ClawHub

Seedance Prompt Wizard

v1.0.4

Seedance 2.0 提示词生成向导。通过引导式对话， 逐步收敛用户需求，生成精准的 Seedance 2.0 Prompt。 不做任何 API 调用，不涉及认证。 触发词：帮我写提示词、生成视频提示词、Seedance提示词、视频生成提示词，制作提示词

⭐ 0· 51·0 current·0 all-time
byxiaoke321@xk103295870-alt·duplicate of @xk103295870-alt/seedance2-video-gen (1.0.2)·canonical: @xk103295870-alt/seedance2-anna
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description say this is a guided prompt-wizard for Seedance 2.0 and the SKILL.md contains only dialogue flow, question templates, prompt structure, and output formatting — all appropriate for a prompt-generation helper. No unrelated credentials, binaries, or system access are requested.
ℹ
Instruction Scope
Instructions are limited to asking the user questions and assembling a Seedance prompt. The doc references an external API URL and mentions 'link validity: 24 hours' and example API parameters as usage guidance; however the skill itself does not instruct the agent to call that API or transmit data, so this is informational rather than an operational instruction. If the agent or a user later uses the generated prompt with the referenced API, they should validate that separately.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, no credentials, and no config paths. There is no disproportionate request for secrets or unrelated service tokens.
✓
Persistence & Privilege
always is false and the skill is user-invocable. The default ability for the agent to invoke the skill autonomously is unchanged; that normal platform behavior does not raise additional concerns here given the skill's limited scope.
Assessment
This skill is an instruction-only prompt wizard and appears coherent with its stated purpose. Before using: (1) confirm you do not paste secrets or private files into the conversation when providing references; (2) if you plan to run the generated prompts against the referenced Seedance API, review that API's documentation and access requirements separately (the skill itself does not perform API calls); (3) test generated prompts with non-sensitive example content first to ensure results meet expectations.

Like a lobster shell, security has layers — review code before you run it.

latestvk9787g93gbxqe9ys9y11m9bbbn847bge

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments