AI Social Media Content
NeverSight/learn-skills.dev
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X.
A skill your agent uses 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…
Install Higgsfield Repurpose
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurpose --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/higgsfield-repurpose .claude/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .claude/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurposeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurpose --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/higgsfield-repurpose .agents/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .agents/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurpose --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/higgsfield-repurpose .cursor/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .cursor/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git --path skills/higgsfield-repurpose--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurpose --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/higgsfield-repurpose .gemini/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .gemini/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurposeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/higgsfield-repurpose .github/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .github/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-repurpose --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/higgsfield-repurpose .opencode/skills/higgsfield-repurpose && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-repurpose" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-repurpose into .opencode/skills/higgsfield-repurpose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-repurpose", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
higgsfield-repurpose- GitHub stars
- 713
- Token cost
- ~3.9k tokens
- SKILL.md length
- 1,744 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses 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…
- Works in 5 steps: Estimate first — get_cost: true +… → Pick or make a style —… → Upload the source — the user uploads… → …
- The user already has a FINISHED video and wants Higgsfield to repurpose
- SKILL.md covers QUICK FACTS, What this sub-skill is for, Paid or free — read this… and Shorts Studio, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Higgsfield Repurpose is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. 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…
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Writing & Content, covering Content repurposing and AI video generation. It works with YouTube. The repository describes itself as: Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an… The licence is MIT.
When your agent uses it
- The user already has a FINISHED video and wants Higgsfield to repurpose
- 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
Example prompts
- “turn my video into shorts”
- “will this go viral”
- “score my ad”
- “/higgsfield-repurpose”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Estimate first — get_cost: true + duration_seconds (free; no preset, no upload).
- Pick or make a style — shorts_studio_list_presets returns the user's own presets
- Upload the source — the user uploads through media_upload_widget (type=video);
- Create — PAID. Returns a session with empty job_ids.
- Poll shorts_studio_status until clips appear. status='completed' means every
What it can do on your machine
Read from SKILL.md and the folder at commit 7075497. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Higgsfield Repurpose loads about 3.9k tokens when it runs. Until then it costs about 213 tokens; SKILL.md has 1,744 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from OSideMedia/higgsfield-ai-prompt-skill at commit 7075497, republished under its MIT licence (© OSideMedia). 1,744 words, ~3,864 tokens.
Download SKILL.mdSave it as
.claude/skills/higgsfield-repurpose/SKILL.md (or your agent's skills folder).- 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
- metadata.version
- 1.0.0
- metadata.updated
- 2026-09-26
- metadata.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) →
- 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) |
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-form clips using a style preset. PAID — reserves credits."
| Param | Values | Notes |
|---|---|---|
source_video_id | uuid | The uploaded video's video_input id (media_upload_widget, type=video). Required unless get_cost |
preset_id | uuid | From shorts_studio_list_presets or shorts_studio_create_preset. Required unless get_cost |
preset_source | user · cms | The preset item's own preset_source. Required unless get_cost |
aspect_ratio | 9:16 (default) · 16:9 | Output orientation |
resolution | 720p | The only value — the schema pins it as a constant |
get_cost | bool | With duration_seconds, returns the estimate and submits nothing |
duration_seconds | > 0, ≤ 120 | Source length; required when get_cost is true |
The run, in order:
- Estimate first —
get_cost: true+duration_seconds(free; no preset, no upload). - Pick or make a style —
shorts_studio_list_presetsreturns the user's own presets first, then the CMS library (paginated vianext_cursor); or make one (below). - Upload the source — the user uploads through
media_upload_widget(type=video); the tool asks for an upload before it is called, never a chat attachment. - Create — PAID. Returns a session with empty
job_ids. - Poll
shorts_studio_statusuntil clips appear.status='completed'means every clip job is terminal, not necessarily successful — check each clip.
