Seedance Interview Short logo

Seedance Interview Short

CommunityPopular
Emily2040
seedance-interview-short

This skill should be used when the user wants a fast Seedance 2.0 creative brief, a short interview, a compressed intake flow, or a quick director-style clarification before prompt writing.

Overview

PublisherEmily2040
Repositoryseedance-2.0
Skill nameseedance-interview-short
Stars
7.4K
Forks
1.1K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Emily2040 on GitHub. Read the source before you install it.

Installation

Install the Seedance Interview Short AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Emily2040/seedance-2.0.git /tmp/seedance-2.0
mkdir -p .claude/skills
cp -r /tmp/seedance-2.0/skills/seedance-interview-short .claude/skills/seedance-interview-short
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance Interview Short in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seedance Interview Short on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seedance Interview Short is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

seedance-interview-short

Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.

Use this when speed matters more than exhaustive creative discovery. The goal is to turn a vague idea into a compact director brief with no more than three questions, then route to prompt writing.

Speed does not bypass story judgment. Load the Director's Read before producing the compact brief. Use its canonical classification and the corresponding internal record; do not duplicate or broaden the lane rules here. Never reconstruct the read from remembered craft.

Intent

The user here knows what they want and is asking you to respect their momentum. The soul of this skill is restraint: find the one missing piece that would sink the generation, ask only that, and get out of the way. Speed is the form their trust takes.

Process

Ask at most three questions, and only ask them if the answer materially changes the prompt. Assume no film background: ask in everyday words, give pickable options, and attach a default so "I don't know" never stalls the brief. Prioritize:

  1. What happens in the video, and what is different at the end? (not sure? I'll pick one simple action with a visible ending)
  2. Do you have photos, clips, or sound that should define this clip's appearance, movement, or sound? (none is fine; I'll draft from your idea)
  3. Only if the user asks for connected clips, a longer scene to divide, or continuation: how must the complete story end, and what accepted footage or final frame already exists? (if continuing, I need the accepted clip or final frame)

Unknown duration alone does not make a sequence. For one clip, ask at most one blocking question; otherwise state a reversible assumption and draft. Do not ask whether this should become a series before the first draft. Preserve information the user already supplied. Explicit connected-clip or continuation intent still activates sequence planning and its accepted-footage gate.

If the user already supplied enough information, do not ask. Produce a brief immediately. If the user speaks production language fluently, drop the plain phrasing and ask in director terms.

Run the interview and brief in the user's language; for localized starting-point menus and invites, load interview-starters. If the user gives explicit shot, lens, camera, blocking, or performance direction, keep it verbatim and compile it into a shot-contract-grade brief - never simplify or override a professional's spec. When direction is unresolved, draft with a reversible assumption or offer up to three brief-specific choices from that reference; this counts toward the existing question limit. Options change staging, attention, timing, or performance and state a real tradeoff. A “choose for me” reply means choose and draft now. Preserve chosen and rejected options, and skip the menu for a specified brief.

Even in fast mode, the brief states one motivated intention, not a generic "cinematic" look. For narrative work, derive it from the completed Director's Read record and translate the turn, visible suppressed behavior, and non-transferable detail into filmable or audible carriers. For non-narrative work, serve the utility intent without inventing want, power, conflict, or subtext. Load directing-engine only when the right setup for the scene is genuinely unclear.

Compact Brief Pattern

Internal lane record from the Director's Read, then: Mode: [T2V/I2V/V2V/R2V]. Subject: [anchor]. Beat: [before -> action -> final state]. Camera: [one move]. Light/style: [physical source and safe descriptor]. Sound: [dialogue/ambience/SFX/music/silence]. Constraints: [identity, IP, safety, product, prompt budget].

Routing Rule

Route to seedance-sequence when the user requests connected clips or a long story that needs multiple generations; seedance-continuation for accepted-footage continuation; seedance-prompt for a full standalone production prompt; seedance-prompt-short for a compact prompt, including one clip whose duration is undecided; seedance-copyright for IP/likeness risk; or seedance-troubleshoot when the user starts from a bad result.

Output Contract

Return one compact brief under 150 words, any missing high-impact question, and a recommended skill route. When an optional choice is still pending, show the short options instead of a dossier; after selection, output only the chosen brief unless alternatives were requested. Choosing a direction does not authorize paid generation. Keep Director's Read labels out of final generation prose; show the internal record only when the user requests the planning rationale or when another agent needs the handoff. If the request is a sequence, include the complete story ending, likely clip count, current clip job, and the fact that future prompts stay provisional until accepted footage is reviewed.

Frequently asked questions

What does the Seedance Interview Short AI skill do?

This skill should be used when the user wants a fast Seedance 2.0 creative brief, a short interview, a compressed intake flow, or a quick director-style clarification before prompt writing.

Why use Seedance Interview Short on TypingMind?

Because you install it once and use it with any model. Seedance Interview Short is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seedance Interview Short in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Emily2040/seedance-2.0/tree/main/skills/seedance-interview-short. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seedance Interview Short?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seedance Interview Short?

As many as you like. As long as a model supports skills, you can use Seedance Interview Short with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seedance Interview Short AI skill free?

Yes. It is published on GitHub by Emily2040 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