Gracker Writing logo

Gracker Writing

Community
Gracker
gracker-writing

按 Gracker 的工程师口吻写作、审阅和润色技术文章,也用于恢复旧稿作者声音、检查社交稿的表达与 AI 味。

Overview

PublisherGracker
Repositorygracker-writing
Skill namegracker-writing
Stars
50
Forks
5
Bundled files
15
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 15 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Gracker on GitHub. Read the source before you install it.

Installation

Install the Gracker Writing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Gracker/gracker-writing/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Gracker/gracker-writing.git \
  .claude/skills/gracker-writing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gracker Writing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gracker Writing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gracker Writing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Gracker Writing

让读者看清问题、判断依据和作者的真实处境。保留工程师与同行交流的直接感,也容得下犹豫、失败、玩笑和生活。文风不能替代事实,规范也不能把作者抹掉。

先确定这次要做什么

优先服从用户给出的体裁、读者、材料和改动范围。信息足够就开始;只补问会改变文章方向或交付要求的问题。

请求工作方式按需读取
写新稿、扩写、重写根据材料组织论点与叙述,结构为内容服务作者声音、结构与表达
润色、精修、去 AI 味先确认原文含义,再修具体问题;不默认重构全文改稿范围、局部表达诊断
找回旧稿口吻、修复前序改写对照可信原稿,恢复有依据的损失,同时保留已确认的纠错作者声音、改稿范围
review、只给意见指出位置、问题和影响;没有改稿授权时不直接改正文质量复核
社交稿、调研转长文按读者目的选择材料与推进顺序,依体裁决定筛选、解释或保留清单社交表达、调研长文

不要为了执行本 skill 把每份 reference 都加载一遍。短文可能只需要主文件;需要细则时再读对应文件。

共同约束

  • 材料决定能说到哪。 区分来源事实、作者观察、推断和建议。不得补出不存在的测试、数字、人物、对话或经历;材料不足就收窄判断,或说明缺什么。
  • 编辑不改变事实强度。 保留否定、条件、范围、时间和不确定性;“可能有效”不能润色成“已经有效”。技术纠错与文风修改分别判断。
  • 作者仍是说话的人。 原有的第一人称、提问、自嘲、感叹和旁白按作用取舍,不因命中词库删除。新稿不能靠编造经历或反复加“我认为”冒充作者。
  • 改动有具体理由。 歧义、重复、断裂、误译或无依据的拔高都可修;仅仅“不够整齐”“像能翻回英文”或某个词出现多次,不足以判错。
  • 保留可识别内容。 术语、代码、引用、数据和链接不能为了语言顺滑失真。机器可读内容的检查见基础校对。

写新稿

先用一句话理清:读者带着什么问题来,文章准备回答什么,手头有什么材料。这是组织思路,不要求在正文里按固定句式交代。

根据材料选择展开方式。排查复盘可以跟着观察和判断走;教程按操作依赖走;概念解释先给读者需要的整体关系;观点文说明理由,必要时讨论反例;个人记录可以从一个场景或感受开始。不要要求所有文章三句开题、固定章节数或每段都有数据。

进入技术判断时,给出足以复查的依据。涉及会变的事实,核对适用版本与时间;来源只能支持推测时,不写成定论。写作授权不等于已经在作者的环境中验证过。

正文解释到位就收束。可给结论、尚未解决的问题、下一步或延伸阅读;不必统一成行动清单,也不必额外升华。

改稿与恢复

读完当前稿再动手。纯精修保留核心观点、体裁和叙述顺序;必要的拆句、衔接和错字修复不受某份句式清单限制。大幅删节、重排或新增论证应有用户授权或明确任务依据。

恢复原稿时,先确认版本关系。区分被删的作者表达、已修正的事实和后加的说明。能恢复经历而保留纠错,就同时保留;找不到旧稿依据,不补写“作者可能会这么说”的故事。

译文也要保留观点归属、情绪分寸和具体细节。可以换成目标语言自然的说法,不把原文压成摘要,也不把口头玩笑逐字译成怪话。

按材料选择展示方式

  • 代码有助于理解时才放;交代用途、关键位置及运行条件。完整示例、节选和伪代码应能区分,省略不能伪装成可直接执行。
  • 数值比较说明对象、单位、口径和影响判断的条件。质性比较可以用具体差异说明,不为了满足格式编出两组数字。
  • 表格适合横向比较,列表适合并列项或步骤,图适合关系和变化。图的抽象层级由读者任务决定,省略关键因果关系时要说明。
  • 工具和语法按目标平台实际能力选择,不假定某种图表围栏到处可渲染。

交付前复核

完整文章、长帖和调研稿的文风验收,先读取整稿审查,通读全文,检查段落作用、结论推进、情绪与内容的关系,以及条件是否在收尾时丢失,再做局部检查。单句分别成立不能作为整稿通过的依据。只处理指定句段、错字或排版时,遵守本次范围。

回读正文与本次改动:含义是否漂移,因果是否成立,段落是否顺,作者是否还在。按任务修复成立的问题;没有问题的句子保留。完整检查维度见质量复核,无需每次附上打分表。

报告时区分文风是否仍需修改、事实核查是否完成。只做了局部精修或缺少原始材料,不笼统宣布整稿通过。

用户要成稿,就交成稿;要审查,就交具体发现;要修改文件,就报告修改与验证结果。正文和编辑说明分开。发布、投递、定时任务行为和文件落点由当前任务决定,本 skill 不规定渠道或自动执行外部操作。

条件性参考

  • 词组与改写案例:检查黑话、套话和生硬表达时,查常见词组、改前改后与应保留的语境。
  • 自然表达:判断具体感、作者反应和叙述节奏是否被磨平。
  • 基础校对:含义、术语、数字、错字与机器可读边界。
  • 文档组织:说明性长文的标题、段落和交叉引用。
  • 中文排版:空格、标点、大小写;沿用用户或项目约定。
  • Android 术语:仅在相应领域使用,不是所有技术写作的默认模型。

规则放在哪里

通用方法解决跨题材的写作问题;作者偏好描述 Gracker 的口吻;领域附录处理特定术语;项目和渠道约定留在项目文档或调用任务中。临时要求不自动成为长期规则。

从一次失败中提炼规则时,先说明它解决什么问题、何时不适用、是否已有同类规则。保留能解释判断的词组、改写对照和原稿片段,注明材料前提与适用边界;不要只留下抽象原则。案例不能成为必须复现的内容、语气或结构,排查词表也不能变成自动禁词表。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gracker Writing AI skill do?

按 Gracker 的工程师口吻写作、审阅和润色技术文章,也用于恢复旧稿作者声音、检查社交稿的表达与 AI 味。

Why use Gracker Writing on TypingMind?

Because you install it once and use it with any model. Gracker Writing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gracker Writing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Gracker/gracker-writing/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gracker Writing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gracker Writing?

As many as you like. As long as a model supports skills, you can use Gracker Writing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gracker Writing AI skill free?

Yes. It is published on GitHub by Gracker under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