#348 by GitHub stars
imraywang/wewrite
公众号内容全流程 Skill,从热点抓取到微信草稿箱,一句话跑完整条内容管道
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/wewrite/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-learn/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-publish/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-rewrite/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-stats/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-style/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-topic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-visual/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
skills/wewrite-write/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2860fbe95831 → 8a5cdabd303c
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2860fbe95831
No earlier version was observed for comparison.
Verified commit 8a5cdabd303c147f174c9597dd334a1c3d3b50bd
git clone --filter=blob:none --no-checkout https://github.com/imraywang/wewrite.git .hotskills/imraywang-wewrite && git -C .hotskills/imraywang-wewrite checkout --detach 8a5cdabd303c147f174c9597dd334a1c3d3b50bd
# Copy each selected skill directory from .hotskills/imraywang-wewrite into .claude/skills/<skill-name>/Heat
7.1- Star growth, last 7 daysAhead of 93% of tracked repositories
- Star growth, last 24 hoursAhead of 92% of tracked repositories
- Rank movement, last 7 daysAhead of 55% of tracked repositories
- Commits, last 30 daysAhead of 67% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- wewrite
skills/wewrite - wewrite-learn
skills/wewrite-learn - wewrite-publish
skills/wewrite-publish - wewrite-review
skills/wewrite-review - wewrite-rewrite
skills/wewrite-rewrite - wewrite-stats
skills/wewrite-stats - wewrite-style
skills/wewrite-style - wewrite-topic
skills/wewrite-topic - wewrite-visual
skills/wewrite-visual - wewrite-write
skills/wewrite-write
How it works
wewrite
When your agent uses it
微信公众号内容主入口:完成选题、素材、写作和审稿,并按用户要求独立追加配图、排版或草稿箱发布。 也负责把风格设置、学习修改、数据复盘和多平台改写分发给对应 wewrite-* 模块。 触发关键词:公众号、微信文章、微信推文、草稿箱、微信排版、写公众号、写一篇。 通用文章、博客、邮件、短视频和网站 SEO 不触发。
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
1,573 tokensWhen the skill is activated
Reference documents
19,648 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行原则
- 路由
- 内容流程
- 可选后续动作
- 失败与恢复
Files
../../.claude-plugin/plugin.jsonasset589 bytes../wewrite-learn/SKILL.mddoc2,490 bytes../wewrite-learn/references/learn-edits.mddoc2,375 bytes../wewrite-publish/SKILL.mddoc2,646 bytes../wewrite-publish/references/wechat-constraints.mddoc11,694 bytes../wewrite-review/SKILL.mddoc3,992 bytes../wewrite-review/references/seo-rules.mddoc1,039 bytes../wewrite-rewrite/SKILL.mddoc2,791 bytes../wewrite-rewrite/platforms/douyin.yamlasset742 bytes../wewrite-rewrite/platforms/xiaohongshu.yamlasset756 bytes../wewrite-rewrite/references/multiplatform-rewrite.mddoc1,546 bytes../wewrite-stats/SKILL.mddoc1,928 bytes../wewrite-stats/references/effect-review.mddoc621 bytes../wewrite-style/SKILL.mddoc1,950 bytes../wewrite-style/references/onboard.mddoc4,309 bytes../wewrite-style/references/style-template.mddoc2,179 bytes../wewrite-style/style.example.yamlasset1,321 bytes../wewrite-topic/SKILL.mddoc3,911 bytes../wewrite-topic/references/topic-selection.mddoc7,531 bytes../wewrite-visual/SKILL.mddoc2,662 bytes../wewrite-visual/references/visual-guide.mddoc777 bytes../wewrite-write/SKILL.mddoc5,212 