dy-content-compliance
Skill1 starsChanged 14 days agoMITView on GitHub
经验规则,以平台最新《抖音社区自律公约》为准;涉嫌风险的内容以平台「快速检测」结果为准。
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-agents-standard.mdcCursor rule
- .cursor/rules/dy-publish.mdcCursor rule
- .cursor/rules/jev-claude.mdcCursor rule
- .cursor/rules/xhs-bundesliga.mdcCursor rule
- .cursor/rules/xhs-package-dod.mdcCursor rule
- .cursor/rules/xhs-publish-plain-text.mdcCursor rule
- .cursor/rules/xhs-series-v2.mdcCursor rule
- .cursor/rules/xhs-traffic.mdcCursor rule
- football-content-opsSkill
- atutun-xhs-coverSkill
- dbs-xhs-titleSkill
- douyin-cliSkill
- dy-culture-rxSkill
- dy-flowus-dbSkill
- dy-note-adaptSkill
- ip-character-systemSkill
- jev-judgeSkill
- tt-note-adaptSkill
- xhs-account-positioningSkill
- xhs-content-complianceSkill
- xhs-flowus-dbSkill
- xhs-note-structureSkill
- xhs-pipelineSkill
- xhs-title-ab-testSkill
- xhs-title-skillSkill
- xhs-topic-bankSkill
- xhs-voice-polishSkill
- xhs-weekly-retroSkill
- xiaohongshu-cliSkill
The file
Files
dy-content-compliance — 抖音内容合规审查
用途
生成抖音标题、描述、配图文案时的合规审查。与小红书规则是镜像逻辑,本卡单独生效,不套 xhs 卡。
经验规则,以平台最新《抖音社区自律公约》为准;涉嫌风险的内容以平台「快速检测」结果为准。
严禁(直接限流/处罚)
1. 竞品/跨平台
- 提「小红书」「快手」「B站」「微信」等平台名(小红书镜像大忌)
- 露出其他平台的 logo / 水印(小红书图卡必须先确认无水印,本仓图卡只带 BAWBAW + @bawbaw,可直发)
- 外链/导流:微信号、QQ、电话、二维码引流、评论区导流
2. 极限用语(同 xhs,绝对化)
- 第一、唯一、首个、NO1、Top1
- 最高、最低、最好、最大、最强、最全、最新、最佳
- 顶级、世界级、国家级、金牌、绝对、100%、永久
3. 诱导互动(处罚)
- 点赞、关注、收藏、转发、一键三连、口令
- 用「评论区聊聊/你怎么看」引导讨论(可),不要写「求赞/求关注」
4. 资质类(更严)
- 医疗、金融、教育、法律、财经等需资质;无资质别碰硬科普/荐股/问诊
5. 隐私/侵权
- 未经授权真人正脸、车牌号、身份证、水印截图
- 版权音频/影视片段
抖音图文规范
- 标题 ≤30 字,描述 ≤1000 字
- 图 1–35 张,推荐 3:4(1080×1440)
- 话题:正文内联
#话题,蹭相关热点可,别堆无关话题 - 热点时效 24h;避免高频重复发同一内容
发布前核验清单
- 已过抖音可发闸(
.cursor/rules/dy-publish.mdc):题材、封面、时段、间隔 - 封面是夜场比分卡,不是 XHS 对撞板 / 今天风原图
- 标题无极限用语、无平台名
- 描述无竞品/导流/诱导互动
- 图片无小红书或其他平台水印/logo
- 无资质类敏感内容
- 话题与内容相关,≤8–10 个
- 已把小红书正文改成抖音短描述(文案转换 skill)
- 已选配乐,不是原声空发
与 xhs 卡的关系
- xhs 卡禁止提「抖音」;dy 卡禁止提「小红书」——两卡各自用,不要互相套。
- 合规分:
xhs post返回 10/10 只代表过小红书检查,不保证抖音,需再走本卡。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

