h3-first-person-finger-controlled-dance

h3-first-person-finger-controlled-dance is a skill for Codex from linkprint/local-ai-movie-workspace. It costs 83 tokens per session (679 once invoked), scanned A, original, MIT.

A prompt-writing guide for MiniMax H3, a video-generation model, focused on first-person smartphone dance scenes controlled by literal finger directions.

In plain words
What is it for?
Use it to write or refine prompts for playful, non-sexual dance videos with an original adult performer and one visible controlling hand.
Why use it?
It removes guesswork when turning up, down, left, and right hand commands into immediate, readable dancer movements while keeping the camera view and body continuity consistent.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to write or refine prompts for playful, non-sexual dance videos with an original adult performer and one visible controlling hand.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance
Install

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.

Any agent
npx skills add linkprint/local-ai-movie-workspace --skill h3-first-person-finger-controlled-dance
Clone the repo
git clone --depth 1 https://github.com/linkprint/local-ai-movie-workspace

Made for: Codex.

Wrote 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.

agentmods badge for h3-first-person-finger-controlled-dance

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance/github.svg)](https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance)
Your own site
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance/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.

agentmods 80×15 button for h3-first-person-finger-controlled-dance

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance"><img src="https://agentmods.dev/badge/skills/linkprint/local-ai-movie-workspace/h3-first-person-finger-controlled-dance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.00679
Opus 5 $0.00042 $0.00340
Sonnet 5 $0.00017 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 12d ago against content hash a738cf8dd058, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

h3-first-person-finger-controlled-dance 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.

images/workspace/admin-skills/h3-first-person-finger-controlled-dance/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

H3 First-Person Finger-Controlled Dance

Treat each finger command as an immediate physical input, not a metaphor or a loose musical suggestion.

Route the Request

  • For prompt writing or refinement, return text only.
  • Read references/style-blueprint.md and use $h3-prompt-writing.
  • Invoke $h3-video-generation only when the user explicitly asks to generate or render.
  • Use I2VA when one image defines the exact identity, costume, environment, lighting, high camera angle, and opening composition. Otherwise use T2VA with an original adult dancer.

Lock Composition and Control

  1. Picture 1, when supplied, is the sole authority for dancer identity, costume, environment, lighting, and opening high-angle smartphone POV.
  2. Show exactly one connected foreground arm: forearm, wrist, palm, and fingers remain anatomically joined. Keep it in the lower-right quadrant at roughly 10–18% of frame area.
  3. Keep the hand away from frame center, the dancer's face, and torso. No second hand or floating fingers.
  4. Hold the camera about 1.0–1.2 meters from the dancer at a high angle. Keep the dancer at roughly 70–80% of frame height and do not zoom out.
  5. Map controls literally: UP = whole body rises, DOWN = whole body lowers, LEFT = full body and weight shift left, RIGHT = full body and weight shift right.
  6. Finger motion and dancer motion begin on the same beat: no reaction delay, no one-beat delay, no anticipation, and no independent choreography between commands.
  7. Prevent twitch substitutions. LEFT and RIGHT must move the full body and center of mass, not only hips, shoulders, or a tiny local sway.
  8. Use a declared command ledger and finish with LEFT -> RIGHT -> UP, holding the final raised pose.

Render Rules

  • Keep one render to 4–15 seconds. A 10-second clip can execute the ten-command sequence in the reference when every command remains readable.
  • Default to 864x480; allow 960x544 when requested. Explicit 768p means 1344x768 and may never be downgraded.
  • Use one original adult dancer and energetic, stylish, non-sexualized movement. Exclude minors, adult content, nudity, sexualized choreography or framing, celebrity likeness, named characters, extra hands, floating fingers, delayed reactions, zoom-out, camera cuts, text, logos, subtitles, and watermarks.

Read the full file on GitHub · 37 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 12d ago First seen · 37 lines · 83 tokens per session scan A a738cf8dd058

Subscribe to this mod's changes

h3-first-person-finger-controlled-dance is a skill published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 14d ago), licensed MIT. It adds 83 tokens to every session and 679 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

higgsfield-seedance

Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…

OSideMedia/higgsfield-ai-prompt-skill · 100 tokens

higgsfield-acting

Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…

OSideMedia/higgsfield-ai-prompt-skill · 165 tokens

higgsfield-prompt

Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.

OSideMedia/higgsfield-ai-prompt-skill · 56 tokens

higgsfield-seedance-2-5

Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omnireference / videoedit / videoextension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video editing, forward/backward extension…

OSideMedia/higgsfield-ai-prompt-skill · 191 tokens

higgsfield

Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…

OSideMedia/higgsfield-ai-prompt-skill · 147 tokens

higgsfield-assist

Use 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 get more from fewer credits, or platform efficiency tips.

OSideMedia/higgsfield-ai-prompt-skill · 56 tokens