bytes../wewrite-write/personas/cold-analyst.yamlasset2,388 bytes../wewrite-write/personas/humor-storyteller.yamlasset2,668 bytes../wewrite-write/personas/industry-observer.yamlasset2,216 bytes../wewrite-write/personas/midnight-friend.yamlasset2,583 bytes../wewrite-write/personas/sharp-journalist.yamlasset1,930 bytes../wewrite-write/personas/tech-coder.yamlasset2,620 bytes../wewrite-write/personas/warm-editor.yamlasset2,371 bytes../wewrite-write/references/article-brief.mddoc2,383 bytes../wewrite-write/references/content-enhance.mddoc2,127 bytes../wewrite-write/references/editorial-quality.mddoc1,709 bytes../wewrite-write/references/frameworks-quick.mddoc782 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesSKILL.mdcore5,815 bytesreferences/pipeline-state.mddoc2,663 bytes
Read SKILL.md
# WeWrite — 公众号内容主入口
## 运行原则
- 默认连续完成内容流程,不在每一步停下来。用户说“交互模式”时,才在选题和框架处确认。
- 每篇文章必须用独立任务目录,不能覆盖另一篇文章。
- “写一篇”默认只交付审过的本地稿;生成图片和发布都不是默认动作。
- 配图、排版和发布是正文完成后的独立动作;不得为了排版或发布自动触发生图。
- “完整制作”是正文、配图和本地预览的组合快捷方式;只有明确说“推到草稿箱/发布”才允许调用发布命令。
- 搜索失败时可以继续写分析和经验判断,但不得把模型记忆包装成已核实的事实。
`{home}` 是 `wewrite home` 返回的状态目录。`{skill_dir}` 是本 skill 目录。确定性操作走 `wewrite` 命令。
## 路由View the complete source on GitHubwewrite-learn
When your agent uses it
WeWrite 自学习模块:从用户的人工修改中学习写作偏好(playbook 飞轮)、导入范文建风格库、 从公众号文章学习排版主题。 触发关键词:学习我的修改、我改了学习一下、导入范文、学习这篇文章、查看范文库、 学习排版、学排版。 不应被通用的"学习"、"总结这篇文章"触发——需要公众号/WeWrite 上下文。
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
691 tokensWhen the skill is activated
Reference documents
610 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行约定
- 子功能分发
Scripts executed separately
../../install.sh../../install.sh
Files
../../install.shruns4,091 bytes../../install.shruns4,091 bytesSKILL.mdcore2,490 bytesreferences/learn-edits.mddoc2,375 bytes
Read SKILL.md
# wewrite-learn — 自学习(改稿飞轮 / 范文库 / 排版学习)
## 运行约定
- **CLI**:确定性操作走 `wewrite` 命令(需在 PATH;缺失则引导 `uv tool install wewrite`,或在仓库里 `bash install.sh`)。
- **{home}**:用户状态目录 = `$WEWRITE_HOME` 或 `~/.wewrite`(`wewrite home` 可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。
- **`读取: <路径>`** = 用文件读取工具真实读完该文件再继续,不是注释。
- **references/**:本 skill 自带 `{skill_dir}/references/`;references 文档内的 `{skill_dir}` 即本 skill 目录。
## 子功能分发
| 用户说 | 动作 |
|--------|------|
| 学习我的修改 / 我改了,学习一下 | `读取: {skill_dir}/references/learn-edits.md`,按其流程执行。支持本地 markdown 修改与微信草稿箱同步(`wewrite learn-edits --from-wechat`) |View the complete source on GitHubwewrite-publish
When your agent uses it
WeWrite 排版发布模块:把 Markdown 做成微信预览,或在用户明确授权后推入公众号草稿箱; 也支持主题画廊和图片帖。只处理微信公众号。
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
693 tokensWhen the skill is activated
Reference documents
3,543 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 前置
- 预检
- 动作
- 辅助功能
Files
SKILL.mdcore2,646 bytesSKILL.mdcore2,646 bytesSKILL.mdcore2,646 bytesSKILL.mdcore2,646 bytesSKILL.mdcore2,646 bytesreferences/wechat-constraints.mddoc11,694 bytes
Read SKILL.md
# wewrite-publish — 排版、预览、草稿箱
## 前置
用户指定文章时使用该文件;否则 `wewrite run show`。如果
`artifacts.illustrated_article` 存在且非空就使用它,否则使用 `artifacts.article`;读取标题、
摘要、封面、预览路径、发布权限和降级标记。已完成文章可以直接排版或发布,不要恢复写作
任务。主题取 style.yaml 的 `theme`,默认 `professional-clean`。
排版和发布不得自动调用 `wewrite-visual`。没有封面时照常生成本地预览;只有用户另行要求
配图时才进入视觉模块。
用户本轮明确要求“推到草稿箱/发布”时,有任务先运行
`wewrite run permission publish allow`;用户撤回时运行 `wewrite run permission publish deny`。View the complete source on GitHubwewrite-review
