Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
检查和清理中英文文本里的 AI 套路,适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求;按场景控制力度,同时保留事实、术语、语域和责任主体。
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhua --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .claude/skills/shuorenhua && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .claude/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-mainType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhua --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .agents/skills/shuorenhua && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .agents/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhua --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .cursor/skills/shuorenhua && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .cursor/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lornshrimp/Lorn.NovelWriteSkills.git --path 'CommonSkills/通用-去AI味重写/shuorenhua-main'--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhua --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .gemini/skills/shuorenhua && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .gemini/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhuaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .github/skills/shuorenhua && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .github/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lornshrimp/Lorn.NovelWriteSkills shuorenhua --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lornshrimp/Lorn.NovelWriteSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'CommonSkills/通用-去AI味重写/shuorenhua-main' .opencode/skills/shuorenhua && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "shuorenhua" agent skill from https://github.com/lornshrimp/Lorn.NovelWriteSkills/tree/main/CommonSkills/%E9%80%9A%E7%94%A8-%E5%8E%BBAI%E5%91%B3%E9%87%8D%E5%86%99/shuorenhua-main into .opencode/skills/shuorenhua/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shuorenhua", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
shuorenhua检查和清理中英文文本里的 AI 套路,适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求;按场景控制力度,同时保留事实、术语、语域和责任主体。
Shuorenhua is an agent skill from lornshrimp/Lorn.NovelWriteSkills. 检查和清理中英文文本里的 AI 套路,适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求;按场景控制力度,同时保留事实、术语、语域和责任主体。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 59 other files, including reference files and assets (for example `.github/ISSUE_TEMPLATE/bad-case.md`, `AGENTS.md` and `CHANGELOG.md`).
It sits in Development. The repository describes itself as: 一个面向长篇网文 / 小说创作工作流的 AI 写作资产库。它不是“随手堆提示词”的仓库,而是一套围绕 题材设计 → 大纲搭建 → 章节创作 → 审阅润色 → 多平台改写 → 质量门禁 → 分发落盘 搭起来的可复用写作系统。 The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit f36540b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Shuorenhua loads about 2.5k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 25 tokens; SKILL.md has 651 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from lornshrimp/Lorn.NovelWriteSkills at commit f36540b, republished under its MIT licence (© lornshrimp). 651 words, ~2,470 tokens.
.claude/skills/shuorenhua/SKILL.md (or your agent's skills folder). This skill also uses 54 other files; get the full folder from GitHub.把文本从”像模型在表演写作”拉回”像具体人在当前场景下表达”。
这份 skill 不是敏感词替换器,也不是反技术、反抽象、反专业。它的目标是减少模板感、表演感和语域漂移,同时保住事实、术语和责任主体。
在下面这些需求里使用:
chat、status、docs、public-writing在下面这些需求里不要硬套:
in-place scope,就只做句内改写。按固定顺序做,不要跳步:
