CN Video Script Writer 短视频脚本生成器
v1.0.0短视频脚本生成专家，面向抖音、B站、YouTube、小红书、视频号内容创作者，快速生成爆款脚本和文案。触发场景：用户提到"写脚本"、"短视频脚本"、"抖音文案"、"B站脚本"、"视频选题"、"直播话术"、"爆款标题"、"小红书笔记"、"视频号脚本"、"YouTube脚本"、"口播稿"、"分镜脚本"、"带货话术"、...
⭐ 0· 121·0 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/description (short-video script writer for Douyin/B站/YouTube/etc.) align with the provided SKILL.md and reference templates; the files contain templates, hook formulas, and platform style guides that are appropriate and expected for this purpose. No unexpected resources (cloud creds, binaries) are requested.
Instruction Scope
Runtime instructions are limited to collecting user input (theme, platform, audience), selecting templates from included reference files, and generating scripts/titles/tags. There are no instructions to read system files, access environment variables, call external endpoints, or exfiltrate data.
Install Mechanism
No install spec and no code files (instruction-only). Nothing is downloaded or written to disk by an installer; this is the lowest-risk install profile.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no disproportionate secret requests or unrelated credential asks.
Persistence & Privilege
always is false and the skill does not request special persistent privileges or modifications to other skills. disable-model-invocation is default (false), which is the platform normal behavior and not itself a red flag.
Assessment
This skill appears coherent and low-risk from a technical-access perspective (no creds, no installs, no external endpoints). Things to consider before installing or using it: 1) Provenance/trust: source/homepage is unknown—if you need stronger supply-chain assurance, prefer skills with a known author or homepage. 2) Content risk: the templates encourage attention-grabbing hooks (e.g., numerical claims, '99% of people') — review outputs for false/misleading claims, legal/compliance issues (advertising, endorsements, medical/financial advice), and avoid publishing unverified assertions. 3) Privacy: the skill will ask for topic/product/user-provided details—do not send sensitive personal data or secrets into prompts. 4) Copyright and originality: outputs are template-driven; check for potential plagiarism or reuse of copyrighted material if that matters for your publishing. 5) Test before scale: run sample prompts to check tone, accuracy, and whether it fits your brand/community rules. Overall, technically coherent and internally consistent, but exercise the usual editorial and provenance caution.Like a lobster shell, security has layers — review code before you run it.
chinesevk9750fcmfygmcyktr2j59k7sm183j2e9contentvk9750fcmfygmcyktr2j59k7sm183j2e9creatorvk9750fcmfygmcyktr2j59k7sm183j2e9latestvk9750fcmfygmcyktr2j59k7sm183j2e9videovk9750fcmfygmcyktr2j59k7sm183j2e9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.