Seedance Troubleshoot logo

Seedance Troubleshoot

CommunityPopular
Emily2040
seedance-troubleshoot

This skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.

Overview

PublisherEmily2040
Repositoryseedance-2.0
Skill nameseedance-troubleshoot
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 Troubleshoot 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-troubleshoot .claude/skills/seedance-troubleshoot
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance Troubleshoot 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 Troubleshoot 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 Troubleshoot 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-troubleshoot

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 retake-protocol to record the failed criterion, observed or user-reported evidence, useful parts of the take, one plausible repair, and the remaining authorized limits. Diagnose before rewriting; repeated failures do not prove the prompt is wrong. Consider mode mismatch, conflicting references, ambiguity, unsupported controls, model variation, or missing preservation constraints. A review or rewrite request does not authorize another generation. At zero/exhausted budget, submit nothing; preserve model/tier, duration, resolution, and reference roles unless an already authorized change covers them.

When the diagnostic tree has no row for the failure, load model-mechanics and propose a testable hypothesis from the observed failure: conflicting priorities, ambiguous constraints, action timing, continuity state, reference roles, detail readability, or audio attribution. Do not present a diagnosis as proof of hidden model internals. Load field-observed-tips, reference-workflow, and api-workflow when the failure involves continuation, edit/extend, source clips, audio references, or platform-specific errors. Load shot-list-continuity for multi-shot drift and delivery-qc for final-client or delivery failures. When sequence state is present, load failure-atlas, continuation-handoff, and continuity-qc; diagnose against continuity locks, completed beats, exact reference tags, and reserved future beats.

Intent

A failed generation feels personal - the user showed the machine their idea and the machine returned something broken. The soul of this skill is rescue without blame: describe a plausible failure mechanism without blaming the user; preserve the idea as well as the prompt. They should leave with a fix and their confidence intact.

Diagnostic Tree

SymptomLikely causeFirst repair
Product or face changesI2V prompt re-described visible identity or overloaded motion.Add preservation constraints; remove duplicate static detail.
Camera jumpsSeveral incompatible moves or no endpoint.Choose one move with start and finish.
Generic outputHollow style words and weak action.Replace with physical action, source light, material, and sound.
Motion ignoredStatic prompt or no visible consequence.Add actor, verb, timing, and changed end state.
Lip-sync poorMoving head/camera, long dialogue, unassigned speaker.Lock framing, shorten line, assign speaker.
VFX noisyEffect has no source, physics, or dissipation.Add source, material, path, interaction, and endpoint.
Prompt blockedProtected IP, real-person, graphic, or bypass-like wording.Rewrite intent in safe production language without evasion.
Extension quality degradesNo last-frame anchor or too many new variables across continuations.Use returned last frame as first frame and change one variable.
Audio reference ignoredCompeting video sound, no visual beat mapping, or unsupported combo.Mute competing video and map one visible event to the beat.
Text/logos breakSmall text asked to move or be redrawn.Keep text static, centered, and protected; animate light around it.
Client QC failsPrompt output treated as final delivery without post/QC.Route to delivery preflight, post fix, or regenerate only the failing shot.
Continuation assumed planned endingPrevious clip was not reviewed or observed_end_state was ignored.Replace opening with actual observed end state.
Previous action restartedCompleted beat was not marked already_happened.Add completed beat exclusion.
Future beat leakedReserved beat entered the current prompt.Remove future beat and stop earlier.
Identity reference conflicts with continuity sourceSource clip controlled transient state and identity at once.Re-anchor identity from canonical reference.
Screen direction resetAxis relation was not locked or intentionally reset.Preserve screen direction or declare new-shot axis reset.
Open motion lostSubject or camera vector was not inherited.Carry motion vector into the opening sentence.
Camera phase restartedParent camera endpoint was not recorded.Start from observed camera phase.
Prop state contradictedOwner, position, or condition was missing.Add prop state handoff.
Audio phase restartedCompleted dialogue or music phase was not logged.Continue or intentionally change the audio phase.

Repair Process

First quote the failing phrase or missing element. Then state a plausible cause or testable hypothesis, with its uncertainty; call it a root cause only when the evidence establishes causation. Next, remove conflicts rather than adding complexity. Recommend one primary repair variable rather than adding more adjectives. Finally, produce one conservative retry prompt and one optional creative variant only if the user wants exploration.

Conservative Retry Pattern

[Reference role if any]. Preserve [identity/product/environment] exactly. One visible action: [specific verb and consequence]. Camera: [single move]. Lighting: [physical source]. Sound: [ambient/SFX/dialogue]. Constraints: [what must not change].

Escalation Rules

If the same error repeats, split the scene into shorter clips, reduce characters, simplify hand or face motion, use stronger reference role mapping, or change the mode. For unstable text/logos, keep them static, centered, and protected; do not ask the model to redraw small text during motion.

For edit/extend failures, preserve the source clip first and change only the failing layer. If a surface supports returned last frames, use that still as the next first-frame anchor before extending.

Output Contract

Return the failed criterion, observed or user-reported evidence, a plausible cause or testable hypothesis with uncertainty, and a repaired prompt when useful. Add a conservative retry proposal only when it serves the diagnosis; preserve the user's existing settings and authorization. Do not present uncertain causation as a proven root cause or submit a generation merely because a revision was requested.

Frequently asked questions

What does the Seedance Troubleshoot AI skill do?

This skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.

Why use Seedance Troubleshoot on TypingMind?

Because you install it once and use it with any model. Seedance Troubleshoot 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 Troubleshoot in TypingMind?

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

Which AI models can use Seedance Troubleshoot?

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 Troubleshoot?

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

Is the Seedance Troubleshoot 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 👇