chat / status / docs / public-writingprotected spans,看有没有必须保留的术语、系统主语、引用原文、命令或正式语体Tier 1 / Tier 2 / Tier 3,按问题命中强度判断,不要把 Tier 当作改写力度minimal / standard / aggressivestructural / bounded / in-place,判断这次能删到什么程度——自由删并重排、只把整句空话进删除清单、还是一句都不删references/,默认继续按问题类型补看 Protected Spans、Positive Style Contract、微操作手册、结构反模式 和相关短语表;如果目标是“改完能直接发”,或文本明显属于 README、release note、论坛帖、issue 回复,再补看 Scene Packs、真实样本评测 和 改写示例annotation mode执行第 6 步时,先按“模式”处理,再按“词条”兜底:
先判主场景,再处理局部问题。混合文本只保留一个主语域,其他语域只在必要信息层面留下。
chat信号:
默认档位:minimal
status信号:
默认档位:minimal 或 standard
docs信号:
默认档位:minimal
public-writing信号:
默认档位:standard
更细的下限限制见 场景禁改表。
如果文本本身命中下面任一子场景,不依赖用户是否明说,也不受主场景初判限制,都要补看 Scene Packs:
README:出现项目介绍、快速开始、安装方式、功能列表、README intro 等信号时,第一屏要说清“这是什么、给谁用、解决什么问题”release-note:出现版本标题、Release Highlights、Added / Changed / Fixed / Tested、changelog 列表等信号时,列清本版变更、验证和限制,不写发布宣言forum-post:出现 Linux.do / V2EX / 社区帖 / 发帖复盘等信号时,保留维护者的真实观察和社区语气,不改成公告issue-reply:出现 issue / PR 回复、bad case、复现、下一版补 benchmark 等信号时,先确认问题和下一步,不做客服式安抚子场景只负责发布目的和语气收束,不覆盖 protected spans、Tier、档位和回读规则。完整策略见 Scene Packs。
只加载 SKILL.md 时,也必须能完成基础改写。下面这些规则默认直接生效:
值得注意的是、让我来为你解释、希望这对你有帮助、Great question!综上所述、归根结底、本质上、At the end of the day不是 X,而是 Y、与其 X,不如 Y 多数删前半句,直接说 Y研究表明、数据显示、studies show、experts say 默认按场景选择 rewrite-safe 或 audit-only;只有用户明确要保留原论证骨架时才用 rewrite-with-placeholder;不要补虚构来源赋能、抓手、闭环、收窄、兜住、落盘、leverage你不是敏感、你只是太久没被稳稳接住了、你问到了问题的核心、顶刊作者的素养,默认删姿态层,改回低承诺回应或具体判断;不要硬演“我懂了”基于……、通过……来……单文件模式只是兜底,不是完整模式。只要环境里能读 references/,默认就继续补看对应文件;只有在 system prompt 真的只给了 SKILL.md 时,才退化为只按本文件做基础清理。
处理无源引用时,固定只在这 3 种模式里选一种:
rewrite-safe研究表明 / studies show / 业内人士认为 这类权威铺垫chat 和 public-writingaudit-onlydocs 和 statusrewrite-with-placeholder如果用户没指定模式,就按场景默认值走;如果文本跨场景,优先取更保守的 audit-only。
minimal适用于:文本本身基本自然,只需去掉局部模板感、收尾腔和多余修辞。
默认动作:
standard适用于:有明显 AI 腔或语域混搭,但信息骨架是好的。
默认动作:
aggressive适用于:Tier 1 命中密集,或 Tier 1 + Tier 2 叠加后整段呈现强模板感或强表演感。
限制:
Tier 1 明显密集,或多类结构问题叠加时才允许docs 默认不要升到 aggressiveScope 表示这次能不能改动句子和段落结构,和 minimal / standard / aggressive 是两条轴。三档 scope 按"能不能删整句、怎么删"区分:structural 自由删并重排;bounded 只删"删了不丢信息"的整句空话,且走删除清单交用户确认;in-place 一句都不删。
structural默认 scope。适用于短文本、明确要求重写的文本、AI 味密度很高且不需要保留原节奏的文本。
允许动作:
bounded中文 public-writing 长文(约 1000 字以上)的默认 scope。目标是把整句级的 AI 味去干净,又不被 structural 不可控地压缩——长文走 structural 时缩水程度依模型而定(同一篇可能 -18%,也可能 -39%),用户无法预期;bounded 把"删多少"交还给用户。
和另两档的关系:
structural 克制:不合并相邻句、不重排段落、不删承担节奏的实句或有意重复in-place 能去味:允许删"整句都是空话"的句子,但不直接删,而是进删除清单交用户拍板一句能进删除清单,必须同时满足三条:
两类动作分开走(实测依据:长文里句首引导词模型能句内清掉,但整句空话在 in-place 下删不掉,只会被软化成另一种说法):
值得一提的是 / 归根到底 / 这说明)后面还跟着实质内容 → 直接句内洗,删引导词留骨架,不进清单不仅仅是……更是…… 的价值拔高)→ 进删除清单,不擅自软化成另一种说法输出:正文给句内洗后的稿,末尾附「建议删除(待确认)」清单,每条写 原文 + 为什么删了不丢信息。用户点头才删,长度由用户拍板。
in-place适用于用户明确要求"完全原样 / 一句都别删 / 严格保句数"的情况,比 bounded 更严:整句空话也不删,只做句内降调。
默认触发条件:
bounded 仍删多了禁止动作:
允许动作:
删短语前先做语义独立性检查:删掉短语后,剩余部分必须仍是完整、可读、没有悬空指代的陈述句。否则改用句内替换,不要硬删。遇到整句空话,保留原句并标注 [空句,建议人工确认是否删除],不擅自软化成新说法。
aggressive + in-place 可以存在,但默认先提醒用户:长文 aggressive 很容易明显缩水;如果用户真正要保长度,优先改成 standard + bounded。用户明确坚持时,再执行 aggressive + in-place,但仍遵守不删整句、不并句、不重排的边界。
Tier 表示问题命中强度,与 严重度分级 保持一致,不表示改写力度。
默认替换。命中这类词或句式时,通常直接删掉或换成更具体的表达。常见类型:
默认处理:局部命中用 minimal 或 standard,密集命中时可升到 aggressive
单独出现可以放行,但同段聚集时是 AI 味信号。常见类型:
长度参考:短段落(< 100 字/词)同段 2+ 个即标记;长段落(≥ 100 字/词)同段 3+ 个再标记。
默认处理:保留最贴切的一个,其余改写;通常用 minimal 或 standard
常见词本身不构成问题,只在全文密度明显过高时才处理。常见类型:
重要 / 关键 / 核心 / 提升significant / innovative / effective默认处理:只替换一部分重复命中,通常用 minimal,必要时不改
以下内容默认优先保留,除非用户明确要求改风格且改动不损害信息:
不要为了“像人”把文本改得更假。专业文本可以专业,关键是别模板化、别表演化。
完整的保护清单见 Protected Spans。
改写后的文本应尽量满足:
更完整的正向目标、分场景校准和“cleaner vs more human”对照见 Positive Style Contract。
