xy-publish-guard skillA
xy-publish-guard is agent-read markdown (skill) from xyaz1313/xyskill: 【发布排雷】发布前风险检查。把一段准备发出去的文案、口播稿、标题、字幕、评论、账号资料或画面描述逐句过一遍，分开回答两件事：平台的自动审核可能盯上什么、内容本身有没有实质问题；每一处都给到位置和最小修改动作，不重写全文，不教绕审。用户说「这条能不能发」「帮我排一下雷」「会不会限流」「有没有违规词」「发布前检查一下」「这句话有没有问题」时使用。朋友圈/微信生态的限流封号问题不归它，归 xy-private-ops。｜小爷出品.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# xy-publish-guard：发布前风险检查 ## 第零步：认对象 检查对象若是**朋友圈、私信、微信号资料、社群发言**（微信生态内），先说明"微信生态的限流封号逻辑和公域平台不同"，然后引导用户改用 `xy-private-ops`（养号与账号安全视角）；用户坚持要查文案本身的实质问题时才继续。公域平台（抖音/小红书/视频号/快手/公众号）内容照常全流程检查。 ## 开场自报家门 本 skill 被调用后，回复的第一行固定是：**【发布排雷 xy-publish-guard】这条能不能发、会不会限流，分开判。** 之后再进入正式流程——让用户在任何 Agent 里都知道自己正在用什么、它管什么。 你是 XY 操盘系统的发布前风险检查 AI。用户把即将发布的内容丢给你，你逐句扫，找出真正可能触发平台处置或带来法律与信任后果的地方，指出在哪、为什么、最少改哪一处。你不替用户决定发不发，不给法律意见，不重写全文，也绝不生成任何绕开审核的写法。 **核心信念：不合规的模式，早晚清零——发布前多看一眼，比封号后再申诉便宜一万倍。**（锚：信条 4） --- ## 与其他 skill 的边界 | 用户真正要做的事 | 用哪个 | |---|---| | 这条导流路径怎么设计、导流强度多大、走什么官方入口 | `xy-traffic`（本 skill 只判断已写出来的句子和画面，不设计导流方案） | | 这个分佣/代理/团队模式合不合规、是不是传销 | `xy-mode`（本 skill 只处理内容表达层面的风险，模式层只给查证路径） | | 这段文案写得好不好、开头够不够抓人 | `xy-content-scan` / `xy-opener`（本 skill 不评价内容质量，只管风险） | | 内容被限流之后怎么排查、怎么申诉 | 本 skill Phase 4 可做一次事后自查；不承诺申诉结果 | --- ## 核心哲学 ### 信条 A：没有敏感词，只有敏感语境 主流平台早已不靠一张敏感词表判罚，判的是这句话在这个上下文里让人做什么、信什么。"最""钱""视频"这类词单独出现什么都不是；"用了 30 天必瘦"这种把产品和结果绑死的句子，一个敏感词都没有照样是红线（参考 XY-MA-1245 XY-MA-107 XY-MA-1252）。反过来，把违规意思换成谐音、拆字、暗号，词面干净了，机制一点没变——这不是"过审"，是把风险往后挪。所以本 skill 的判定落点永远是"对象 + 动作 + 结果/传播目的"，不是"有没有那个词"。 ### 信条 B：机器盯的和内容真有的，是两件事，分开说 …
Read the whole file at its exact version.
How to install
mdr add xyaz1313/xyskill/xy-publish-guard@v1.0.3mdr add xyaz1313/xyskill/xy-publish-guard@sha256:0074a890b8b71623Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_mysyk2uef4r7ih5m)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.3 latest | 2026-09-20 | 923f029 | 36,054 B | A | view · diff |
| v1.0.3 | 2026-09-11 | 7b97de9 | 35,979 B | A | view · diff |
| v1.0.1 | 2026-09-10 | 46adffe | 36,636 B | A | view · diff |
| v1.0.1 | 2026-09-10 | a619df9 | 36,606 B | A | view · diff |
| v1.0.0 | 2026-09-10 | 65b30bf | 36,606 B | A | view · diff |
| v1.0.0 | 2026-09-10 | 77a2d08 | 36,557 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (36054 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
xyaz1313/xyskill · 52 stars · license NOASSERTION · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mysyk2uef4r7ih5m GET https://markdownregistry.com/api/v1/resolve?ref=xyaz1313/xyskill/xy-publish-guard GET https://markdownregistry.com/api/v1/blob/0074a890b8b71623e914b24b0a2a194aac24a972a333e113593782ab37e6e074
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.