← 返回 Skills 市场
GPT-4o-image
作者
coolhackboy
· GitHub ↗
· v1.0.0
· MIT-0
300
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install poyo-gpt-4o-image
功能描述
Use PoYo AI GPT-4o Image through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants to generate or edit media with this model fami...
安全使用建议
This skill appears coherent and limited to calling PoYo's image API. Before installing: (1) Confirm POYO_API_KEY is a dedicated API key for PoYo (do not reuse other service keys). (2) When using callback_url, ensure the webhook endpoint is trusted and won't leak generated content or user data. (3) Be aware the included script reads payloads from a file or stdin — avoid passing secrets or unrelated files as the payload argument. (4) If you need stronger guarantees, test the curl command in a controlled environment and inspect returned task_id behavior.
功能分析
Type: OpenClaw Skill
Name: poyo-gpt-4o-image
Version: 1.0.0
The skill bundle is a standard integration for the PoYo AI GPT-4o Image API. The shell script `scripts/submit_gpt_4o_image.sh` and the instructions in `SKILL.md` are strictly aligned with the stated purpose of submitting image generation tasks to `https://api.poyo.ai/api/generate/submit`. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name, description, SKILL.md, and the included shell script all target PoYo's image generation endpoint and only require curl and POYO_API_KEY, which are proportionate to the described purpose.
Instruction Scope
Runtime instructions are limited to building/submitting JSON payloads to https://api.poyo.ai/api/generate/submit, saving task_id, and polling status or using a callback URL. The script reads a payload file or stdin — expected behavior for a submission tool. There are no instructions to read unrelated system files or secrets.
Install Mechanism
This is an instruction-only skill with one small helper script and no install steps or external downloads. No suspicious install sources or extraction behavior are present.
Credentials
The only required environment variable is POYO_API_KEY (declared as primary), which is exactly what's needed to call the PoYo API. No additional credentials, config paths, or unrelated env vars are requested.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills/config. It can be invoked normally by the agent without elevated persistence.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install poyo-gpt-4o-image - 安装完成后，直接呼叫该 Skill 的名称或使用
/poyo-gpt-4o-image触发 - 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
v1.0.0
Initial release of poyo-gpt-4o-image skill.
- Supports submitting and tracking image generation/editing jobs with the PoYo GPT-4o Image model family.
- Builds and submits PoYo-compatible payloads to the `https://api.poyo.ai/api/generate/submit` endpoint.
- Handles both image generation (`gpt-4o-image`) and image editing (`gpt-4o-image-edit`) tasks.
- Provides workflow instructions, payload requirements, model selection guidance, and endpoint usage notes.
- Requires a `POYO_API_KEY` for authentication.
元数据
常见问题
GPT-4o-image 是什么？
Use PoYo AI GPT-4o Image through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants to generate or edit media with this model fami... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 300 次。
如何安装 GPT-4o-image？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install poyo-gpt-4o-image」即可一键安装，无需额外配置。
GPT-4o-image 是免费的吗？
是的，GPT-4o-image 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
GPT-4o-image 支持哪些平台？
GPT-4o-image 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 GPT-4o-image？
由 coolhackboy（@coolhackboy）开发并维护，当前版本 v1.0.0。
推荐 Skills