默认输出一个推荐版本,不默认输出审稿过程、多版本比稿或逐条点评。
只有在用户明确要求下面这类事情时才启用:
先别改,先标问题这段哪里像 AI只做诊断 / 审稿 / 标注先告诉我该不该改annotation mode 不直接给整段改写稿,默认只输出最重要的 1-5 个问题点。每个问题点固定包含这 4 个字段:
问题族:例如 开场套话 / 无源引用 / 工程师腔 / 语域混搭触发点:点明命中的词、结构或局部句子建议动作:删掉、换成具体表达、补来源、保持不动是否建议改写:是 / 否额外约束:
是否建议改写:否annotation mode 时,仍然按默认改写合同输出单一推荐版本遇到无源引用时,输出必须符合所选模式:
annotation mode 下,只输出对应的处理建议,不直接给整段改写稿rewrite-safe:建议删掉无证据权威铺垫;如果不是 annotation mode,再给改写结果,不补虚构来源audit-only:优先点明缺来源、缺归属,而不是假装已经证实rewrite-with-placeholder:允许保留论证位置,但要显式暴露“此处待补来源”;如果不是 annotation mode,可以给带占位提示的改写结果只有在高风险误杀时,才额外补一行极短说明,例如:
保留了系统主语和术语,避免失真。这里只做轻改,避免把正式公告写成口语贴。提交改写前,把回读固定拆成两步,不要混着做:
先检查这 5 项:
如果删掉一句后段落突然没了落点,就补一条事实句,不要补口号句。
bounded / in-place scope 下额外检查:
in-place:输出字数低于原文 85% 时,回退检查是否误删整句、并句或压段落(in-place 不该删任何整句)bounded:字数会因删整句空话而下降,不设硬下限;但要确认删除清单里每条都是"删了不丢信息"的纯空句,没混进实句或承担节奏的重复只有在第一遍已经保住事实、但读起来还有轻微 AI 味时,才做第二遍。第二遍固定只查这 5 件事:
结论先说 / 直接说结论 / 值得注意的是 这类提示层总的来说 / 归根结底 / 最终来看 这类空收尾方向是对的 / 意义重大 / 真正理解了用户第二遍只允许做轻量修正:
第二遍不要做的事:
场景保守策略:
public-writing 和 AI 味偏重的 chat,第二遍更常需要docs / status / code-context 默认更保守;如果第二遍会让语气变口语、变广告、或影响保真,就停在第一遍SKILL.md + references/ 一起工作Tier 1 / 2 / 3 校准命中规则:看 严重度分级annotation mode 的对照:看 改写示例默认做法是:先用本文件完成“场景、Tier、档位、输出合同”的主判断,再按问题类型补读 references/;只有在单文件安装场景里,才停留在本文件的兜底规则。
© lornshrimp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 54 other files (references, assets) in CommonSkills/通用-去AI味重写/shuorenhua-main of lornshrimp/Lorn.NovelWriteSkills.
Open the folder on GitHubat commit f36540b
Shuorenhua next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Shuorenhua this skilllornshrimp/Lorn.NovelWriteSkills | 232 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
lornshrimp/Lorn.NovelWriteSkills
A skill your agent uses when creating a full or partial set of genre wrapper skills under a genre directory.
lornshrimp/Lorn.NovelWriteSkills
Vibe Writing 写作系统,用于创建高质量、低AI检测率的中文文章。适用于公众号文章、博客、Newsletter等内容写作,也可用于修改已有文章降低AI味,或审校内容质量。包含三遍审校机制、降AI味技巧和口语化写作指南。
Categories
检查和清理中英文文本里的 AI 套路,适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求;按场景控制力度,同时保留事实、术语、语域和责任主体。. NovelWriteSkills.
Shuorenhua fits situations like: development work in your project.
Run `npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a claude-code`. Or copy the skill folder (CommonSkills/通用-去AI味重写/shuorenhua-main in lornshrimp/Lorn.NovelWriteSkills) into .claude/skills/shuorenhua in your project. Claude Code loads it when a task matches its description.
Run `npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a codex`. Or copy the skill folder (CommonSkills/通用-去AI味重写/shuorenhua-main in lornshrimp/Lorn.NovelWriteSkills) into .agents/skills/shuorenhua in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lornshrimp/Lorn.NovelWriteSkills --skill shuorenhua -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shuorenhua, .gemini/skills/shuorenhua, .github/skills/shuorenhua and .opencode/skills/shuorenhua in your project.
SKILL.md names no scripts, command-line tools or credentials: Shuorenhua is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Shuorenhua is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 22k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Shuorenhua: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
lornshrimp (a GitHub user) maintains it in lornshrimp/Lorn.NovelWriteSkills, which has 232 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 4, 2026.
Source: lornshrimp/Lorn.NovelWriteSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.