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-content-factorygit 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-content-factory)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-content-factory"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-content-factory/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-content-factory"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-content-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 166 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00183 | $0.03417 |
| Opus 5 | $0.00092 | $0.01708 |
| Sonnet 5 | $0.00037 | $0.00683 |
| Haiku 4.5 | $0.00018 | $0.00342 |
Grade A, and why
higgsfield-content-factory scanned grade A with 0 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Content Factory — Campaign Orchestration Pipeline
A 5-stage pipeline that runs a full ad campaign on top of Higgsfield
Marketing Studio: Research → Plan → Generate → Publish → Report. Where
higgsfield-marketing-studio is the engine reference (what the presets,
parameters, hooks, and avatars are), Content Factory is the orchestration
layer that drives a whole campaign turn by turn — researching trends,
planning a dated content calendar, generating in batches, scheduling to ads,
and reporting cost savings.
Translated from Adil Aliyev's higgsfield-content-factory source skill, per
the v3.7.13 / v3.7.16 translation precedent. All Marketing Studio API
ground-truth — preset slugs, parameter schema, hook/setting/avatar handling
— lives in ../higgsfield-marketing-studio/SKILL.md and is NOT restated
here. This sub-skill carries the pipeline scaffolding the marketing-studio
sub-skill deliberately deferred. The publish + cost-report tail (Stages 4–5)
lives in the companion publish-and-report-workflow.md satellite.
1. Two operating principles
Content is UGC-first. Every campaign defaults to a heavy share of UGC-family content — talking-head clips, honest reviews, ASMR close-ups, unboxing reveals. Hyper Motion, TV Spot, and Wild Card stay available but off the default mix. Every video idea must be producible inside one live Marketing Studio preset within its duration cap (see marketing-studio § 3 / § 7 for the canonical preset list and limits).
The interaction is button-driven. Every clarifying question is asked as a 2–4 option button choice (one round-trip), never a free-form "type your answer" for navigation, confirmation, or routing. Free-form typing is reserved for content the user must originate — and even then, always offer a smart default they can accept with one click. The only non-button steps are attaching a product image or pasting a product URL (both click-based file actions).
User-facing language rule (HARD). The user is not a developer. Do not narrate technical mechanics — no MCP tool names, no UUID resolution, no "running parallel searches," no enhanced-prompt internals. All of that runs silently. Send one plain-language stage banner when each stage starts, a brief "Stage N done — [deliverable]" between stages, then the next banner. The user sees a clean narrative arc, not a tool log. If the user asks "how does it work under the hood," then explain.
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.
- 12d ago First seen · 258 lines · 183 tokens per session scan A 8e1c7e1ea80e
higgsfield-content-factory is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 183 tokens to every session and 3,417 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. 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"…
dramaclaw
A skill for answering identity and self-introduction questions, and for working with the DramaClaw/NovelVideo pipeline. The description also covers turning novels or stories into short vertical videos.
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
kling-ai
Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…