agentleFS
Sign inStart free
LeoYeAILeoYeAI/seedance-skills/skills/seedance-pipeline/SKILL.md

seedance-pipeline

Skill42 starsChanged 4 months agoMITView on GitHub

This skill should be used when the user asks about Seedance 2.0 workflow operations, API planning, BytePlus ModelArk, Dreamina/Jimeng surfaces, provider/router APIs, China-facing surfaces, ComfyUI, post-production, stitching, batch workflow, or integration planning.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this for operational workflows, APIs, web surfaces, post-production, and integration planning.

    line 24
  2. Very specific:

    Always load [ref:api-status] for current API and platform claims.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

seedance-pipeline

Use this for operational workflows, APIs, web surfaces, post-production, and integration planning.

Intent

Behind every API question is a person with a deadline, a budget, and something at stake on this working tomorrow. The soul of this skill is being the one voice in the room that answers with dates, sources, and a path instead of optimism. Reliability is the kindness this user needs.

Status Rule

Always load [ref:api-status] for current API and platform claims. Load [ref:model-name-map] when a user says Pro, Fast, V2, or a wrapper model ID. Do not rely on old release-status memory. Load [ref:api-workflow] for implementation planning, task lifecycle, Runway/Volcengine/provider field differences, pricing caveats, upload handling, and production readiness. Load [ref:pro-filmmaking-standards] for professional film, commercial, agency, localization, post, and delivery workflows. Load [ref:delivery-qc] before saying an asset is delivery-ready.

Workflow Split

  1. Web workflow: Dreamina/Jimeng surface, references, prompt, output review.
  2. API workflow: Volcengine, BytePlus, Runway, fal, or provider/router docs, model ID, auth, file handling, task creation, polling/querying, cancellation/deletion, task ledger, and retrieval.
  3. Professional production workflow: treatment, shot list, continuity ledger, reference rights map, review loop, post handoff, and delivery/QC.
  4. Post workflow: edit, conform, stitching, stabilization, audio cleanup, captions/subtitles, color, localization, versioning, textless, and delivery.
  5. First/last-frame workflow: map first frame, last frame, transition action, identity locks, and ending target.
  6. Runway workflow: model seedance2, runway:// uploads, audio-reference combination rules, plan/region caveats, and SDK type lag are Runway-specific.
  7. Provider/router workflow: EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML API, MuAPI, SeeGen, Segmind, or similar surfaces must be labeled provider-specific and rechecked before code or pricing guidance.
  8. China-facing workflow: prefer official ByteDance/Volcengine/BytePlus/Doubao/Jimeng/Jianying sources; workflow hosts, Chinese-language blogs, and business-partner news are not public API providers without provider-owned docs.
  9. Community workflow: ComfyUI or unofficial nodes must be labeled community/unverified unless sourced.
  10. Corpus-mining workflow: classify sources before reuse; extract structure and vocabulary, not unsafe raw prompts.

Output Contract

Return the workflow path, source status, required inputs, production phase, validation steps, delivery assumptions, and risks. For professional jobs, include the next artifact to create: brief, shot list, continuity ledger, prompt batch, review packet, localization matrix, or QC preflight.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free