When your agent uses it
WeWrite 编辑审稿模块:核对任务、事实来源、观点和实用性,必要时直接改稿,只有通过编辑门槛 才生成公众号成稿。也响应“检查这篇文章”。通用代码 review 和网站 SEO 不触发。
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,074 tokensWhen the skill is activated
Reference documents
1,358 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 前置
- 审稿与改稿
- 保存编辑报告
Files
SKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytesreferences/seo-rules.mddoc1,039 bytes../wewrite-write/references/article-brief.mddoc2,383 bytes../wewrite-write/references/editorial-quality.mddoc1,709 bytes
Read SKILL.md
# wewrite-review — 编辑、改稿与成稿
## 前置
用户指定文章时检查该文件;否则运行 `wewrite run show`,优先读取 `artifacts.draft`,并读取
`artifacts.brief`、`artifacts.claims` 和 `artifacts.sources`。旧任务没有初稿产物时才回退
`artifacts.article`。管道内先运行 `wewrite run step review in_progress`。
完整读取:
```text
读取: {skill_dir}/../wewrite-write/references/article-brief.md
读取: {skill_dir}/../wewrite-write/references/editorial-quality.md
读取: {skill_dir}/references/seo-rules.mdView the complete source on GitHubwewrite-rewrite
When your agent uses it
WeWrite 多平台改写模块:把一篇公众号文章(或指定源稿)内容级真改写成其他平台版本, 当前支持小红书(图文笔记)、抖音(口播脚本),检查编辑质量与源稿相似度。 触发关键词:改写成小红书、小红书版、抖音版、口播稿、多平台分发、一稿多发、平台改写。 不应被"翻译"、"缩写"、"换个标题"触发——那些是单平台编辑动作。
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
790 tokensWhen the skill is activated
Reference documents
442 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行约定
- 前置
- 执行
- 完成
Scripts executed separately
../../install.sh../../install.sh
Files
../../install.shruns4,091 bytes../../install.shruns4,091 bytesSKILL.mdcore2,791 bytesplatforms/douyin.yamlasset742 bytesplatforms/xiaohongshu.yamlasset756 bytesreferences/multiplatform-rewrite.mddoc1,546 bytes
Read SKILL.md
# wewrite-rewrite — 一源多平台改写
## 运行约定
- **CLI**:确定性操作走 `wewrite` 命令(需在 PATH;缺失则引导 `uv tool install wewrite`,或在仓库里 `bash install.sh`)。
- **{home}**:用户状态目录 = `$WEWRITE_HOME` 或 `~/.wewrite`(`wewrite home` 可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。
- **`读取: <路径>`** = 用文件读取工具真实读完该文件再继续,不是注释。
- **references/**:本 skill 自带 `{skill_dir}/references/`;references 文档内的 `{skill_dir}` 即本 skill 目录。
- **任务状态**:用 `wewrite run show` 读取当前任务。
## 前置
1. **源文章**:按优先级解析——用户指定的文件/粘贴内容 > 当前任务的
`artifacts.article`。都没有 → 问用户"要改写哪篇?给我文件路径View the complete source on GitHubwewrite-stats
When your agent uses it
WeWrite 数据复盘模块:拉取微信公众号文章的阅读/分享/点赞数据,回填历史记录并给出 选题、标题、框架的调整建议。 触发关键词:看看文章数据、文章数据怎么样、效果复盘、看看表现、阅读量怎么样。 需要公众号/WeWrite 上下文;不应被通用的"数据分析"触发。
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
526 tokensWhen the skill is activated
Reference documents
172 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行约定
- 执行
Scripts executed separately
../../install.sh../../install.sh
Files
../../install.shruns4,091 bytes../../install.shruns4,091 bytesSKILL.mdcore1,928 bytesreferences/effect-review.mddoc621 bytes
Read SKILL.md
# wewrite-stats — 文章数据复盘
## 运行约定
- **CLI**:确定性操作走 `wewrite` 命令(需在 PATH;缺失则引导 `uv tool install wewrite`,或在仓库里 `bash install.sh`)。
- **{home}**:用户状态目录 = `$WEWRITE_HOME` 或 `~/.wewrite`(`wewrite home` 可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。
- **`读取: <路径>`** = 用文件读取工具真实读完该文件再继续,不是注释。
- **references/**:本 skill 自带 `{skill_dir}/references/`;references 文档内的 `{skill_dir}` 即本 skill 目录。
## 执行
```
读取: {skill_dir}/references/effect-review.md
```View the complete source on GitHubwewrite-style
When your agent uses it
