agentleFS
full-aigc-pluginsfull-aigc-plugins/dreamina-design-plugin/skills/dreamina-auto-seedance/SKILL.md

dreamina-auto-seedance

Skill0 starsChanged 23 days agoApache-2.0View on GitHub

Automatically turn a validated DCC preview into an approved Seedance video through Dreamina Design MCP, with submit-once recovery and verified download.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user explicitly wants the validated Blender preview turned into a final Seedance video automatically rather than opened in …

    line 8
  2. Very specific:

    Never send the .blend scene.

    line 29
  3. Distinctive:

    Never resubmit after timeout or an unknown state.

    line 30
  4. Very specific:

    Never treat CLI exit zero or querying as Completed.

    line 31
  5. Very specific:

    Never invent a quote. If none is available, stop unless the exact request has auto_exact_request authorization.

    line 40
  6. Very specific:

    Call dreamina_submit_video once and persist its submit ID before reporting Submitted.

    line 43
  7. Very specific:

    Call dreamina_query_task for the same ID until success, failure, or Unknown.

    line 45
  8. Distinctive:

    Keep account identity, credentials, approval material and local absolute paths out of the cross-plugin ledger.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Automatic Seedance Entry

Use when the user explicitly wants the validated Blender preview turned into a final Seedance video automatically rather than opened in Jimeng Web.

能力边界说明

✅ 能做

  • Validate the local preview receipt and current SHA-256.
  • Discover live Dreamina capabilities/account readiness.
  • Obtain action-time approval, submit once, query, download and verify.

⚠ 需要用户确认

  • A paid request must have an exact model, resolution, duration and either an authoritative maximum-charge envelope or explicit auto_exact_request permission when Dreamina exposes no quote API.
  • Dreamina authentication or Web compliance prerequisites may require user action.

❌ 超出范围

  • Never send the .blend scene; send only the validated preview.
  • Never resubmit after timeout or an unknown state.
  • Never treat CLI exit zero or querying as Completed.

Workflow

  1. Require PreviewValidated; independently re-hash the local artifact.
  2. Instantiate McpDesignClient over the host's MCP tool invoker. It may call only dreamina_cli_status, dreamina_account, dreamina_submit_video, and dreamina_query_task.
  3. Build the exact multimodal2video request from live capability data.
  4. Never invent a quote. If none is available, stop unless the exact request has auto_exact_request authorization; native paid-action approval still occurs inside dreamina_submit_video.
  5. Call dreamina_submit_video once and persist its submit ID before reporting Submitted.
  6. Call dreamina_query_task for the same ID until success, failure, or Unknown; unknown permits query-only recovery.
  7. Download into the approved root, verify media metadata, bytes and SHA-256, then and only then transition to Completed.

The durable handoff must retain the real submit identifier:

{"state":"Submitted","design_submit_id":"<provider-submit-id>","retry_allowed":false}

Privacy

Keep account identity, credentials, approval material and local absolute paths out of the cross-plugin ledger. Persist non-secret hashes, submit IDs, states, timestamps and error categories only.

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.