wepr-editorial-quality SKILL.md skillA
wepr-editorial-quality from shenyuannext/wepr-growth-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shenyuannext/wepr-growth-skills/wepr-editorial-quality@git:20260823.0852328Pins git:20260823.0852328 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shenyuannext/wepr-growth-skills
- Path
skills/wepr-editorial-quality/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260823.0852328, committed Aug 23, 2026
- First version recorded
- Aug 13, 2026
- Size
- 4,264 bytes
- Repository stars
- 7
- License
- MIT
审计并修复客户方案、传播稿、公关文案、广告文案、品牌文章、社交媒体内容和说明性文字中的机械表达、空泛判断、模板化节奏、证据缺口与作者语气流失。适用于用户要求降低 AI 感、检查文稿是否像机器生成、保留个人风格进行最小改写、发布前质检或说明具体修改；不判断文本是否确由 AI 创作，也不在缺少依据时新增事实、数据和观点。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# WEPR 文稿质量工作台 把“读起来像机器”拆成可定位、可解释、可修改的问题。保护事实和作者声纹，只改真正妨碍理解、可信度或表达目的的部分。 ## 路由 - 只检查、不改写：使用“诊断模式”，并读取 [references/diagnosis-and-patterns.md](references/diagnosis-and-patterns.md)。 - 保留作者风格完成改写：使用“最小改写模式”，并读取 [references/voice-preservation.md](references/voice-preservation.md)。 - 客户方案、公关、广告或其他高风险文本：同时读取 [references/evidence-and-delivery.md](references/evidence-and-delivery.md)。 - 需要自然中文终稿时，先完成本技能的质量与证据检查，再交给 `$wepr-human-writing`。 ## 工作流程 1. 确认读者、渠道、文本任务、作者身份、期望动作、可修改范围和不能改变的事实或措辞。 2. 通读全文，先判断核心意思和篇章任务，不逐句见词就改。 3. 建立内部保护清单：事实、数据、专有名词、报价、范围、承诺、合规表述，以及作者常用词、节奏、态度、幽默、不确定性和有效细节。 4. 将问题分成证据、清晰度、结构、语气和表面模式五类。先修证据与意思，再处理文风。 5. 将“写作机械感”和“内容实质风险”分开判断。后者包括虚构事实、误导性因果、未披露利益、危险建议、歧视或羞辱、隐私泄露、侵权素材及无法兑现的承诺；文风自然不能抵消这些风险。 6. 诊断模式只列可核验问题；改写模式执行最小必要改动，并保留原有有效结构和有辨识度的句子。 7. 完稿后进行反向核对：事实是否改变、观点是否加重、语气是否被抹平、具体信息是否被抽象化、篇章是否仍完成原任务。 ## 判断纪律 - 不声称或推测文本由 AI 生成。只能说明发现了哪些可观察的表达模式，以及这些模式如何影响阅读。 - 不用禁词表机械判定。一个词是否有问题，取决于它是否准确、具体、符合作者语气和文本任务。 - 不把所有短句、排比、标题、冒号、转折和总结都当作问题。广告、演讲、正式方案和社交内容的有效结构可以保留。 - 不为了“像人”故意加入错别字、口头禅、虚构经历、情绪或无依据的强观点。 - 不把专业内容改得娱乐化，也不把有个性的表达统一成平滑、礼貌、等长的标准段落。 ## 输出模式 ### 诊断模式 按严重程度输出： | 位置或原句 | 问题类型 | 影响 | 修改方向 | | --- | --- | --- | --- | 只引用识别问题所需的最短片段。结尾说明哪些个性表达值得保留，不给“AI 概率”或虚构分数。 …
Read the whole file at its exact version.
How to install
mdr add shenyuannext/wepr-growth-skills/wepr-editorial-quality@sha256:20fefe944e1fdc00The line at the top of this page pins the label git:20260823.0852328, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ctnhe6d4anwg7gpm)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 13, 2026 and Aug 23, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260823.0852328 latest | 2026-08-23 | 0852328 | 4,264 B | A | view · diff |
| git:20260823.fe8c22f | 2026-08-23 | fe8c22f | 4,005 B | A | view · diff |
| git:20260813.1e50630 | 2026-08-13 | 1e50630 | 3,990 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 (4264 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
shenyuannext/wepr-growth-skills · 7 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ctnhe6d4anwg7gpm GET https://markdownregistry.com/api/v1/resolve?ref=shenyuannext/wepr-growth-skills/wepr-editorial-quality GET https://markdownregistry.com/api/v1/blob/20fefe944e1fdc00cd01ebb42425cc5e485543c6c74bdcb5eafb0a5e4775fd48
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.