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-repurposegit 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-repurpose)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-repurpose"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-repurpose/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-repurpose"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-repurpose.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 | $0.00197 | $0.04173 |
| Opus 5.5 | $0.00079 | $0.01669 |
| Sonnet 5.5 | $0.00039 | $0.00835 |
| Haiku 4.5 | $0.00020 | $0.00417 |
Grade A, and why
higgsfield-repurpose 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 19d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Repurpose — Shorts, Clips, and Analysis of Finished Video
QUICK FACTS
Routing aids — read the linked sections for the full rules. Nothing in this sub-skill is field-tested.
- Four surfaces take a video that already exists: Shorts Studio (restyle → shorts), Clipify (YouTube → subtitled clips), Virality Predictor (a score), Video Analysis (a scene breakdown) →
- Paid vs free is per tool —
shorts_studio_createis PAID; itsget_costestimate and preset creation state they are free; list / status calls state no cost → - Shorts Studio: source 4–120s, output 720p only, 9:16 default (16:9 optional); preflight with
get_cost: true+duration_seconds— no preset or upload needed for the estimate → - Shorts Studio presets store a STYLE (≤10 media, videos ≤30s, public https URLs) — write the preset prompt as laws, not adjectives →
- Clipify: exactly ONE YouTube URL per job; 1–20 clips; 9:16 / 1:1 / 16:9; subtitle font, case, position and highlight colour are parameters →
- Virality Predictor: input is a confirmed uploaded video or a completed generated video; it is a PREDICTION — compare variants with it, don't treat it as audience data →
- Video Analysis: exactly one of uploaded video / YouTube URL; ~3–5 min; warn up front: the longer the video, the less accurate the breakdown →
- Burned-in captions, cuts, soundtrack, voice swaps are other surfaces — hand-off map →
What this sub-skill is for
Every surface here starts from a video that already exists — a finished ad, a long YouTube video, a generated clip — and produces something derived from it: restyled shorts, cut-down clips, a performance prediction, or a scene list. None of them writes a generation prompt from scratch; that is the rest of this library.
| Surface | Input | Output | Tool / model |
|---|---|---|---|
| Shorts Studio | One uploaded video, 4–120s + a style preset | A set of AI-restyled short-form clips | shorts_studio_* (MCP) |
| Clipify | One YouTube URL | Ready-to-share clips with subtitles | clipify (video catalog model) |
| Virality Predictor | An uploaded or generated video | Virality / engagement / attention / hook / retention-risk prediction + dashboard | virality_predictor (MCP) |
| Video Analysis | An uploaded video or a YouTube URL | Scene-by-scene analysis | video_analysis_* (MCP) |
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.
- 19d ago First seen · 243 lines · 197 tokens per session scan A 7cfcf224e68d
higgsfield-repurpose is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (750 stars, last pushed 20d ago), licensed MIT. It adds 197 tokens to every session and 4,173 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-28.
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…
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.
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.
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.