks for a different one. Allowed values: 1:1, 4:5, 5:4, 3:4, 4:3, 2:3, 3:2, 9:16, 16:9.

Resolution

Use 2k for every product-photoshoot job.

Delivering results

Print the image URLs as a short bulleted list. No JSON, no IDs, no internal model names, no enhanced prompt text. If a job failed, mention it briefly with the failure status.

3 lifestyle shots ready:
- https://cdn.higgsfield.ai/.../job_abc.jpg
- https://cdn.higgsfield.ai/.../job_def.jpg
- https://cdn.higgsfield.ai/.../job_ghi.jpg

What this skill does NOT do

  • Does not write gpt_image_2 prompts directly. Backend owns prompt assembly.
  • Does not auto-pick a different image-gen model. Always gpt_image_2.
  • Does not replace higgsfield-generate Marketing Studio for branded video / avatar workflows.
  • Does not replace higgsfield-generate for raw text-to-image without a product or brand context.

Common mistakes to avoid

  • Asking more than 4 interview questions in a single message.
  • Picking the wrong mode (e.g. product_shot when the user wants a Pinterest pin).
  • Calling node ../higgsfield-studio/scripts/hf.mjs create gpt_image_2 --prompt ... directly instead of node ../higgsfield-studio/scripts/hf.mjs photoshoot — bypasses the prompt enhancer and produces noticeably worse output.
  • Pasting the assembled prompt back to the user — they want the URLs.
  • Using a --mode value not in the table above.

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.