dbs-content-risk-check is a pre-publish review for creators on Chinese social and content platforms. You submit a title, body, subtitles, voice-over, image text, a profile or a video description, and it points to the exact sentence or frame that may cause blocking, review or reduced reach.
It answers two separate questions: what an automatic filter may pick up, such as contact details, links, QR codes or listed words, and what is a real problem in the content, such as fraud, false claims or illegal lead generation. Strong opinions, emotion and personal style stay untouched. When asked about a video disclaimer, it also writes a three-line on-screen note.
What You Get
- A two-line conclusion: what machine review may flag and whether the content has a real problem
- A priority list of quoted passages with the concrete problem and the smallest edit
- A list of passages that may trip machine review, with notes on likely false alarms
- Facts to confirm before publishing, such as product category, qualification or sponsorship
- An optional three-line on-screen note for a video, when the context calls for it
- A statement of what was not checked
Common Use Cases
- Checking a Xiaohongshu note for contact details, external links or ad structure before posting
- Reviewing recruitment, order-taking or product posts for lead-generation and qualification issues
- Reviewing medical, finance or education claims for unsupported promises
- Asking what small caption to put on a video that states an opinion or personal experience
What Makes It Unique
Most keyword checkers return a list of flagged words. This Skill keeps machine-filter risk and content risk as two separate verdicts, demands a named mechanism before calling something a real violation, and keeps strong opinions and personal voice. It refuses to produce workarounds such as homophones or coded comments, never says a post can or cannot be published, and gives no legal opinion.
Under The Hood
This Skill is instructions only. The agent reads SKILL.md, which holds the review steps, the risk categories, the report format and the rules for on-screen notes, and applies them to what you submit. It has no scripts and writes no files. It does not open links in your draft unless you ask for the page to be checked, and it looks up a platform’s current official rules on the web only when the answer depends on them.