WeWrite 风格设置模块:首次使用引导(onboard)+ 重设公众号写作风格配置(style.yaml)。 触发关键词:重新设置风格、修改风格配置、设置公众号风格、公众号首次设置、换写作人格、 改排版主题偏好。也由主入口 wewrite 在缺 style.yaml 时自动激活。 不应被通用的"改文风"、"润色"触发——那是编辑动作,不是配置动作。
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
544 tokensWhen the skill is activated
Reference documents
1,924 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行约定
- 执行
Scripts executed separately
../../install.sh../../install.sh
Files
../../install.shruns4,091 bytes../../install.shruns4,091 bytesSKILL.mdcore1,950 bytesreferences/onboard.mddoc4,309 bytesreferences/style-template.mddoc2,179 bytesstyle.example.yamlasset1,321 bytes
Read SKILL.md
# wewrite-style — 风格设置 / Onboard
## 运行约定
- **CLI**:确定性操作走 `wewrite` 命令(需在 PATH;缺失则引导 `uv tool install wewrite`,或在仓库里 `bash install.sh`)。
- **{home}**:用户状态目录 = `$WEWRITE_HOME` 或 `~/.wewrite`(`wewrite home` 可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。
- **`读取: <路径>`** = 用文件读取工具真实读完该文件再继续,不是注释。
- **references/**:本 skill 自带 `{skill_dir}/references/`;references 文档内的 `{skill_dir}` 即本 skill 目录。
- 本模块是**交互式**的(需要问用户问题),不受主管道"全自动"约束。
## 执行
**触发场景**:
1. 主入口 Step 1 发现 `{home}/style.yaml` 不存在(首次使用)View the complete source on GitHubwewrite-topic
When your agent uses it
WeWrite 选题模块:抓取全网热点 + 垂类高频需求 + 历史表现分析 + 搜索需求,为公众号 生成 10 个评分排序的选题(含高频角度与常青选题)。 触发关键词:公众号选题、找几个选题、今天写什么、热点选题、热搜选题、爆款选题、选题建议。 需要公众号/微信上下文;不应被抖音/短视频/网站的选题需求触发。
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
1,138 tokensWhen the skill is activated
Reference documents
2,249 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 运行约定
- 前置
- 2.1 热点抓取
- 2.1b 高频需求参考
- 2.2 历史分析 + SEO
- 2.3 生成选题
- 完成
Scripts executed separately
../../install.sh../../install.sh
Files
../../install.shruns4,091 bytes../../install.shruns4,091 bytesSKILL.mdcore3,911 bytesSKILL.mdcore3,911 bytesSKILL.mdcore3,911 bytesSKILL.mdcore3,911 bytesreferences/topic-selection.mddoc7,531 bytes
Read SKILL.md
# wewrite-topic — 选题
## 运行约定
- **CLI**:确定性操作走 `wewrite` 命令(需在 PATH;缺失则引导 `uv tool install wewrite`,或在仓库里 `bash install.sh`)。
- **{home}**:用户状态目录 = `$WEWRITE_HOME` 或 `~/.wewrite`(`wewrite home` 可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。
- **`读取: <路径>`** = 用文件读取工具真实读完该文件再继续,不是注释。
- **references/**:本 skill 自带 `{skill_dir}/references/`;references 文档内的 `{skill_dir}` 即本 skill 目录。
- **任务状态**:通过 `wewrite run show/update/step` 读取和更新;不直接改状态文件。
## 前置
- `{home}/style.yaml` 存在 → 提取 `topics`、`content_style`。不存在 → 问用户"你的
公众号主要写哪几个方向?"用回答临时代替 topics,并提示可用 **wewrite-style** 完成完整设置。View the complete source on GitHubwewrite-visual
When your agent uses it
WeWrite 视觉模块:为公众号文章生成封面和必要的内文配图,或只交付提示词。触发词: 封面图、公众号配图、给文章配图、换封面。通用绘图和 logo 设计不触发。
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
736 tokensWhen the skill is activated
Reference documents
222 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 前置
- 执行
Files
SKILL.mdcore2,662 bytesSKILL.mdcore2,662 bytesSKILL.mdcore2,662 bytesreferences/visual-guide.mddoc777 bytes
Read SKILL.md
# wewrite-visual — 封面与配图
## 前置
用户指定文章时使用该文件;否则 `wewrite run show`,读取当前任务的 `artifacts.article`、
`artifacts.illustrated_article`、`artifacts.image_prompts`、`artifacts.images_manifest`、
`visual`、`flags` 和任务目录。已完成的文章也可以直接配图,不要恢复或新建写作任务。
有任务时运行 `wewrite run step visual in_progress`。用户直接给了任务外文章时独立执行,
不写任务状态;提示词和图片放进文章同目录的 `<文件名>-assets/`,带图副本写成
`<文件名>-illustrated.md`。
根据本轮原话确定模式并用 `wewrite run update` 记录:只要封面用 `cover`,封面和必要内文图