Schema mismatch to know about:
shorts_studio_statussays to poll each clip'sjob_id"via job_status", but nojob_statustool is in the connector's 2026-09-26 tool list — the listed job tools arejobs_wait,job_displayandshow_generation_by_ids. Which one the status tool means is unverified.
Not published: how many clips a session produces, how long each is, and what the restyle keeps from the source (timing, audio, framing). Look at one real session before promising any of them.
Style presets (free)
shorts_studio_create_preset stores a style from reference media — no generation, no
credits.
- Limits: ≤ 10 media total; each video ≤ 30s (send
durationso the cap applies); every media item a public https URL (use an uploaded media's URL, ormedia_import_urlfirst). - Fields:
name(required),prompt(optional style direction),image_medias,video_medias,thumbnail. - Naming: Higgsfield's own tool instruction is to give an unnamed preset a random friendly two-word name rather than ask — follow it.
- What this library adds
[INFERENCE — untested]: a style preset is a saved style block, the same job as Cinema Studio's Manual Style — so write itspromptthe same way: laws, not descriptions (grade behaviour, lighting law, texture, camera register), no vague labels, no director name-drops. See../higgsfield-cinema/SKILL.md§ Manual Style — Authoring Guide.
Show full SKILL.md (760 more words)Show less
Clipify
[OFFICIAL — platform, 2026-09-26] — model clipify, "Turn one YouTube video into
ready-to-share clips with subtitles" (video catalog, ../../specs/models_explore_snapshot_2026-09-26.json).
| Param | Values | Default |
|---|---|---|
urls | YouTube URL array — "Provide exactly one URL; submit one Clipify job per source video" | required |
clips_num | 1–20 | 10 |
clip_aspect | 9:16 · 1:1 · 16:9 | 9:16 |
subtitle_font | notosans · notoserif · notosansdisplay · ibmplexsans · mplusrounded1c · bebasneue · archivoblack · unbounded · inter · montserrat · bangers · permanentmarker · playfairdisplay · caveat | notosans |
subtitle_case | upper · lower · as-is | as-is |
subtitle_position | bottom · center · top | bottom |
subtitle_highlight_hex | #RRGGBB | #FFE84D |
track_face_crop | bool — "Track faces when cropping clips" | true |
max_height | 144–2160 — "Maximum source processing height" | 1080 |
segment_seconds | 2–60 — "Segment duration in seconds" | 10 |
Clipify vs Shorts Studio. Clipify cuts one YouTube video into subtitled clips; it has no style or restyle parameter. Shorts Studio restyles one uploaded video into AI-generated clips from a preset. Long talk / podcast / tutorial → clips: Clipify. A short piece whose look should change: Shorts Studio.
The source is fetched from YouTube — clip only videos the user owns or has the rights to.
What segment_seconds controls beyond its one-line description is not documented.
Virality Predictor
[OFFICIAL — Higgsfield MCP tool schema, virality_predictor, 2026-09-26]
"predicts a video's virality potential, engagement, attention, audience response, retention risk, hook strength, and creative performance with an interactive dashboard."
action: "create"withparams.medias: [{role: "video", id: <uuid>}]— the id is a confirmed uploaded videomedia_idor a completed generated videojob_id;params.modelis the constant"virality_predictor".action: "preview"withparams.job_idre-opens an existing dashboard.- CLI face: Higgsfield's own skills repo says its Virality Predictor path "Uses
Virality Predictor (
brain_activity) with--video"[OFFICIAL — Higgsfield skills repo README, v0.12.0]; CLI 1.1.23model get brain_activityshows a text-output model named "Brain Activity" that requiresmedias. That the two are the same product rests on that README line — not verified here.
How this library uses it [INFERENCE — untested]:
- It is a prediction, not audience data. This repo has never compared its scores with real performance. Report it as "the predictor says", never as "this will go viral".
- Compare variants, don't chase a number. The useful question is relative: hook A vs hook B on the same ad, cut 1 vs cut 2. Rewriting a creative only to move one score is optimizing the instrument.
