← 返回 Skills 市场
tracevan

Wechat Feige Formatter

作者 TraceVan · GitHub ↗ · v2.3.5 · MIT-0
cross-platform ✓ 安全检测通过
245
总下载
1
收藏
1
当前安装
13
版本数
在 OpenClaw 中安装
/install wechat-feige-formatter
功能描述
公众号排版工具。用户提供任意格式的文章内容(草稿、纯文字、已有 Markdown 均可), AI 自动识别结构、添加排版标记,生成专业公众号 HTML。 Use when: 用户说"帮我排版"、"转成公众号格式"、"生成 HTML";用户上传文章内容或文件 NOT for: 纯文本渲染;用户只想预览已有 HTML
安全使用建议
This skill appears to be what it says: a Markdown/text → WeChat HTML formatter implemented in bundled Python scripts, with no external installs or credentials required. Before using it: 1) Review the bundled scripts (formatter.py and scripts/formatter.py) yourself — running them executes code on your machine. 2) Do not pass paths to sensitive system files (e.g., /etc, SSH keys, config directories); the skill accepts local file paths and will read files you point it at. 3) Test on non-sensitive sample content first (confirm output and image embedding behavior). 4) Note minor issues: there are duplicate/near-duplicate script files and small code inconsistencies in the repository, which likely indicate maintenance/quality issues (not malicious intent). If you need higher assurance, run the scripts in an isolated environment (sandbox or container) before use.
功能分析
Type: OpenClaw Skill Name: wechat-feige-formatter Version: 2.3.5 The 'wechat-feige-formatter' skill is a legitimate tool designed to convert Markdown content into styled HTML for WeChat Official Accounts. The bundle consists of a Python script (formatter.py) that uses only standard libraries to parse Markdown and generate HTML with embedded CSS and JavaScript for theme switching. The instructions in SKILL.md and the optimization rules in the references directory are strictly focused on content structure and visual formatting, with no evidence of prompt injection, data exfiltration, or malicious execution. The script's ability to read local image files and convert them to base64 is consistent with its stated purpose of creating portable HTML for easy copy-pasting into the WeChat editor.
能力评估
Purpose & Capability
Name/description, SKILL.md, README and the included Python scripts all align: they parse Markdown/text and generate styled HTML for WeChat. The requested inputs (uploaded .md/.txt, pasted text, or local file path) and the single runtime action (call scripts/formatter.py) are appropriate for a formatter skill.
Instruction Scope
SKILL.md explicitly instructs the agent to read the bundled references/排版优化规则.md (present) and to accept local file paths as input. Reading the bundled rules is fine; allowing arbitrary local file paths is necessary for formatting user files but also means the agent will open files on the host if given a path — advise users not to supply sensitive system paths. The workflow tells the agent to execute a local Python script (scripts/formatter.py) — expected but means code runs on the host.
Install Mechanism
No install spec; instruction-only plus bundled Python scripts. No downloads from external URLs, no package managers, and the code claims to use only the Python standard library. This is a low-install-risk design (but executing bundled code still runs on the host).
Credentials
The skill requests no environment variables, no credentials, and no special config paths. The only sensitive operation is reading files (including images to embed) that users explicitly provide; those are proportional to the formatter's function.
Persistence & Privilege
always is false and the skill does not request permanent/system-wide presence. It instructs running local Python scripts but does not declare modifying other skills or system configs. Autonomous invocation is allowed (platform default) but not combined with other red flags here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install wechat-feige-formatter
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /wechat-feige-formatter 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.3.5
wechat-feige-formatter 2.3.5 - BREAKING 开篇语法调整:自动生成的 BREAKING 框只取主标题,避免与正文重复。如需自定义,需用列表写法,字段有说明,避免误判为正文。 - 新增/修改参数说明:--brand-color 现默认桃色,示例更新,同时新增 --no-embed-images 关闭图片 base64 内嵌,并明确默认嵌图行为。 - 明确 HTML 默认特性:页面内置主题色切换,支持一键复制,多配色预览等。 - 文档规范细化:「每个 BREAKING 字段须用 - 开头」等规则写法强调,避免格式错误。 - 其它细节描述补充和更新,部分概述更清晰易懂。
