Douyin Ai Script Generator
v1.0.0抖音AI视频脚本生成器。基于《AI自媒体短视频创作核心方法论》，由大模型直接生成高质量抖音AI主题短视频脚本。当用户需要：(1)生成抖音AI视频脚本，(2)创作AI主题的短视频内容，(3)获取AI热点话题并生成脚本时触发使用。支持自动搜索AI热点、大模型基于方法论自由生成脚本、使用爆款视频检测表评分（60分制，≥...
⭐ 0· 82·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description claim AI-based Douyin script generation. The SKILL.md and small helper script only rely on a web search tool (search_web) and a local save step; no unrelated credentials, binaries, or installs are requested. The included methodology file matches the described generation approach.
Instruction Scope
Instructions direct the agent to use an external 'search_web' tool for live trends, generate scripts using the included methodology, score them, and 'save to project root'. Saving files to the project root is expected for a generator but is the only file-system action the skill asks for. The skill also recommends a '恐惧驱动' (fear-driven) template — this is an ethical/content concern rather than a technical incoherence.
Install Mechanism
No install spec; instruction-only skill with one tiny helper script that only prints guidance. No downloads, package installs, or archive extraction are present.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The runtime instructions reference only a network search tool (search_web) which is consistent with the described automatic hotspot lookup.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. It can be invoked autonomously by default (platform normal), which is appropriate for an agent tool that generates content on demand.
Assessment
This skill appears coherent and low-risk from a technical perspective, but consider the following before installing:
- File writes: the agent will save generated scripts to the project root; ensure you are comfortable with the agent having permission to write files in that location and review any files it creates.
- Network searches: live trend fetching uses a search_web tool — confirm that the agent's search integration and any resulting data are acceptable for your environment.
- Content ethics and compliance: the methodology explicitly recommends 'fear-driven' templates that amplify anxiety; review generated content for compliance with platform rules and to avoid harmful or misleading messaging before publishing.
- Manual review recommended: the built-in scoring is subjective; always inspect and, if needed, edit outputs before posting.
If you want stronger guarantees, request that the skill log created file paths and do a quick manual audit of a few generated scripts.Like a lobster shell, security has layers — review code before you run it.
latestvk97bafmvhse56nadkjd6xmkxw183dbnt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.