Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-marketing-studiogit clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-marketing-studio)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-marketing-studio"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-marketing-studio/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-marketing-studio"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-marketing-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00230 | $0.14763 |
| Opus 5.5 | $0.00092 | $0.05905 |
| Sonnet 5.5 | $0.00046 | $0.02953 |
| Haiku 4.5 | $0.00023 | $0.01476 |
Grade D, and why
higgsfield-marketing-studio scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
## 8. Output prompt style — flowing OR sectioned (NOT a hard rule) Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Default to flowing paragraph for prompts under 50 words. Use sectioned structure when the prompt has discrete beats (time-coded narrative, multi-clip campaign, explicit Style / Dynamic / Static separation). Don't impose How it starts
The opening of the file, as written. The whole thing — 765 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Marketing Studio
QUICK FACTS
Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.
- Hard duration cap: 4–15s per clip; out-of-range values get clamped; longer narrative = multi-clip sequence edited externally →
- 9 presets: UGC, Tutorial, Unboxing (
ugc_unboxing), Hyper Motion, Product Review, TV Spot, Wild Card, UGC Virtual Try On, Pro Virtual Try On → - Pro Virtual Try On slug is
virtual_try_on, NOTpro_virtual_try_on→ - Preset routing happens via
show_marketing_studio.mode—generate_videohas NOmodeparameter at all → - Hook + setting picklists on FIVE presets only: UGC, Tutorial, Unboxing, Product Review, UGC Virtual Try On (NOT Pro Virtual Try On) →
- 9 hooks (4 stunt / 5 subtle) as of 2026-05-18 — picklists drift; enumerate live for current UUIDs →
- 14 settings (8 realistic / 6 unrealistic) as of 2026-05-18, passed by UUID as
setting_id→ avatarsarray MUST contain exactly one entry; emptyavatars: []substitutes a random face per render — always pass one →- Two-person scenes: primary in
avatars, secondary as a reference image inmedias→ avatarsandmediasare top-level siblings ofparams— NOT nested underparams; wrong nesting rejects →promptis optional;aspect_ratioenum: auto/21:9/16:9/4:3/1:1/3:4/9:16;resolution: 480p/720p/1080p (default 720p) →get_costfor MS: the 2026-05 schema said unsupported; the 2026-09-26generate_videoschema no longer states that exception — untested either way, so tryget_cost: trueand keeptransactions(limit=200)as the post-hoc check →- Ad Multiplier (
ad_multiplier, "powered by Seedance 2.5"): many independently edited versions of ONE supplied 4–30s ad; same four modes as Seedance 2.5 incl. 1080p; Higgsfield's connector loads itsad-multiplierworkflow FIRST → - One object swapped in one clip is Genjutsu (
hf_mult_replace_object), not Ad Multiplier → - Three MS models exist:
marketing_studio_video(this skill),marketing_studio_image,ms_image— callms_image"DTC Ads" with users → - Three avatar types: preset (~40 in library), uploaded, text-generated →
- TV Spot has a default packshot beat — negate explicitly ("ABSOLUTELY NO PACKSHOT") when unwanted →
- Flowing AND sectioned prompt styles both render — "no section labels" is craft opinion, not an engine constraint; default flowing under 50 words →
- Cannot do: >15s clips, non-human lip-sync, multi-character dialogue, multi-setting single output, free-form hook/setting IDs, >1 avatar →
- Escape hatches when MS can't render it: Wan 2.7, Veo 3.1, Cinema Studio Video 3.0, Seedance 2.0, Kling 3.0 →
- Budget anchor: ~$0.06/credit ≈ ~$9 per video (the more credible of two non-canonical rate samples) →
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago Changed · +70 lines · +66 tokens per session db219ad14259
- 1mo ago First seen · 695 lines · 164 tokens per session scan D 137c1060d7f4
higgsfield-marketing-studio is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 230 tokens to every session and 14,763 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks the agent to reveal its instructions, tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.
workflows
Use in Freezone/虾画 chat when the user selects a Skill or asks to create, plan, analyze, or expand a dynamic canvas workflow for short drama, ads, ecommerce, product video, MV, text, image, video, or audio production.