seedance-troubleshoot
Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.
Best use case
seedance-troubleshoot is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.
Teams using seedance-troubleshoot should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/seedance-troubleshoot/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How seedance-troubleshoot Compares
| Feature / Agent | seedance-troubleshoot | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# seedance-troubleshoot · Diagnostic Tree (v5.0)
This skill diagnoses and fixes the most common Seedance 2.0 failure modes. It uses a simple diagnostic tree to identify the root cause and provides a specific, actionable solution.
## The Diagnostic Tree
Start at the top and work your way down.
### 1. Is the output blurry, jittery, or morphing?
- **Root Cause:** Overspecification. Your prompt is too long, has too many competing details, or too many actions in a short time (violating beat density).
- **Solution:**
1. **Cut the prompt length** to 30-100 words.
2. **Use a reference.** Find an `@Image` or `@Video` that shows the style or action you want and replace 50+ words of description with a single `@reference` tag.
3. **Simplify the action.** Reduce the number of distinct movements in the shot.
### 2. Is the camera chaotic, spinning, or ignoring your instructions?
- **Root Cause:** You have violated the **One-Move Rule** by stacking multiple camera moves in a single shot.
- **Solution:**
1. Rewrite the camera instruction to include only **ONE** primary move (e.g., `slow dolly push`, `handheld tracking`, `static wide shot`).
2. If you need multiple moves, use the `[Cut to:]` syntax to create a sequence of shots, each with its own single move.
3. For complex moves, use a `@Video` reference and tell the model to `Match the camera movement from @Video1`.
### 3. Is the character not looking like your reference image?
- **Root Cause:** The prompt is re-describing the character, which competes with and overrides the `@Image` reference.
- **Solution:**
1. **Delete all physical descriptions** of the character from the prompt (hair color, clothing, face).
2. The prompt should only describe the character's **action and emotion**.
3. Ensure the `@Image` reference is a clear, well-lit shot of the character.
### 4. Is the action stiff, slow, or lacking impact?
- **Root Cause:** Lack of intent and physics language. The model doesn\'t know *how* to perform the action.
- **Solution:**
1. **Add degree adverbs:** `violently`, `gracefully`, `frantically`, `dramatically`.
2. **Add physics consequences:** `dust erupts`, `sparks fly`, `the character staggers`, `sweat flies off in slow motion`.
3. **Use an `@Video` reference** of a similar action to give the model a clear example.
### 5. Is the output just not what you wanted?
- **Root Cause:** Your prompt is ambiguous. Words like `cinematic`, `epic`, and `beautiful` are subjective and mean nothing to the model.
- **Solution:**
1. Run the prompt through the **Anti-Slop Check** in the [skill:seedance-prompt] skill.
2. Replace every subjective adjective with a measurable, observable detail.
3. **Iterate.** Make small changes to your prompt and re-roll 3-5 times. Do not expect a perfect result on the first try.
---
*Maintained by [Emily (@iamemily2050)](https://github.com/Emily2040)*Related Skills
seedance-vocab-zh
Look up 550+ Chinese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 22 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Mandarin, translating a production concept into Chinese Seedance vocabulary, or verifying term accuracy.
seedance-vocab-ru
Look up 450+ Russian cinematic, photography, and production terms rooted in the Eisenstein/Tarkovsky Soviet montage tradition, with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Russian or translating production concepts into Russian Seedance vocabulary.
seedance-vocab-ko
Look up 450+ Korean cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Korean or translating production concepts into Korean Seedance vocabulary.
seedance-vocab-ja
Look up 450+ Japanese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Japanese or translating production concepts into Japanese Seedance vocabulary.
seedance-vocab-es
Look up 450+ Spanish cinematic, photography, and production terms — Castilian and Latin American — with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Spanish or translating production concepts into Spanish Seedance vocabulary.
seedance-vfx
Specify VFX physics contracts, energy effects, particle systems, destruction physics, and multi-layer VFX hierarchies for Seedance 2.0. Use when adding explosions, fire, water, lightning, magic effects, or any physically simulated element to a scene.
seedance-style
Control visual style, render-engine tokens, animation registers, period aesthetics, CGI material contracts, and style transfer via reference for Seedance 2.0. Use when setting a specific look — cinematic, anime, 3D, vintage, photorealistic — or when style is inconsistent across a shot chain.
seedance-recipes
Apply genre recipe templates to Seedance 2.0 — product ads, fight scenes, brand films, mood pieces, dialogue clips, one-take journeys, music videos, novel adaptations, architecture walkthroughs, and action transfers. Use when you need a ready-made prompt structure for a known genre or format.
seedance-prompt
Construct a production-ready prompt for Seedance 2.0 using the Director\'s Formula. Use when a user has a clear vision and needs to translate it into a genre-aware, intent-driven prompt. Covers genre routing, I2V gate, 30-100 word target, physics language, and anti-slop check.
seedance-prompt-short
Build, validate, and compress Seedance 2.0 prompts to a hard 2000-character limit using the Five-Layer Stack, @Tag delegation, and the new Compression Engine. Use when constructing or debugging any T2V, I2V, V2V, or R2V prompt for the short-form workflow.
seedance-pipeline
Integrate Seedance 2.0 with ComfyUI nodes and post-processing chains covering upscale, frame interpolation, color grade, composite, and metadata cleanup. Use when building automated video pipelines, connecting Seedance to external tools, or finishing and delivering a generated video clip.
seedance-motion
Control motion timing, beat density, action choreography, and sequential video extension chains for Seedance 2.0. Covers fight-scene physics, per-shot motion contracts, and multi-clip continuation techniques. Use when motion is too fast, too slow, or jittery, when choreographing action sequences, or when extending a video across multiple clips.