← 返回 Skills 市场
729
总下载
0
收藏
1
当前安装
8
版本数
在 OpenClaw 中安装
/install pixeldojo
功能描述
Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog,...
安全使用建议
This skill appears to do what it says: call PixelDojo's API, poll jobs, and download results. Before enabling it, confirm you trust https://pixeldojo.ai and are comfortable providing an API key. Note the registry metadata omits marking PIXELDOJO_API_KEY as the primary credential — ensure the platform will prompt for or securely store that key. Be aware the helpers will save files into your home Pictures folder (or to any path you pass), and the skill requires outbound network access to the PixelDojo API. If you want tighter control, run the helpers in a sandboxed environment, use a scoped/rotatable API key, and review or run the scripts manually to verify behavior.
功能分析
Type: OpenClaw Skill
Name: pixeldojo
Version: 1.3.3
The PixelDojo skill bundle provides a legitimate integration for an AI image and video generation service. It includes shell and Python scripts (generate.sh, models.sh, scripts/generate-nano-banana.py) that interact with the https://pixeldojo.ai API to list models, submit generation tasks, and download the resulting media files. The implementation follows standard practices, such as using environment variables for API keys and sanitizing user input for filenames, with no evidence of malicious intent or data exfiltration.
能力评估
Purpose & Capability
Name/description, SKILL.md, api.json, and the helper scripts consistently implement calls to PixelDojo's API. Required binaries and the single required env var (PIXELDOJO_API_KEY) are appropriate for contacting the service and running the provided helpers.
Instruction Scope
Runtime instructions only call the PixelDojo API, poll job status, and download returned assets. The scripts read only the declared env vars (PIXELDOJO_API_KEY and optional PIXELDOJO_API_BASE) and write output under the user's home Pictures dir or a user-specified path; they do not attempt to read unrelated system files or other credentials.
Install Mechanism
This is instruction-only with bundled helper scripts (no install script that fetches arbitrary code). No external download or network-based installer is executed at install time.
Credentials
The skill requests only PIXELDOJO_API_KEY (appropriate). Minor metadata mismatch: registry metadata lists "Primary credential: none" while files require PIXELDOJO_API_KEY. The manifest requires python3 even though only the optional Nano Banana helper uses it—this is benign but worth noting.
Persistence & Privilege
always is false and autonomous invocation is the platform default. The skill writes outputs under user-owned paths and does not modify other skills or system-wide agent configuration.
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 pixeldojo - 安装完成后，直接呼叫该 Skill 的名称或使用
/pixeldojo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
v1.3.3
Add explicit frontmatter metadata for source attribution and runtime requirements to align scanner-visible metadata with api.json and SKILL.md.
v1.3.2
Republish security-reviewed PixelDojo skill after dependency cleanup and clearer runtime requirements; no undeclared Python packages.
v1.3.1
Remove undeclared Python requests dependency, clarify runtime requirements in SKILL.md, and tighten packaging consistency for security review.
v1.3.0
Polish PixelDojo skill for ClawHub publishing: clarify product positioning, tighten SKILL.md and metadata, clean up helper messaging, add API base override support, and validate package cleanly.
v1.1.0
Refresh PixelDojo skill against live /api/v1/models catalog, update documented model list, and make models.sh fetch current models dynamically.
v1.0.2
Save generated files to ~/Pictures/AI Generated/ for easy access in Finder and Photos app
v1.0.1
Fix metadata - add requires env/bins to SKILL.md header for registry parsing
v1.0.0
Initial release - generate AI images and videos via PixelDojo API
元数据
常见问题
PixelDojo 是什么？
Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 729 次。
如何安装 PixelDojo？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pixeldojo」即可一键安装，无需额外配置。
PixelDojo 是免费的吗？
是的，PixelDojo 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
PixelDojo 支持哪些平台？
PixelDojo 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 PixelDojo？
由 blovett80（@blovett80）开发并维护，当前版本 v1.3.3。
推荐 Skills