
微信公众号运营助手
概览
Weaver is an open-source AgentWaker role for evidence-backed WeChat Official Account operations. It covers AI-signal research, editorial planning, deep technical tutorials, visual production, WeChat-compatible formatting, private review, approval-bound draft/publication actions, and performance review. - A complete AgentWaker role profile under agent-soul/ - English and Chinese role detail pages - Reusable skills for research, planning, drafting, visuals, formatting, JPage review, WeChat draft/publication, and performance analysis - Official WeChat API helpers and an optional SSH token broker - Local tests for renderers, collectors, visual packages, and API helpers Research and local rendering are read-only by default. Every external write, asset upload, draft mutation, preview send, public publication, mass delivery, or deletion requires explicit approval for the exact target and payload.
README
以下为原文 README 节选,完整内容请查看原文。
WeChat Official Account Operator
Weaver is an open-source AgentWaker role for evidence-backed WeChat Official Account operations. It covers AI-signal research, editorial planning, deep technical tutorials, visual production, WeChat-compatible formatting, private review, approval-bound draft/publication actions, and performance review.
What is included
- A complete AgentWaker role profile under
agent-soul/ - English and Chinese role detail pages
- Reusable skills for research, planning, drafting, visuals, formatting, JPage review, WeChat draft/publication, and performance analysis
- Official WeChat API helpers and an optional SSH token broker
- Local tests for renderers, collectors, visual packages, and API helpers
Safety model
Research and local rendering are read-only by default. Every external write, asset upload, draft mutation, preview send, public publication, mass delivery, or deletion requires explicit approval for the exact target and payload. Credentials, cookies, access tokens, unpublished material, and runtime output must stay outside Git.
Quick start
Requirements
| Scope | Requirement |
|---|---|
| Core role, lifecycle, and validation | Git, Ruby 2.6+, Python 3.9+ |
| JPage private preview | Node.js 20+, @code2rich/jpage, and an operator-owned token |
| Official WeChat API actions | An eligible account, required API permissions, credentials, and an approved IP allowlist or token broker |
| SSH token broker | Linux with systemd, OpenSSH, Python 3.9+, and curl |
| Browser draft fallback or generated visuals | A compatible agent runtime with an authorized browser or image-generation tool |
Standalone checkout
-
Clone this repository:
git clone https://github.com/code2rich/agentwaker-wechat-official-account-operator.git cd agentwaker-wechat-official-account-operator -
Copy
env/.env.exampletoenv/.envand fill only the integrations you intend to use. The real file is ignored by Git. -
Set absolute runtime paths from the repository root:
export AGENT_WORK_DIR="$PWD/workdir" export AGENT_MEMORY_FILE="$PWD/agent-soul/MEMORY.md" -
Start a tracked run:
ruby tools/agent-runtime.rb start \ --role . \ --goal "Draft an evidence-backed WeChat article" \ --tool codex -
Read
wechat-official-account-operator-skills/SKILL.mdto route a task to the appropriate specialist skill.
Install as an Agent Skill
The repository root contains SKILL.md, so a Skill-compatible client can use
the whole checkout without separating its runtime files:
git clone \
https://github.com/code2rich/agentwaker-wechat-official-account-operator.git \
~/.agents/skills/wechat-official-account-operator
If your client uses a different Skill directory, clone the repository there instead. Keep the entire repository together: specialist skills rely on the
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add code2rich/agentwaker-wechat-official-account-operator