# hellowind777

> Open-source publisher. Listings imported from github.com/hellowind777 — credited to the original author with their license.

- **Listings:** 3
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/hellowind777
- **Website:** https://github.com/hellowind777

## Published listings

- [Hello Auditkit](https://agentstack.voostack.com/l/skill-hellowind777-hello-auditkit-hello-auditkit) — Skill · Free · security-reviewed — `agentstack add skill-hellowind777-hello-auditkit-hello-auditkit`
  |
- [Hello Multimodal](https://agentstack.voostack.com/l/skill-hellowind777-hello-multimodal-hello-multimodal) — Skill · Free · security-reviewed — `agentstack add skill-hellowind777-hello-multimodal-hello-multimodal`
  此技能应在用户消息包含图片/截图/照片时使用——优先由主模型尝试处理图片，若主模型无法正常处理（报错/无法读取/无法识别/格式错误/内容块缺失等）则使用此技能进行视觉理解。此技能也应在用户要求生成图片/画图/配图时使用。
- [Hellomedia](https://agentstack.voostack.com/l/skill-hellowind777-hellomedia-hellomedia) — Skill · Free · security-reviewed — `agentstack add skill-hellowind777-hellomedia-hellomedia`
  默认假设宿主主模型不能看图/读视频/听音频。用户消息含图片/截图/照片/视频/音频（含剪贴板粘贴、路径），或要求视觉理解、生图/改图、生视频/改视频/延长（含 image_to_video / reference_to_video）、TTS/STT 时，必须使用本技能。有磁盘路径用 --image；粘贴图/无路径用 vision.py --from-clipboard（需用户重新复制图片到系统剪贴板）或请用户保存路径。不要先尝试主模型识图。生图支持 skill config.json 与 Codex/Hermes/OpenClaw/env/CLI 凭据。

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.