Super Oral Broadcast Agent
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_a690e492/13727539951.
About this skill
Problem: spoken scripts need more than polished prose
Short-video talking scripts require a strong first few seconds, enough information density in the middle, and an ending that invites on-platform engagement without creating compliance risk. Many drafts also contain plausible data, outdated policy references, or claims whose sources and context are not verified before publication.
How the skill works
Super Oral Broadcast Agent turns spoken-script production into a reviewable workflow:
- Structure selection: choose from ten broadcast templates, such as A: problem -> counterintuitive claim -> three-step breakdown, G: seven-step spoken framework, or I: opinion -> rebuttal -> own view.
- Opening and ending design: build the first three seconds using preview, front-loading, and retention hooks; keep closing calls limited to safe platform actions like follow, like, or comment.
- AI-tone removal: remove filler, formulaic contrast, overwrought rhetoric, and common AI-like phrasing, then rewrite the copy in a more human, conversational register.
- Fact and timeliness checks: use multi-search-engine to cross-check data, policies, and cases across search engines, with time filters when the source may be stale.
- Compliance review: scan for absolute claims, finance-sensitive wording, off-platform funneling, medical-efficacy terms, political red lines, and missing AI-content labels.
The output can include a scorecard covering compliance safety, factual accuracy, natural expression, and publishing readiness. Scores below 80 suggest revisions before release, while higher scores can be treated as closer to publishable.
Boundaries
The skill is useful for first drafts, script diagnosis, de-AI rewriting, and pre-publication compliance checks, but it is not a legal review. Finance, health, investment, and beauty-efficacy content still requires professional verification and relevant qualifications. Search-based checks depend on page quality, access rights, and fast-changing hot topics. If the user asks for “reply with a keyword to get materials” or “DM me for the file,” the skill should replace that with safe on-platform engagement instead of producing funneling language.
Use Cases
- Draft a science explainer opening by choosing an A or G structure and adding a first-3-second hook plus a closing prompt.
- Rewrite an old script by removing AI-heavy phrasing, fixing pacing, and turning a long article into a recordable spoken draft.
- Review a script before publishing by scanning prohibited terms, checking data freshness, and producing a compliance and fact scorecard.
- Find a timely topic by searching the last 24 hours across multiple engines, verifying case sources, then writing the spoken script.
Best For
- Short-video operators running Douyin talking accounts who need weekly topics, opening hooks, and compliant scripts.
- Knowledge creators or industry writers who need long articles and reports turned into recordable spoken scripts.
- Editors doing pre-publication checks who need quick scans for prohibited terms, funneling phrases, and data sources.
- Writers using LLM drafts who need to rewrite AI-like copy into more natural spoken language.
Related Skills
Rewrite self-introductions by scenario, audience, and duration, with memory hooks, structure feedback, and speakable practice versions.
Helps AI Agents apply local CSS themes to Markdown articles with wenyan-cli, including preview, WeChat draft publishing, and theme registration.
Turn Markdown or plain text into styles for Xiaohongshu, WeChat Official Accounts, Zhihu, Weibo, Douyin, Bilibili, and Toutiao.
A multi-platform writing workflow for WeChat that emphasizes information gain, scannability, SEO/GEO, and localization to produce verifiable, high-signal blog posts.