/higgsfield-repurpose

name: higgsfield-repurpose
description: "Use when the user already has a FINISHED video and wants Higgsfield to repurpose, restyle, clip or analyze it: Shorts Studio (restyle one 4–120s source video into a set of short-form clips from a style preset), Clipify (turn one YouTube video into subtitled clips), Virality Predictor (predict virality, hook strength, attention, retention risk with a dashboard), or Video Analysis (scene-by-scene breakdown of an uploaded video or a YouTube link). Also use when the user asks which of these cost credits and which are free, 'turn my video into shorts', 'will this go viral', 'score my ad', 'break this video down scene by scene'. Names: shorts_studio_create, shorts_studio_create_preset, shorts_studio_list_presets, shorts_studio_status, clipify, virality_predictor, brain_activity, video_analysis_create, video_analysis_status."
user-invocable: true
metadata:
  tags: [higgsfield, repurpose, post-production, shorts-studio, clipify, virality-predictor, video-analysis, short-form, reels, youtube, analysis]
  version: 1.0.0
  updated: 2026-09-26
  parent: higgsfield

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) [→](#what-this-sub-skill-is-for)
• Paid vs free is per tool — `shorts_studio_create` is **PAID**; its `get_cost` estimate and preset creation state they are free; list / status calls state no cost [→](#paid-or-free--read-this-before-calling-anything)
• 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)
• Shorts Studio presets store a STYLE (≤10 media, videos ≤30s, public https URLs) — write the preset prompt as laws, not adjectives [→](#style-presets-free)
• 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 [→](#clipify)
• 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 [→](#virality-predictor)
• Video Analysis: exactly one of uploaded video / YouTube URL; ~3–5 min; **warn up front: the longer the video, the less accurate the breakdown** [→](#video-analysis)
• Burned-in captions, cuts, soundtrack, voice swaps are other surfaces — hand-off map [→](#where-the-neighbouring-jobs-live)

---

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) |

**Not this sub-skill:** changing what is *inside* a clip (swap an object, re-light, extend it) — that is `../higgsfield-seedance-2-5/SKILL.md` (video_edit / video_extension), `../higgsfield-seedance-vfx/SKILL.md`, or Genjutsu (`../higgsfield-marketing-studio/SKILL.md` § 14). Many edited versions of one ad → Ad Multiplier, same § 14.

---

Paid or free — read this before calling anything

`[OFFICIAL — Higgsfield MCP tool schema, 2026-09-26]` unless marked.

| Tool | Spends credits? | Evidence | |---|---|---| | `shorts_studio_create` | **PAID** — "reserves credits" | Tool description | | `shorts_studio_create` with `get_cost: true` + `duration_seconds` | **Free** — "estimate the credit cost without submitting a job"; no preset or source video needed | Tool description | | `shorts_studio_create_preset` | **Free** — "just stores a STYLE — no generation, no credits" | Tool description | | `shorts_studio_list_presets` · `shorts_studio_list_sessions` · `shorts_studio_status` | **Not stated** — list / status calls that submit nothing; not called free here | Tool descriptions (silent on cost) | | `clipify` | **Not stated.** It is a video-catalog model, so it runs through `generate_video` / the CLI and can be preflighted with `get_cost: true` (MCP) or `higgsfield generate cost clipify …` (CLI — confirm the flag form with `higgsfield model get clipify` first) | `[OFFICIAL — platform, 2026-09-26]` snapshot has no price field | | `virality_predictor` | **Not stated**, and the tool has no `get_cost` field | Tool schema | | `video_analysis_create` | **Not stated**, and the tool has no `get_cost` field | Tool schema | | `video_analysis_status` · `video_analysis_jobs` | **Not stated** — status / list calls that submit nothing; not called free here | Tool descriptions (silent on cost) |

**Where the schema is silent, do not call it free.** Check the balance before and after (`balance` / `transactions` on MCP, `higgsfield account status` on the CLI) the first time a surface is used, and record what it actually cost. No prices appear in this file because none were measured.

---

Shorts Studio

`[OFFICIAL — Higgsfield MCP tool schema, shorts_studio_*, 2026-09-26]`

> "Start a Shorts Studio short: restyle one uploaded source video (4s–120s) into a set of > AI-generated short