v2.3.4
- 新增 formatter.py 文件,作为核心排版转换脚本 - 更新 clawhub.toml 配置文件,适应功能扩展 - 无需手动添加排版标记,支持多种输入内容自动结构化 - 详细列出 7 项智能格式识别及核心语法规范 - 明确标准 Markdown->HTML 转换流程,支持品牌色定制 - 允许本地服务预览,优化用户操作说明
v2.3.3
- 明确要求排版处理时不新增原文没有的内容,禁止自动插入章节概述句,如“本节xxx”。 - 在排版规则步骤中新增“只对原文做格式标记”,强调内容不被擅自扩充。 - 文档其余部分维持原有结构与说明,提升规范性和清晰度。
v2.3.2
wechat-feige-formatter 2.3.2 - 更新 references/排版优化规则.md,优化排版规范内容。 - clawhub.toml 文件调整,完善依赖和配置。 - 语义和文档描述更准确,流程与用法无功能性变更。
v2.3.1
wechat-feige-formatter 2.3.1 - 更新了核心排版规范,强调需严格按 references/排版优化规则.md 执行全部 7 项识别任务(新增小标题与格式修正识别要求)。 - 简化了章节标题语法说明,明确 formatter 会自动将 ## 标题编号为 PART 章节。 - 强化格式规范,明确特殊框内部禁止空行,每行必须以 > 开头。 - 调整排版元素速查表,更详细区分各类卡片与标记的 formatter 语法与适用场景。 - 对 BREAKING 开篇处理方式做了说明,支持自动与手动两种生成方式。
v2.3.0
- 更新 clawhub.toml 配置和 scripts/formatter.py 脚本,提升稳定性与兼容性 - 增强 Markdown 到 HTML 的转换逻辑,优化排版效果 - 保持核心排版规则及用户交互方式不变
v2.2.0
wechat-feige-formatter 2.2.0 重大升级:支持全自动智能排版,无需用户手动标记。 - AI 现可接受纯文本、草稿、无标记 Markdown,自动识别结构并添加全部公众号排版标记 - 工作流调整:用户不需再手动编辑 Markdown 标记,AI 全程负责格式梳理与优化 - 增强特殊框(STEP/✨/💡/PROMPT)语法规范,内容生成更加标准和美观 - 支持直接粘贴、上传多种格式(.md/.txt/文本),显著减少操作门槛 - formatter.py 脚本调用方式及品牌色自定义参数完善说明
v2.1.0
wechat-feige-formatter 2.1.0 - 增加对 Python 3.6+ 低版本的兼容性说明,指导用户在遇到 glibc 问题时切换 Python 版本 - 修改命令行为 python3 scripts/formatter.py,强调无需第三方依赖,仅用标准库 - 文档细化,明确 glibc 兼容性解决方法和 Python 版本切换用法 - 其他用法、工作流与转化规则保持不变
v2.0.2
**Summary:** Major scope adjustment—removed AI内容智能优化,改为仅处理带标记Markdown。 - 仅支持“带排版标记”的 Markdown 转换为公众号 HTML,移除自动识别、AI 内容优化功能 - 明确要求用户手动添加排版标记(如 ==高亮==、> STEP、> ✨ 等) - 工作流简化:输入→校验排版标记→脚本转换→输出 HTML - 更新使用说明和用户提醒,避免误用无标记/普通 Markdown 文件 - 保持格式转换、品牌色自定义等核心功能不变
v2.0.1
- 增加了明确的用户文件输入流程,要求用户必须上传或指定 Markdown 文件路径;如未提供,直接提示用户上传。 - 强调仅处理用户提供的文档,禁止读取本地 Skill 目录下的文件。 - 明确了各步骤的文件流转,细化输入、优化、转换、输出的顺序和内容来源。 - 输出结果更明确:最终 HTML 直接返回用户,可复制到公众号编辑器或保存。
v2.0.0
wechat-feige-formatter v2.0.0 introduces AI-powered content optimization and refactors the workflow for more intelligent, automated public account formatting. - Adds AI-driven Markdown optimization based on new "排版优化规则",including automatic recognition of steps, keywords, summaries, and prompts. - Replaces the original formatter with a new modular script in scripts/formatter.py. - Simplifies and updates documentation (README.md, SKILL.md) for the new workflow and usage scenarios. - Removes redundant guides, checklists, and legacy code files for a cleaner project structure. - Adds a reference rulebook (references/排版优化规则.md) for content optimization standards.
v1.0.1
- Initial example files added: _meta.json, article.html, and article.md - Provides sample content and structure for quick testing or demonstration of the formatter's output - No changes to core features or formatting logic
v1.0.0
wechat-feige-formatter 1.0.0 - Initial release of the skill. - Converts Markdown articles into Feige-style WeChat-compatible HTML with one click. - Features custom Feige theme: peach color (#DE7356), rounded arcs, gradient backgrounds, and inline styles to avoid WeChat filtering issues. - Supports structured elements: Breaking titles, Part sections, Step cards, warnings, technical/info alerts, and code blocks. - Allows parameter-based customization for colors, component visibility, and advanced formatting. - Easy copy-paste output to WeChat Official Account editor; mobile responsive design.
元数据
Slug wechat-feige-formatter
版本 2.3.5
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 13
常见问题

Wechat Feige Formatter 是什么?

公众号排版工具。用户提供任意格式的文章内容(草稿、纯文字、已有 Markdown 均可), AI 自动识别结构、添加排版标记,生成专业公众号 HTML。 Use when: 用户说"帮我排版"、"转成公众号格式"、"生成 HTML";用户上传文章内容或文件 NOT for: 纯文本渲染;用户只想预览已有 HTML. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 245 次。

如何安装 Wechat Feige Formatter?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install wechat-feige-formatter」即可一键安装,无需额外配置。

Wechat Feige Formatter 是免费的吗?

是的,Wechat Feige Formatter 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Wechat Feige Formatter 支持哪些平台?

Wechat Feige Formatter 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Wechat Feige Formatter?

由 TraceVan(@tracevan)开发并维护,当前版本 v2.3.5。

💬 留言讨论