Token导航 LogoToken导航

Agent Skill · 研究检索

wechat-post-skill(微信发帖技巧)

wechat-post-skill 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

wechat-post-skill 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 37,725。

总安装 1,681周安装 68GitHub Stars 公开资料未说明下载 528核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.3

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:wechat-post-skill(微信发帖技巧)
来源仓库:https://github.com/jiao1yin2he3/wechat-post-skill
安装命令:
openclaw skills install wechat-post-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install wechat-post-skill

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

wechat-post-skill 提供公众号文章全流程辅助,涵盖选题、起草、编辑到发布审核。适用于 OpenClaw 中需要系统化完成微信内容创作的复杂任务。支持内容策划、风格调整和人工确认环节,确保输出质量。

安装命令为 openclaw skills install wechat-post-skill,需授权账号操作权限。注意内容合规审查,避免触发平台规则或版权风险。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install wechat-post-skill;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

wechat-post-skill 怎么安装?

在终端执行 openclaw skills install wechat-post-skill。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

wechat-post-skill 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

wechat-post-skill 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

wechat-post-skill 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

wechat-post-skill 用的人多吗?

公开数据是累计安装 1,681 次,近一周安装 68 次,下载 528 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

wechat-post-skill 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
wechat-post-skill

微信发帖技巧 · 本页

1,681—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
wechat-post-skill
homepage
https://github.com/jiao1yin2he3/wechat-post-skill
description
User-authorized WeChat Official Account article workflow for topic selection, drafting, editing, image planning, pre-publish review, and handoff to the user's configured WeChat publishing tool. Use when the user asks to 发公众号, 写公众号文章, 做公众号推送, or 发布草稿箱. Requires the user to provide and control any WeChat account access through environment variables or a vetted companion publisher.
metadata
openclaw
emoji
📰
homepage
https://github.com/jiao1yin2he3/wechat-post-skill
requires
env
anyBins
primaryEnv
WECHAT_APP_SECRET
companionSkills
notes

WeChat Post Skill

Use this skill to prepare a polished WeChat Official Account draft and hand it off to a user-authorized publishing tool. It is an orchestration workflow, not a credential manager and not a browser-control package.

Safety boundaries

  • Use only for the user's own WeChat Official Account or an account they are authorized to operate.
  • Do not ask the user to paste secrets into chat. Use environment variables or an agent-managed private config controlled by the user.
  • Do not store, print, commit, or publish AppSecret, tokens, cookies, browser profile data, or private account config.
  • Do not publish final content without explicit user direction; default target is the WeChat draft box unless instructed otherwise.
  • If API access is blocked by credentials, permissions, or IP allowlist settings, ask the user to fix account settings; do not bypass controls.
  • Browser-based publishing or image generation is out of scope for this skill. If needed, use a dedicated companion skill in an isolated, user-controlled browser profile.

Core workflow

  1. Pick topic

- If the user already gives a topic: use it directly. - If not: search current hot topics and offer 3 options. - Prefer topics with local relevance, clear public interest, conflict, usefulness, or share value.

  1. Write article

- Create an article folder under the project/workspace, e.g. articles/YYYY-MM-DD-short-title/. - Write article.md at roughly 900–1300 Chinese characters unless the user asks otherwise. - Include image placeholders in Markdown syntax only: ![](img0.png), ![](img1.png), etc. - Use a strong opening, varied paragraph rhythm, useful subheads, and a hard ending with a comment/share prompt.

  1. Humanize/self-edit

- Remove generic AI phrases, over-formal transitions, excessive bold, and excessive em dashes. - Keep the article concrete, local, useful, and conversational. - If an AI-humanizer skill/tool exists, use it for analysis and targeted revision.

  1. Prepare images

- Prepare or generate the article assets in the article folder: - cover.png — WeChat cover, 2.35:1 preferred. - img0.png … — body images, usually 16:9. - Use only image-generation tools explicitly available and authorized in the current environment. - For Gemini web UI image generation, use the separate gemini-browser-image companion skill rather than embedding browser instructions here.

  1. Self-review before draft handoff

- Verify image placeholders use ![](imgX.png). - Verify all referenced image files exist. - Verify no secrets, local-only credentials, cookies, or tokens are embedded in article.md. - Choose theme by topic: - tech/hard analysis: modern - finance/business/career: grace - emotion/life/soft topics: simple - controversy/hot news: default - unsure: grace

  1. Hand off to authorized publisher

- Use a vetted WeChat publishing companion tool when available, such as baoyu-post-to-wechat. - Confirm the required environment variables or private config already exist before running the publisher. - Do not print secret values. Only report whether required configuration is present or missing. - If publishing fails because of WeChat account settings, credentials, permissions, or IP allowlist, stop and ask the user to resolve those settings.

  1. Clean up

- Remove temporary generated-image downloads when safe. - Keep the article folder and source assets unless the user asks to delete them.

Quality bar

  • The article must have a clear traffic goal: clicks, saves, comments, shares, or follower growth.
  • The first 100–300 characters must create tension, curiosity, usefulness, or emotional resonance.
  • Every image must serve the article: cover for click-through, body images for pacing/comprehension.
  • Never hand off for publishing before self-review.

Optional references

  • references/content-playbook.md — article structure, title/opening/ending patterns.
  • references/publishing-notes.md — WeChat draft handoff checks and common failures.

平台分布

OpenClaw

87.19%
按下载量换算460

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills