Vertrauen 46/100mittel Risiko1 Skills

Package

zhayujie/chatgpt-on-wechat

CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长。同时支持飞书、钉钉、企业微信应用、微信公众号、网页等接入,可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助手和企业数字员工。

Trust means

Trust score is a heuristic blend of popularity, freshness, structure quality, and safety penalties. Useful for ranking, not a guarantee.

Risk means

Risk is generated by automated scans of skills, files, and allowed tools. It is not the same thing as a human security review.

Review status

Auto-scanned only. Some caution signals were detected, so treat this as a review queue item, not a safe default.

Risiko: mittel (auto-imported from GitHub; risk not assessed)

Sterne

42.164

Forks

9.820

Skills

0

Dateien

0

Suitable for

Coding-agent users who want reusable development workflows instead of re-prompting Claude Code, Codex, Cursor, or similar tools every session.

Not suitable for

Not ideal if you only need a single command snippet or if your team disallows agent-driven code or shell actions.

Install prerequisites

What to verify before touching install

  • Confirm the package matches your editor, agent, and tool-permission model.
  • Review the first skill for repo assumptions, shell usage, and required context files.
  • Make sure developers know whether this package is guidance-only or action-oriented.

Recommended first read

Review the lowest-risk skill first

Start with the clearest, lowest-risk skill so you understand the package boundary before you install anything.

Pfad: Wurzel

After install

How to verify it actually works

Install it into a disposable or test repo first and run the starter workflow once.
Check whether the agent follows the expected structure, outputs, and guardrails.
Verify the package improves workflow clarity instead of just adding more prompt noise.

Core skills

What this package actually helps you do

Package contents

Folders and files

Last step

Install only after the checks above

If the package fits your workflow, the starter skill makes sense, and the auto-scan signals are acceptable for your environment, then use the exact install command below.

Install command

npx skills add zhayujie/chatgpt-on-wechat

Claude Code

Copy to .claude/skills/

GitHub Copilot

Copy to .github/skills/

Codex CLI

Copy to .agents/skills/

Gemini CLI

Copy to .gemini/skills/

Community Signals

What users think

🟡 Moderate

Ähnliche Packages

Similar packages worth comparing

Keine ähnlichen Packages gefunden.

zhayujie/chatgpt-on-wechat - Install Agent Skills