- Natural pairings: hook variants from
../higgsfield-marketing-studio/SKILL.md, Ad Multiplier versions (same skill, § 14), campaign batches in../higgsfield-content-factory/SKILL.md.
Video Analysis
[OFFICIAL — Higgsfield MCP tool schema, video_analysis_*, 2026-09-26]
- Input — exactly one of:
video_input_id(an uploaded video's media id) oryoutube_url(https onyoutube.com,www.youtube.com,m.youtube.comoryoutu.beonly). - Queued: returns
status='queued'; pollvideo_analysis_statusevery 30–60 seconds untilcompleted(scenes populated) orfailed(fail_reasonpopulated). "Processing typically takes 3-5 minutes on average." Past jobs:video_analysis_jobs. - The warning the tool requires, verbatim: "warn the user up front that the longer the video, the less accurate the scene-by-scene analysis becomes — short clips give the most reliable results." Say it before submitting, every time.
- Practical consequence: trim to the sequence you actually care about before uploading.
Uses in this repo [HYPOTHESIS — UNMEASURED]:
- Reference breakdown — a short reference sequence → a scene list to seed
../higgsfield-shotlist-director/SKILL.mdor to audit with../higgsfield-scene-engine/SKILL.md. Analyze a reference for its structure; the shotlist still gets written, not copied. - Cut check — did a generated multi-shot clip actually cut where the prompt declared ("strictly N shots")? The analysis is a second pair of eyes, not a verdict.
- The output's shape beyond "scenes" is not documented. Treat what comes back as notes to verify against the video, never as ground truth.
Where the neighbouring jobs live
| The user wants | Surface | Where it is covered |
|---|---|---|
| Captions burned into the pixels | Higgsfield's subtitles workflow | ../higgsfield-stack/SKILL.md § Higgsfield's bundled workflows |
| Cuts, trims, soundtrack, layouts, animated text, title cards on footage | Higgsfield's video-editing workflow (Higgsedit) | same |
| The same video at another aspect ratio | reframe (MCP tool; also a CLI workflow — verify params with higgsfield workflow get reframe --json) | — |
| A different voice on the same video | voice_change | ../higgsfield-audio/SKILL.md § Voice change and voice cloning |
| One object swapped, or motion transferred | Genjutsu | ../higgsfield-marketing-studio/SKILL.md § 14 |
| Many independently edited versions of one ad | Ad Multiplier | same |
Provenance
- Shorts Studio, Virality Predictor, Video Analysis:
[OFFICIAL — Higgsfield MCP tool schema, 2026-09-26]— read from the connector's tool definitions; no tool was called. - Clipify:
[OFFICIAL — platform, 2026-09-26]— the videomodels_exploresnapshot. brain_activity: CLI 1.1.23model get(a free schema read) plus Higgsfield's skills repo README v0.12.0.- Nothing here has been run; costs, clip counts, clip lengths and the accuracy of any analysis are unmeasured.
Related skills
../higgsfield-stack/SKILL.md— execution surfaces, preflight, Higgsfield's bundled workflows../higgsfield-audio/SKILL.md— voice change and cloned voices../higgsfield-marketing-studio/SKILL.md— ad creative, Ad Multiplier, Genjutsu../higgsfield-content-factory/SKILL.md— campaign batches that virality scores can rank../higgsfield-shotlist-director/SKILL.md·../higgsfield-scene-engine/SKILL.md— where a scene breakdown goes next
© OSideMedia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/higgsfield-repurpose of OSideMedia/higgsfield-ai-prompt-skill.
