Individual skill

yuwen-publish-precheck

国内自媒体发布前风险自审与保意修复：审口播稿、文章、图文笔记、字幕、封面文字能不能发抖音/小红书/微信视频号，给出具体位置、依据和可直接替换的改稿；被限流/删除/处罚后帮你复盘归因；你的行业敏感词、误报白名单和踩坑案例会沉淀成个人规则库，越用越准。Use when 用户说"能不能发""审一下稿子""查违禁词/敏感词""会不会限流/被限流了""帮我改成能发的版本""发布前检查""被平台处罚/删除了""帮我盯着这个词""导入违禁词表"。Not for 海外平台(X/YouTube)内容审核、起号涨粉策略、写稿创作本身。

SKILL.md

Read pinned source

Source commit b9efdc6bc1938b40ad1c556fba65c562fc182be0

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 812
Repository last updated: Oct 8, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai Repository topic
chinese Repository topic
claude Repository topic
content-compliance Repository topic
cursor Repository topic
douyin Repository topic
wechat-channels Repository topic
xiaohongshu Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.github/ISSUE_TEMPLATE/content-review.ymlasset · 1,837 bytes
.github/workflows/ci.ymlasset · 557 bytes
.gitignoreasset · 598 bytes
CHANGELOG.mddoc · 4,361 bytes
CONTRIBUTING.mddoc · 2,036 bytes
LICENSEasset · 1,067 bytes
LICENSE.mddoc · 1,067 bytes
MAINTAINING.mddoc · 3,998 bytes
README.mddoc · 9,405 bytes
ROADMAP.mddoc · 2,049 bytes
SECURITY.mddoc · 1,527 bytes
SKILL.mdcore · 15,903 bytes
SKILL.mdcore · 15,903 bytes
THIRD_PARTY_NOTICES.mddoc · 649 bytes
data/README.mddoc · 1,318 bytes
data/cases/README.mddoc · 805 bytes
data/history/README.mddoc · 322 bytes
data/wordlists/README.mddoc · 347 bytes
evals/test_rule_integrity.pyruns · 2,497 bytes
evals/test_scan.pyruns · 8,400 bytes
evals/trigger_cases.jsonlasset · 864 bytes
references/diagnose.mddoc · 4,180 bytes
references/industry-finance.mddoc · 9,843 bytes
references/industry-medical.mddoc · 12,321 bytes
references/judgment.mddoc · 5,322 bytes
references/platform-douyin.mddoc · 4,375 bytes
references/platform-shipinhao.mddoc · 1,876 bytes
references/platform-xiaohongshu.mddoc · 1,977 bytes
references/repair.mddoc · 5,193 bytes
references/rules-commercial.mddoc · 16,561 bytes
references/rules-common.mddoc · 25,840 bytes
scripts/scan.pyruns · 11,969 bytes
scripts/terms.jsonasset · 16,021 bytes
templates/expressions.mddoc · 2,266 bytes
templates/my-rules.mddoc · 1,117 bytes
templates/profile.mddoc · 647 bytes
templates/词库示例.mddoc · 496 bytes

Read excerpt


# Publish Precheck｜发布前审

审核的目的是让内容安全地发出去，不是把稿子改成没人看的官样文章。词面命中只是线索，违规与否取决于语境、商业属性和主张对象；修复必须保住作者的口吻、钩子和信息量，只动真正越线的部分。

## Outcome Contract

- **Outcome**：对一份待发布内容给出逐平台结论（可发/改后可发/不建议发）、带原文位置和规则依据的问题清单、可直接替换的修复稿，以及发布前检查单。
- **Done when**：词面预检已跑、候选逐条判定完、（改稿时）修复稿复检通过、报告已按输出模板给出并存档。
- **Evidence**：每个"必改"项都引用原文位置和规则编号；规则文档中每条规则附官方来源引文与链接。

## Hard Rules｜硬边界

- 只降低发布前可见的内容风险，不预测平台内部模型和账号权重，**不承诺 100% 过审**；
- **NEVER** 提供谐音、错字、拼音、拆字、emoji 替换、遮挡、暗号等绕审手段——这类写法平台单独打击，是在制造新风险，用户再要求也不给；