用 `full`,只要提示词用 `prompts`。不要沿用写作模式猜测用户想生图。`prompts` 或View the complete source on GitHubwewrite-write
When your agent uses it
WeWrite 写作模块:在公众号选题明确后完成文章任务书、主张与证据、素材和初稿。由主流程调用, 或响应“就这个选题写正文”。通用写作、博客和短视频文案不触发。
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,395 tokensWhen the skill is activated
Reference documents
1,907 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 前置
- 3. 文章任务与素材
- 4. 写初稿
Files
SKILL.mdcore5,212 bytesSKILL.mdcore5,212 bytesSKILL.mdcore5,212 bytespersonas/cold-analyst.yamlasset2,388 bytespersonas/humor-storyteller.yamlasset2,668 bytespersonas/industry-observer.yamlasset2,216 bytespersonas/midnight-friend.yamlasset2,583 bytespersonas/sharp-journalist.yamlasset1,930 bytespersonas/tech-coder.yamlasset2,620 bytespersonas/warm-editor.yamlasset2,371 bytesreferences/article-brief.mddoc2,383 bytesreferences/content-enhance.mddoc2,127 bytesreferences/editorial-quality.mddoc1,709 bytesreferences/frameworks-quick.mddoc782 bytes
Read SKILL.md
# wewrite-write — 任务书、证据与初稿
## 前置
运行 `wewrite run show` 读取当前任务。没有任务但用户给了选题时,以 `draft` 模式创建;没有
选题则转 `wewrite-topic`。本模块只写 `artifacts.brief`、`artifacts.claims` 和
`artifacts.draft`;`artifacts.article` 由审稿模块在通过后生成。
读取 `{home}/style.yaml`;不存在则先执行 `wewrite-style`。按优先级读取自定义人格
`{home}/personas/<name>.yaml`、内置 `personas/<name>.yaml`,最后回退 `midnight-friend`。
人格只控制表达偏好,不能覆盖事实、个人材料和文章任务书。
进入时运行 `wewrite run step write in_progress`。
View the complete source on GitHubSkills included
- wewrite
- wewrite-learn
- wewrite-publish
- wewrite-review
- wewrite-rewrite
- wewrite-stats
- wewrite-style
- wewrite-topic
- wewrite-visual
- wewrite-write
Repository facts
- License
- MIT
- Created
- Mar 26, 2026
- Last pushed
- Nov 2, 2026
- Forks
- 575
- Open issues
- 3
- Project activity
- Active
Rank over the last 12 weeks
Now #348 · best #272 · down 44 in 30 days
- #340 on Oct 29
- #343 on Oct 30
- #345 from Oct 31 to Nov 2
- #348 on Nov 3
- #347 from Nov 4 to Nov 5
- #348 since Nov 6
76 earlier periods
- #268 on Aug 2
- #270 on Aug 7
- #272 on Aug 8
- #268 on Aug 9
- #277 on Aug 10
- #272 on Aug 11
- #273 on Aug 12
- #277 on Aug 13
- #275 on Aug 14
- #272 on Aug 15
- #277 on Aug 16
- #275 on Aug 17
- #283 on Aug 18
- #281 on Aug 19
- #280 on Aug 20
- #281 on Aug 21
- #275 on Aug 22
- #282 on Aug 23
- #283 on Aug 24
- #285 on Aug 25
- #284 on Aug 26
- #282 on Aug 27
- #284 on Aug 28
- #283 on Aug 29
- #278 on Aug 30
- #285 on Aug 31
- #286 on Sep 1
- #285 on Sep 2
- #289 on Sep 3
- #283 on Sep 4
- #282 on Sep 5
- #283 on Sep 6
- #288 from Sep 7 to Sep 10
- #286 on Sep 11
- #290 on Sep 12
- #292 on Sep 13
- #296 on Sep 14
- #297 on Sep 15
- #295 on Sep 16
- #294 on Sep 17
- #296 on Sep 18
- #290 on Sep 19
- #297 on Sep 20
- #296 on Sep 21
- #300 from Sep 22 to Sep 23
- #298 on Sep 24
- #296 on Sep 25
- #292 on Sep 26
- #298 on Sep 27
- #302 on Sep 28
- #301 on Sep 29
- #299 on Sep 30
- #298 on Oct 1
- #302 on Oct 2
- #296 on Oct 3
- #295 on Oct 4
- #304 on Oct 5
- #303 on Oct 6
- #304 on Oct 7
- #306 on Oct 8
- #309 on Oct 9
- #302 on Oct 10
- #307 on Oct 11
- #314 on Oct 12
- #312 on Oct 13
- #315 on Oct 14
- #313 on Oct 15
- #316 from Oct 16 to Oct 18
- #320 on Oct 19
- #322 on Oct 20
- #324 on Oct 21
- #326 on Oct 22
- #325 on Oct 23
- #322 on Oct 24
- #330 on Oct 25
- #334 on Oct 28
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 23 notes
