higgsfield
Skill1 starsChanged 49 days agoMITView on GitHub
Generate videos and images with the pay-as-you-go Higgsfield API (api.higgsfield.ai) from inside a project - 79 models including Seedance, Kling, Wan, Minimax Hailuo, LTX, Grok Imagine, Soul, Ideogram, Recraft, Qwen Image and Marketing Studio. Price a request, upload reference media, submit, wait, and download to outputs/. Use when the user asks to create or edit a video or image with Higgsfield or any of these models.
- Reads credentials
10 other projects use a version of this.
Adopted by
Most recently taken up by
- JustinPerea/nebula-nodestheir own version, first seen Nov 5, 2026
- aaronjmars/miroshark-aeontheir own version, first seen Oct 21, 2026
- aeonfun/aeontheir own version, first seen Oct 20, 2026
- MiroShark/miroshark-aeontheir own version, first seen Oct 17, 2026
- aaronjmars/aeontheir own version, first seen Oct 8, 2026
- OSideMedia/higgsfield-ai-prompt-skilltheir own version, first seen Sep 27, 2026
Used with
Projects with it also use aeon-update, auto-workflow and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
aaronjmarsSkillaeon-update
Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.
Also in 4 projects that use this
aaronjmarsSkillauto-workflow
Two-mode aeon.yml workflow builder - analyze inspects URLs and emits a tiered, signal-verified skill-enablement plan plus an aeon.yml diff; enable flips slugs to enabled:true and opens a PR.
Also in 4 projects that use this
- +10 more from aaronjmars
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- aaronjmars/aeon★ 789same name
- aeonfun/aeon★ 789same name
- OSideMedia/higgsfield-ai-prompt-skill★ 788same name
- OpenCoven/coven★ 75same name
- robonuggets/higgsfield-skill★ 61same name
- Starchild-ai-agent/official-skills★ 32same name
- JustinPerea/nebula-nodes★ 23same name
- aaronjmars/miroshark-aeon★ 20same name
- MiroShark/miroshark-aeon★ 20same name
- mahshid1378/Owner-avatar-higgsfield-ai-prompt-skill★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If the user names a model, use it exactly (model id like kling-video-v3.0-pro-text-to-video or its endpoint …
- Very specific: line 14
If they don't, suggest one that fits the task (text-to-video, image-to-video, reference-to-video, video-edit, text-to-image, image edit) …
- Very specific: line 19
Write JSON to work/higgsfield/<job>.json with only parameters from info.
- Very specific: line 27
If it reports no USD price (some Seedance 2.0, Seedance 2.5 reference/edit/extend, Cinema Studio, Genjutsu, Marketing Studio …
- Distinctive: line 28
If the estimate itself fails with HTTP 500 (some Kling motion-control and video-edit models), say so.
- Very specific: line 34
If run times out: hf.py wait --job <name>, then hf.py download --job <name>.
- Distinctive: line 41
Call estimates estimates. The real charge is on the console usage page.
“Common” is measured: kept by at least 6 in 10 of the 9 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.
Files
Higgsfield generation
Helper: python <skill-dir>/scripts/hf.py (Python 3.8+, standard library only). JSON on stdout, progress on stderr. Run it from the user's project folder; jobs are recorded in work/higgsfield/jobs.db, files go to outputs/.
1. Pick the model
hf.py models [words]searches all models, e.g.hf.py models kling image.MODELS.mdin the skill folder lists them all with example prices.- If the user names a model, use it exactly (model id like
kling-video-v3.0-pro-text-to-videoor its endpointkling-video/v3.0/pro/text-to-video). Never swap to a different model or variant without asking. - If they don't, suggest one that fits the task (text-to-video, image-to-video, reference-to-video, video-edit, text-to-image, image edit) and mention its example price. Default for video:
bytedance-seedance-2.5-text-to-video, 5 s, 720p. hf.py info <model>shows every parameter (type, allowed values, default, required), outputs, pricing note, and an example. Read it before writing a request; parameters differ between models, even between variants of one model. For full details open the model'sagent_promptURL frominfo.
2. Build the request
- Write JSON to
work/higgsfield/<job>.jsonwith only parameters frominfo.hf.py validate --model M --input Fchecks it offline. - Local images/video/audio:
hf.py upload <file>returns apublic_url; put that URL in the model's field (image_url,image_urls,video_url,start_image_url, ...). Only upload files the user asked you to use. Supported: jpg, png, webp, gif, wav, mp4. - Marketing Studio product shots / ads with a preset:
hf.py presetslists preset ids; ask the user to choose; setenhance_prompt: true,preset_id, and the product image inimage_urls. Never invent preset ids. hf.py checkverifies the key for free. If credentials are missing, tell the user to fill~/.config/higgsfield/.env(HF_API_KEY_ID,HF_API_KEY_SECRET). Never ask for or print the key, and never put it in commands or project files.
3. Price it
hf.py estimate --model M --input F is free. Tell the user the number and whether it is exact from Higgsfield, computed, or an upper bound.
- If it reports no USD price (some Seedance 2.0, Seedance 2.5 reference/edit/extend, Cinema Studio, Genjutsu, Marketing Studio flare/sunburst, Minimax H3 reference): show the pricing text and ask whether they accept an unknown price. Only then add
--allow-unpriced. - If the estimate itself fails with HTTP 500 (some Kling motion-control and video-edit models), say so; ask before submitting without a price.
4. Generate
- A clear request to generate ("make a 5 s video of ...") authorizes that one generation at the quoted price. Asking for advice, prices, or installing the skill does not.
hf.py run --model M --input F --job <name>submits, waits, downloads. Use a short descriptive job name (beach-intro-v1). Add--max-usd Nor--budget NAME --budget-usd Nonly when the user sets a limit.- If
runtimes out:hf.py wait --job <name>, thenhf.py download --job <name>. Never resubmit to retry.
Protecting the user's money
- Same
--jobname is never charged twice. An identical request under a new name is refused unless the user wants another copy (--allow-duplicate). - Status
unknownafter submit means it may have been charged. Do not submit again. Get the request ID from the user (console or Higgsfield support) and runhf.py attach --job <name> --request-id <id> --model <m>. hf.py listshows all jobs with request IDs, status, estimates, files.hf.py cancel --job <name>works only while queued.- Call estimates estimates. The real charge is on the console usage page.
5. Check and report
Confirm the files exist and look at them (for video, extract a frame with ffmpeg) before describing the result. Report paths, model, settings, and estimated cost.
Keeping models current
python <skill-dir>/tools/sync_models.py re-downloads every model's agent prompt from Higgsfield and rebuilds models/ and MODELS.md. For one model: python tools/sync_models.py <endpoint>. Project-specific model files in work/higgsfield/models/ override bundled ones.
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
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.

