SKILLEMALL.ai
GitHub ↗ RU Sign in

AF seedance-2-prompt-engineering-video-gen

Design production English prompts for Seedance 2.0 then generate text-to-video or image-to-video on WeryAI (`SEEDANCE_2_0`), using bundled recipes (A–K), mode-to-JSON mapping, camera vocabulary, and pre-flight checklists. Use when you need JiMeng-grade prompt control translated to WeryAI submit-* flows with explicit pre-submit confirmation. SEO: Seedance 2.0 prompt engineering; Seedance text and image to video; recipe library.

ClawHub Agent Skills author: parallel world v1.1.2 MIT-0 9 files body ≈ 3 547 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 52/100 · Will not run — References files that are not bundled: url

GeneratorAI and agentsMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
81
Run on models
none yet
Process rating
F
52/100
Will not run
References files that are not bundled: url
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: url

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: url
  • 0Tools and files. 1 referenced file(s) missing: url
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (seedance-2-prompt-engineering-video-gen) differs from the folder (seedance-2-prompt-engineering-to-video)
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 42 steps, 1 vague phrases
  • 100Failures and branches. 5 branches, has a failure section
  • 100Execution cost. Instruction body is 3547 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 430: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 42 items
  • +4Has examples (0 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: clean
This is a disclosed WeryAI video-generation skill with paid network actions and optional image upload, but the artifacts describe those behaviors clearly and keep them aligned to the stated purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026