skills/wewrite/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinstall.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinstall.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedinstall.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedinstall.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedinstall.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-topic/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-topic/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-topic/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/wewrite-visual/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 19 broad permissionsin 10 files: skills/wewrite-learn/SKILL.md:1 skills/wewrite-publish/SKILL.md:1 skills/wewrite-review/SKILL.md:1 and 7 more
- 5 dangerous shell commandsin 1 file: install.sh:71
- 20 network referencesin 1 file: skills/wewrite-publish/references/wechat-constraints.md:96
- No hidden or obfuscated text
- No instruction overrides
- 10 executable scriptsin 1 file: install.sh:1
- No access to secrets
- No requests to vote in Hot
Show all 54 signals by file
install.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Dangerous shell operationline 71
echo "⚠ 跳过 $SKILLS_TARGET:它是指回本仓库的符号链接,请先 rm 掉再重跑" >&2 - Dangerous shell operationline 71
echo "⚠ 跳过 $SKILLS_TARGET:它是指回本仓库的符号链接,请先 rm 掉再重跑" >&2 - Dangerous shell operationline 71
echo "⚠ 跳过 $SKILLS_TARGET:它是指回本仓库的符号链接,请先 rm 掉再重跑" >&2 - Dangerous shell operationline 71
echo "⚠ 跳过 $SKILLS_TARGET:它是指回本仓库的符号链接,请先 rm 掉再重跑" >&2 - Dangerous shell operationline 71
echo "⚠ 跳过 $SKILLS_TARGET:它是指回本仓库的符号链接,请先 rm 掉再重跑" >&2
skills/wewrite-publish/references/wechat-constraints.md
- Network accessline 96
<!-- ✅ 需要用户手动处理 --> <img src="https://imagebed.com/cover.png"> - Network accessline 96
<!-- ✅ 需要用户手动处理 --> <img src="https://imagebed.com/cover.png"> - Network accessline 97
<img src="https://imagebed.com/cover.png"> - Network accessline 97
<img src="https://imagebed.com/cover.png"> - Network accessline 209
<!-- 链接会保留,但需要微信审核 --> <a href="https://www.example.com" style="color: #7c3aed;">链接文本</a> - Network accessline 209
<!-- 链接会保留,但需要微信审核 --> <a href="https://www.example.com" style="color: #7c3aed;">链接文本</a> - Network accessline 210
<a href="https://www.example.com" style="color: #7c3aed;">链接文本</a> - Network accessline 210
<a href="https://www.example.com" style="color: #7c3aed;">链接文本</a> - Network accessline 212
<!-- 建议:显示完整URL --> 官方网站:https://www.example.com - Network accessline 212
<!-- 建议:显示完整URL --> 官方网站:https://www.example.com - Network accessline 213
官方网站:https://www.example.com - Network accessline 213
官方网站:https://www.example.com - Network accessline 214
GitHub仓库:https://github.com/user/repo - Network accessline 214
GitHub仓库:https://github.com/user/repo - Network accessline 433
### 官方文档 - [微信公众平台 - 帮助中心](https://kf.qq.com/product/weixinmp.html) - Network accessline 433
### 官方文档 - [微信公众平台 - 帮助中心](https://kf.qq.com/product/weixinmp.html) - Network accessline 434
- [微信公众平台 - 帮助中心](https://kf.qq.com/product/weixinmp.html) - Network accessline 434
- [微信公众平台 - 帮助中心](https://kf.qq.com/product/weixinmp.html) - Network accessline 435
- [微信公众号编辑器使用说明](https://mp.weixin.qq.com) - Network accessline 435
- [微信公众号编辑器使用说明](https://mp.weixin.qq.com)
skills/wewrite/SKILL.md
- Broad permissionsline 1
Bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 54 facts
