← 返回 Skills 市场
169
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install ppt-ocr
功能描述
OCR for PowerPoint (.ppt, .pptx) presentations with scanned or image-embedded slides. Uses MinerU to extract text from image-based presentation content. Feat...
安全使用建议
This skill appears internally consistent: it expects the mineru-open-api CLI and a MinerU token and runs that CLI to OCR .ppt/.pptx files. Before installing or using it: 1) Expect your slides (or any URL you pass) to be sent to the MinerU service — don't upload sensitive/proprietary slides unless you trust mineru.net and understand their data handling and token scopes. 2) Verify the npm package and the GitHub repo (versions, maintainership, recent activity) before running 'npm install -g' or 'go install'. 3) If you need local-only processing, consider auditing or building the open-source MinerU code yourself or running it in an isolated environment. 4) Limit the MINERU_TOKEN permissions if possible and store it securely (not in shared shell history).
功能分析
Type: OpenClaw Skill
Name: ppt-ocr
Version: 0.4.0
The ppt-ocr skill is a documentation-based wrapper for the 'mineru-open-api' tool, used to perform OCR on PowerPoint presentations via the MinerU service (OpenDataLab). It requires a standard API token (MINERU_TOKEN) and uses legitimate installation paths via npm or Go. No malicious code, data exfiltration logic, or prompt injection attempts were identified in the provided files.
能力评估
Purpose & Capability
Name/description match the declared binary (mineru-open-api) and the single required env var (MINERU_TOKEN). The install targets (npm package and Go repo) produce the expected binary. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to run mineru-open-api commands, authenticate with MINERU_TOKEN, and process local files or URLs. This is within scope, but the workflow implies uploading file contents to the MinerU service (remote API) — users should expect data transmission to an external service and verify privacy/usage policies before sending sensitive slides.
Install Mechanism
Install is via npm or 'go install' from a named GitHub repo — standard package sources. No arbitrary URL downloads or extracted archives are used. Users should still verify the npm package and GitHub repo for expected code and versions before installing.
Credentials
Only a single token (MINERU_TOKEN) is required and is consistent with the CLI's auth model. No other credentials, secrets, or system config paths are requested.
Persistence & Privilege
Skill does not request always:true, does not declare system config paths, and is user-invocable. Autonomous invocation is allowed (platform default) but not excessive in this skill's context.
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 ppt-ocr - 安装完成后，直接呼叫该 Skill 的名称或使用
/ppt-ocr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
v0.4.0
SEO: expand description for better ClawHub vector search discovery
v0.3.0
Rollback to original version
v0.2.0
SEO optimization v0.2.0
v1.0.1
Minor update
v1.0.0
Initial release
元数据
常见问题
Ppt Ocr 是什么？
OCR for PowerPoint (.ppt, .pptx) presentations with scanned or image-embedded slides. Uses MinerU to extract text from image-based presentation content. Feat... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 169 次。
如何安装 Ppt Ocr？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ppt-ocr」即可一键安装，无需额外配置。
Ppt Ocr 是免费的吗？
是的，Ppt Ocr 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ppt Ocr 支持哪些平台？
Ppt Ocr 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 Ppt Ocr？
由 mzlzyCA（@mzlzyca）开发并维护，当前版本 v0.4.0。
推荐 Skills