Open the folder on GitHubat commit 7075497
Compare with similar skills
Higgsfield Repurpose next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Higgsfield Repurpose this skillOSideMedia/higgsfield-ai-prompt-skill | 713 | — | ~3.9k | Automated safety check: Pass | MIT | |
| AI Social Media ContentNeverSight/learn-skills.dev | 217 | 1 repos | ~1.8k | Automated safety check: Pass | None | |
| Video Plannersugarforever/01coder-agent-skills | 137 | — | ~2k | Automated safety check: Pass | MIT | |
| Video Content Strategistalirezarezvani/claude-skills | 28k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Captions And Clippingsocial-media-skills/skills | 134 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Youtube Downloaderguia-matthieu/clawfu-skills | 150 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Video Planner
sugarforever/01coder-agent-skills
Plan videos and prepare publishing materials for YouTubers/UP主.
Video Content Strategist
alirezarezvani/claude-skills
A skill your agent uses when planning video content strategy, writing video scripts, optimizing YouTube channels, building short-form video pipelines (Reels, TikTok, Shorts), or repurposing…
Captions And Clipping
social-media-skills/skills
The long-form-to-Shorts + sound-off captions mini-skill (Opus Clip / CapCut / Submagic).
Youtube Downloader
guia-matthieu/clawfu-skills
Download and process YouTube content for research. An agent skill from guia-matthieu/clawfu-skills.
Youtube
AgriciDaniel/claude-youtube
The ultimate YouTube creator skill. An agent skill from AgriciDaniel/claude-youtube.
More from OSideMedia/higgsfield-ai-prompt-skill
All 33 skills in this repoHiggsfield
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano…
Higgsfield Assist
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to…
Higgsfield Image Shots
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type…
Higgsfield Mixed Media
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Mixed Media, wants to apply artistic preset styles to an image (Noir, Sketch, Paper, Canvas, Particles, Neon, etc.), combine multiple artistic…
Higgsfield Moodboard
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to…
Higgsfield Motion
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user wants to apply a named Higgsfield motion preset, asks about VFX presets, transformation effects, elemental effects, or transition presets.
Related
Works with
Categories
Questions about Higgsfield Repurpose
What does Higgsfield Repurpose do?
A skill your agent uses 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…. Higgsfield Repurpose is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. 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).
When should I use Higgsfield Repurpose?
Higgsfield Repurpose fits situations like: the user already has a FINISHED video and wants Higgsfield to repurpose; 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.
How do I install Higgsfield Repurpose in Claude Code?
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a claude-code`. Or copy the skill folder (skills/higgsfield-repurpose in OSideMedia/higgsfield-ai-prompt-skill) into .claude/skills/higgsfield-repurpose in your project. Claude Code loads it when a task matches its description.
How do I install Higgsfield Repurpose in Codex?
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a codex`. Or copy the skill folder (skills/higgsfield-repurpose in OSideMedia/higgsfield-ai-prompt-skill) into .agents/skills/higgsfield-repurpose in your project. Codex loads it when a task matches its description.
Can I use Higgsfield Repurpose in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-repurpose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/higgsfield-repurpose, .gemini/skills/higgsfield-repurpose, .github/skills/higgsfield-repurpose and .opencode/skills/higgsfield-repurpose in your project.
What does Higgsfield Repurpose need to run?
SKILL.md names no scripts, command-line tools or credentials: Higgsfield Repurpose is instructions for the agent only.
Does Higgsfield Repurpose access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Higgsfield Repurpose safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Higgsfield Repurpose use?
Higgsfield Repurpose is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Higgsfield Repurpose use?
About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Higgsfield Repurpose?
Skills that share tags, products or a category with Higgsfield Repurpose: AI Social Media Content (NeverSight/learn-skills.dev, 217 stars), Video Planner (sugarforever/01coder-agent-skills, 137 stars), Video Content Strategist (alirezarezvani/claude-skills, 28k stars) and Captions And Clipping (social-media-skills/skills, 134 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Higgsfield Repurpose?
OSideMedia (a GitHub user) maintains it in OSideMedia/higgsfield-ai-prompt-skill, which has 713 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on September 27, 2026.
Source: OSideMedia/higgsfield-ai-prompt-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.