← 返回 Skills 市场
156
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install phosor-ai
功能描述
Generate AI videos (text-to-video, image-to-video) with optional custom LoRA styles via the Phosor AI platform. Supports importing images and LoRA models fro...
安全使用建议
This skill appears to be a straightforward CLI client for phosor.ai and is internally consistent. Before installing: (1) Only provide a PHOSOR_API_KEY you trust—the key is sent as X-API-Key on all requests and will be used/billed by phosor.ai. (2) The CLI will write phosor-pending.json in ~/.openclaw/workspace to track jobs; remove that file if you want no local state. (3) Uploading or importing LoRA (.safetensors) or images will transmit those files or their URLs to Phosor's service—do not upload sensitive data you do not want stored or processed by the external service. (4) If you plan to override PHOSOR_BASE_URL, ensure the endpoint is trusted; note the SKILL.md marks PHOSOR_BASE_URL as required but the client will default to https://phosor.ai if omitted. (5) If you need stronger assurance, review scripts/phosor_client.py (included) to confirm network endpoints and behavior; the code uses urllib and standard HTTPS endpoints documented in references/api.md.
能力评估
Purpose & Capability
The skill name/description (Phosor AI video generation + LoRA support) align with the included CLI and API references. The declared requirements (python3, PHOSOR_API_KEY, PHOSOR_BASE_URL, and a local phosor-pending.json) map to the script's behavior. Minor inconsistency: SKILL.md's requires lists PHOSOR_BASE_URL as required, but the client treats PHOSOR_BASE_URL as optional (defaults to https://phosor.ai).
Instruction Scope
SKILL.md instructs the agent to call the included CLI (scripts/phosor_client.py) for submit/status/result/upload/import operations. The instructions only reference the API key, optional base URL, local pending file, and user-supplied files/URLs (images, .safetensors). There are no instructions to read unrelated system files or other credentials.
Install Mechanism
No install spec is present (instruction-only plus an included Python script). No network downloads or archive extraction during install. The client is stdlib-only and requires python3, which is proportionate for a CLI script.
Credentials
Only PHOSOR_API_KEY (primary) and PHOSOR_BASE_URL are declared. PHOSOR_API_KEY is necessary and expected; PHOSOR_BASE_URL is a reasonable optional override but is declared as required in metadata despite being optional in code. The skill writes a local tracking file (phosor-pending.json) under ~/.openclaw/workspace, which is proportional to its job-polling behavior.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges. It writes only its own pending-job file in the user's workspace and does not modify other skills or system-wide agent configuration. The skill can be invoked autonomously (default), which is normal for skills; this combined with a single API key is not excessive.
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 phosor-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/phosor-ai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
v1.0.2
Phosor AI 1.0.0 – Initial Release
- AI content generation platform, supporting Wan 2.2 14B text-to-video and image-to-video
- Upload and use custom LoRA models for style customization
- 16 CLI commands for job submission, uploads, status, results, and model listing
- Supports preset resolutions (480p/720p/1080p), frame alignment rules, and usage quotas
v1.0.1
Phosor AI 1.0.1
- AI content generation platform, supporting Wan 2.2 14B text-to-video and image-to-video
- Upload and use custom LoRA models for style customization
- 16 CLI commands for job submission, uploads, status, results, and model listing
- Supports preset resolutions (480p/720p/1080p), frame alignment rules, and usage quotas
v1.0.0
Initial release of phosor-ai 1.0.0
- AI content generation platform, supporting Wan 2.2 14B text-to-video and image-to-video
- Upload and use custom LoRA models for style customization
- 16 CLI commands for job submission, uploads, status, results, and model listing
- Supports preset resolutions (480p/720p/1080p), frame alignment rules, and usage quotas
元数据
常见问题
Phosor AI 是什么？
Generate AI videos (text-to-video, image-to-video) with optional custom LoRA styles via the Phosor AI platform. Supports importing images and LoRA models fro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 156 次。
如何安装 Phosor AI？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install phosor-ai」即可一键安装，无需额外配置。
Phosor AI 是免费的吗？
是的，Phosor AI 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Phosor AI 支持哪些平台？
Phosor AI 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 Phosor AI？
由 Jason（@jasonstarlight）开发并维护，当前版本 v1.0.2。
推荐 Skills