higgsfield-faceless-video — Claude Code skill: video and install
The higgsfield-faceless-video Claude Code skill creates finished faceless videos and edits existing ones. It handles requests for explainers, documentaries, illustrated stories, and children's music videos.
MIT 36,600 installs ★ 2,040 updated 2026-09-26
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a claude-codeWhat higgsfield-faceless-video does
The skill produces a finished video without an on-screen presenter, or edits one made earlier. It selects workflow instructions for the requested format, with separate guidance for production, editing, visual style, and captions. The scripts/assemble_blocks.sh helper joins ordered video and audio segments.
Before generation, the brief needs a topic, duration, aspect ratio, language, visual style, voice, and music choices. The skill checks the Higgsfield account, model schemas, and access to ffmpeg, ffprobe, python3, curl, and awk; it also needs the higgsfield CLI and an account. Generation can consume credits. Where supported, higgsfield generate cost estimates the cost; if a required stage or dependency is unavailable, the skill stops before paid generation. Captions also require the dependencies listed in references/captions.md.
What it helps with
- create a narrated explainer video
- shape pacing and visuals for a documentary
- make an illustrated story or children's music video
- edit a previously generated faceless video
Example prompts for the agent
- Create a two-minute explainer about solar energy in English, with a 16:9 aspect ratio.
- Turn this text into an illustrated story in English.
- Edit this faceless video and keep its visual style.
How to install higgsfield-faceless-video
1Skills CLI (Vercel)
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a claude-code2Manually: put the files in place
~/.claude/skills/higgsfield-faceless-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/higgsfield-faceless-video/
1Skills CLI (Vercel)
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a codex2Manually: put the files in place
.agents/skills/higgsfield-faceless-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a cursor2Manually: put the files in place
.cursor/skills/higgsfield-faceless-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install higgsfield-ai/skills higgsfield-faceless-video2Manually: put the files in place
.github/skills/higgsfield-faceless-video/SKILL.md1Skills CLI (Vercel)
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/higgsfield-ai/skills --path higgsfield-faceless-videoManually: put the files in place
.devin/skills/higgsfield-faceless-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about higgsfield-faceless-video
How do I install higgsfield-faceless-video in Claude Code?
Run npx skills add higgsfield-ai/skills --skill higgsfield-faceless-video -a claude-code. The skill file is installed at ~/.claude/skills/higgsfield-faceless-video/SKILL.md.
What does higgsfield-faceless-video do?
It creates finished videos without an on-screen presenter, including explainers, documentaries, illustrated stories, and children's music videos. It can also edit videos created earlier.
What does higgsfield-faceless-video need to run?
It needs the higgsfield CLI, a Higgsfield account, and ffmpeg, ffprobe, python3, curl, and awk. Captions require the dependencies described in references/captions.md.
Source text
SKILL.md · MIT
--- version: 0.14.0 name: higgsfield-faceless-video description: | Create a finished faceless explainer, documentary, illustrated story or children's music video, or edit a previously created faceless video. Use when: "make a faceless video", "create a narrated explainer", "make a children's song video", "edit this faceless video". NOT for: a single silent clip, ads or UGC, unrelated footage edits, or script-only requests. argument-hint: "[topic or source] [duration] [language] [aspect ratio]" allowed-tools: Bash --- # Faceless video Create one finished video with a consistent visual style and narration. For an illustrated explainer use deliberate, diagram-led scenes; for a story or documentary adapt the pacing and visuals to the brief. Do not treat an explainer as a request for rapid cuts. Preserve choices and assets supplied by the user. Choose the requested mode before generating: illustrated explainers use `references/production.md`; fast-cut channel motion uses `references/channel-motion.md`; stills and picture stories use `references/picture-story.md`; a sung children's music video uses `references/song.md`; explicitly requested talking characters use `references/talking-characters.md`; a requested presenter overlay uses `references/presenter.md` alongside the motion workflow; edits to a previously generated video use `references/editing.md`. A request for background music alone is not a song request. Never infer a presenter from an incidental photo. When the brief supplies `animation_mode`, treat `fully_animated` as motion and `scene_based` as stills without asking again. Resolve song intent from the complete brief, including topic and script; an explicitly sung children's video uses song mode even when a voice is supplied. Preserve the production mode when continuing or editing an existing video. ## Before spending credits Resolve missing topic, approximate duration, aspect ratio, language, visual style, voice, music and subtitle choices. Never invent a preset or voice ID. Use `higgsfield preset list video-explainer --json` and `higgsfield voices list --json` for current choices, and resolve a selected preset with `higgsfield preset resolve video-explainer <id> --json`. Confirm photo roles before using reference images. Honor the requested duration; never silently round it up. Find this skill's installed directory and retain its absolute path as `SKILL_DIR`. Keep all work in a persistent session directory, not the skill directory. Before generation verify `higgsfield account status`, `ffmpeg`, `ffprobe`, `python3`, `curl`, and `awk`, and inspect the live schemas using `higgsfield model get` for each planned model. Estimate generation costs with `higgsfield generate cost` where supported; if an estimate is unavailable, disclose that before generation. If any required stage, model, dependency, or requested feature is unavailable, explain and stop before paid work. Do not call `explainer_video` or `video_explainer`. Read `references/production.md` for the generation, assembly, QC, recovery and delivery procedure. For subtitles, read `references/captions.md` and check its dependencies before paid generation. Read `references/creative.md` for style, assets, long-form planning and review, `references/styles.md` for style guidance, and `references/prompts.md` when writing the scene plan. The executable helper `scripts/assemble_blocks.sh` assembles ordered video/audio pairs without changing speech speed; read its usage before running it. The previous skill name is supported for existing installations.
© higgsfield-ai · MIT · higgsfield-ai/skills