vskill: Skill for Claude Code

.claude/skills/higgsfield-seedance/SKILL.md

higgsfield-seedance is a skill for Claude Code from anton-abyzov/vskill. It costs 100 tokens per session (11,477 once invoked), scanned A, a copy of higgsfield-seedance, MIT.

A prompt-writing guide for Seedance 2.0 and Seedance Pro, video-generation tools, that turns scene ideas into structured descriptions and checks prompts that may be rejected.

In plain words
What is it for?
Use it to write cinematic video prompts with camera, subject, action, setting, style, and lighting, or to inspect blocked generations.
Why use it?
It helps make prompts clearer and diagnose failures before wasting generation attempts.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is anton-abyzov/vskill's own configuration. It tells Claude Code how to work on vskill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vskill configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is decomposes into, see `../../vocab.md` § Emotion as Visible Behavior —.

Reuse

Borrowing it

Nothing to install: this file belongs to anton-abyzov/vskill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/anton-abyzov/vskill/main/.claude/skills/higgsfield-seedance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/vskill

Made for: Claude Code.

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 higgsfield-seedance

README.md
[![agentmods](https://agentmods.dev/badge/skills/anton-abyzov/vskill/higgsfield-seedance/github.svg)](https://agentmods.dev/skills/anton-abyzov/vskill/higgsfield-seedance)
Your own site
<a href="https://agentmods.dev/skills/anton-abyzov/vskill/higgsfield-seedance"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/higgsfield-seedance/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 higgsfield-seedance

Your own site · 80×15
<a href="https://agentmods.dev/skills/anton-abyzov/vskill/higgsfield-seedance"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/higgsfield-seedance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,477 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 86% copy Near-identical to another mod 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 $0.00100 $0.11477
Opus 5 $0.00050 $0.05738
Sonnet 5 $0.00020 $0.02295
Haiku 4.5 $0.00010 $0.01148

Measured 7d ago against content hash 61eaa59aec49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

higgsfield-seedance 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 7d 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.

Origin

This is a copy

86% identical to higgsfield-seedance — 681 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/higgsfield-seedance/SKILL.md · 1,237 lines

How it starts

The opening of the file, as written. The whole thing — 1,237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Higgsfield Seedance Director

Use this skill whenever the user wants a Seedance 2.0 / Seedance Pro prompt, OR whenever a Seedance generation has been blocked, flagged, or silently failed. This skill's job is to stop credit waste on filter rejections.


The Filter Model — Read This First

Seedance 2.0's content filter is not a keyword blacklist. It is a language model that reads the full prompt as a single scene and judges intent and context. Most users burn hours swapping individual words — that loop does not work.

The filter compares two things:

  • A prompt that reads like a filmmaker describing a shot → tends to pass.
  • A prompt that reads like a note to a friend → tends to fail.

A word that looks sensitive in isolation can sit inside a well-constructed cinematic prompt without issue — the filter reads the full picture. A prompt with no picture to read (no setting, no visual purpose, no narrative logic) gives the filter nothing to work with, and it errs on the side of caution.

Practical rule: the prompt must describe a scene, not a subject. Fix the voice first, then fix the words.


Instant Fail vs. Delayed Fail — the Diagnostic

This single heuristic saves time on every failure:

Failure timing Meaning What to do
< 10 seconds (instant) Content filter rejection — prompt never reached the GPU Rewrite for voice + remove risk tokens. Do not regenerate unchanged.
> 30 seconds (delayed) Infrastructure, timeout, or complexity — prompt passed the filter but the render failed Simplify action density, cut length, try again

If the user is seeing instant fails in a loop, it is a filter issue — never a GPU issue. Stop them from regenerating before the rewrite.


The Seedance Prompt Formula

Every Seedance prompt should hit these six slots, in this order:

[Camera movement] + [Subject] + [Action] + [Setting] + [Style] + [Lighting]

All six are technically optional — but a prompt that includes all six almost never gets flagged, because the filter has full context to interpret every word. A prompt missing 3+ slots is where flags come from.

Read the full file on GitHub · 1,237 lines

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. 7d ago First seen · 1,237 lines · 100 tokens per session scan A 61eaa59aec49

Subscribe to this mod's changes

higgsfield-seedance is a skill published in the GitHub repository anton-abyzov/vskill (45 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 11,477 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to higgsfield-seedance, differing in 681 lines, and is treated as a copy.

Related

Other skills, from other repositories

cubelife

Give your AI agent a persistent pixel-art character that reflects its state in real time. Use when the user wants to visualise agent activity, add a character companion, or report agent state via MCP.

Ivy-Innovation/cubelife · 44 tokens

gsap-plugins

Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…

calesthio/OpenMontage · 91 tokens

hyperframes

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the…

calesthio/OpenMontage · 167 tokens

seedance-2-0

Generate cinematic clips with ByteDance Seedance 2.0 — the preferred premium video model in OpenMontage when a paid gateway is configured. Use when: (1) producing trailers, teasers, hype edits, or premium cinematic clips, (2) needing native synchronized audio (speech, SFX, ambience) in a single pass, (3) needing…

calesthio/OpenMontage · 194 tokens

ffmpeg

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

calesthio/OpenMontage · 55 tokens

motion-graphics

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…

calesthio/OpenMontage · 187 tokens