← 返回 Skills 市场
Perstudio Image and Video Generation
作者
montenegronyc
· GitHub ↗
· v3.2.1
494
总下载
2
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install skill-perstudio
功能描述
Studio-grade AI image and video generation — photorealistic portraits, product shots, stickers, animations, and more. Just describe what you want.
安全使用建议
This skill appears internally consistent: it needs only a perstudio API key and an npm client plugin and restricts uploads to a small set of directories. Before installing, verify the npm package and GitHub repository match (to avoid typosquatting), review the source code if you can, and confirm the package maintainers/publishing history. Treat PERSTUDIO_API_KEY like any API secret: use a scoped or revocable key if possible, rotate it regularly, and avoid uploading sensitive personal or proprietary images since assets are sent to an external service (perstudio.ai) and generation incurs costs.
功能分析
Type: OpenClaw Skill
Name: skill-perstudio
Version: 3.2.1
The skill bundle is classified as benign. The `SKILL.md` clearly outlines the purpose of AI image/video generation and includes explicit security measures, such as restricting file access for the `upload_asset` action to an allowlist of directories (`~/Pictures`, `~/Downloads`, etc.) and requiring an API key for all operations. There is no evidence of prompt injection attempts against the agent, data exfiltration, malicious execution, or persistence mechanisms within the provided files. The `npm install -g perstudio-openclaw` instruction is a standard method for installing Node.js CLI tools and does not, by itself, indicate malicious intent within this context.
能力评估
Purpose & Capability
Name/description match the declared requirements: a single PERSTUDIO_API_KEY and an npm package (perstudio-openclaw) are reasonable for a third-party image/video generation integration. The declared config path (plugins.entries.perstudio.config.apiKey) is consistent with storing the API key.
Instruction Scope
SKILL.md instructions focus on generation actions and uploading assets. File-access rules are explicit (allowlist for ~/Pictures, ~/Downloads, ~/Desktop, ~/.openclaw/workspace, and temp) and the doc states symlink resolution is performed. Instructions do not ask the agent to read unrelated system files or additional environment variables.
Install Mechanism
Install is via a named npm package (perstudio-openclaw) which is an expected mechanism for a Node-based plugin. NPM installs carry the usual supply-chain risk (typosquatting, malicious package updates), but the mechanism itself is coherent with the skill's purpose. The SKILL.md also points to a GitHub repo for review.
Credentials
Only one credential (PERSTUDIO_API_KEY) is required and it is identified as the primary credential; this is proportionate for a hosted generation service. No other unrelated secrets or config paths are requested.
Persistence & Privilege
The skill is not always-enabled, and model invocation is allowed (the platform default). The skill does not request elevated or cross-skill configuration changes beyond storing its own API key in the declared plugin config path.
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 skill-perstudio - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-perstudio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
v3.2.1
- Updated description for improved clarity and feature detail.
- Added repository link and open-source details.
- Documented new file upload security restrictions: `upload_asset` now only accepts files from specific allowed directories.
- Added a dedicated Security section outlining file and API key requirements.
- Minor updates to usage examples to reflect new path restrictions.
v3.2.0
- Addressed security concerns
- Generate AI images, videos, and audio from natural language prompts.
- Supports a wide range of capabilities: text-to-image, image-to-image, upscaling, inpainting, style transfer, stickers/icons, video, and text-to-speech.
- Includes usage examples and guidance for setup and token management.
v3.1.6
- Added detailed metadata for improved setup and environment variable management.
- No functional or user-facing changes to core features or instructions.
v3.1.5
Security updates
v3.1.3
- Initial release of the perstudio skill.
- Generate AI images, videos, and audio using natural language prompts.
- Supports features like text-to-image, image transformation, product photography, portraits, style transfer, stickers, inpainting, upscaling, and text-to-speech.
- Includes usage examples and instructions for setup.
- Token-based billing with balance check action and pricing information.
元数据
常见问题
Perstudio Image and Video Generation 是什么？
Studio-grade AI image and video generation — photorealistic portraits, product shots, stickers, animations, and more. Just describe what you want. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 494 次。
如何安装 Perstudio Image and Video Generation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-perstudio」即可一键安装，无需额外配置。
Perstudio Image and Video Generation 是免费的吗？
是的，Perstudio Image and Video Generation 完全免费（开源免费），可自由下载、安装和使用。
Perstudio Image and Video Generation 支持哪些平台？
Perstudio Image and Video Generation 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 Perstudio Image and Video Generation？
由 montenegronyc（@montenegronyc）开发并维护，当前版本 v3.2.1。
推荐 Skills