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Executable script in code of a file that runsinstall.sh:1High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:71High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:71High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:71High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:71High confidence
- Dangerous shell operation in code of a file that runsinstall.sh:71High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-learn/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-learn/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-publish/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-publish/SKILL.md:1High confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:96Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:96Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:97Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:97Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:209Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:209Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:210Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:210Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:212Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:212Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:213Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:213Low confidence
- Network access in code of documentationskills/wewrite-publish/references/wechat-constraints.md:214Low confidence
- Network access in code of documentationwewrite-publish/references/wechat-constraints.md:214Low confidence
- Network access in prose of documentationskills/wewrite-publish/references/wechat-constraints.md:433Low confidence
- Network access in prose of documentationwewrite-publish/references/wechat-constraints.md:433Low confidence
- Network access in prose of documentationskills/wewrite-publish/references/wechat-constraints.md:434Low confidence
- Network access in prose of documentationwewrite-publish/references/wechat-constraints.md:434Low confidence
- Network access in prose of documentationskills/wewrite-publish/references/wechat-constraints.md:435Low confidence
- Network access in prose of documentationwewrite-publish/references/wechat-constraints.md:435Low confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-review/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-review/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-rewrite/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-rewrite/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-stats/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-stats/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-style/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-style/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-topic/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdwewrite-topic/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/wewrite-visual/SKILL.md:1High confidence
and 4 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/wewrite/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/wewrite/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/wewrite/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/wewrite/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/wewrite/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/imraywang-wewrite/)