← 返回 Skills 市场
docsagent

DocsAgent

作者 docsagent · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
116
总下载
4
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install docsagent
功能描述
Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web...
使用说明 (SKILL.md)

DocsAgent Skill

DocsAgent is a local-first documentation engine designed to perform lightning-fast hybrid search (text and semantic search) over your private local files.

Key Features

  • Privacy-First: All indexing and searching happen 100% locally on your machine. No documents or data ever leave your system.
  • Hybrid Search: Combines semantic and keyword-based text search for high accuracy.
  • Supported Formats: Optimized for PDF, PPTX, and DOCX files.
  • No Web Dependency: This tool does not perform web searches. It relies on a local index you create.

Privacy Guarantee

  • 100% Local: All processing, indexing, and search operations are performed entirely on your machine.
  • Zero Data Leakage: No data is sent to external servers. Your documents remain private.

When to use

  • Use this when searching for information within your own private documentation, research papers, reports, or presentations.
  • Do not use this for general internet queries, news, or public website information.

Installation

DocsAgent is a CLI toolkit, when you install the global docsagent package, You can directly use 'docsagent' command.

npm install @docsagent/docsagent

For more information, please see https://github.com/docsagent/docsagent.

Usage Guidelines

1. Add Documentation

Adds directory or file paths (PDF, DOCX, PPTX) to the index. You can pass multiple paths at once.

# Add a single directory
docsagent add ./documents/manuals

# Add multiple files and directories at once
docsagent add ./reports/q1.pdf ./presentation.pptx ./notes/meeting-files
  • Use case: Use to index folders or specific private files for searchability.

2. Search Documents

Performs a hybrid search (text + semantic) across your indexed private documents.

# Search for a specific topic
docsagent search "how to configure local encryption"

# Search for technical concepts
docsagent search "API authentication process"

The tool returns the most relevant snippets with their source paths and scores.

  • Important: Ensure your documents have been indexed using the add operation before searching.

3. List Indexed Sources

Lists all files currently being monitored or indexed.

docsagent list

4. Check Status

Shows the indexing progress and service health.

docsagent status

5. Stop Agent

Stops the indexing service.

docsagent stop

Workflow: Answering Questions from Local Docs

  1. Check Index: If unsure if the documents are indexed, you can try a search first.
  2. Search: Execute search with a specific query derived from the user's request.
  3. Analyze: Review the context returned. If multiple snippets are found, synthesize them into a coherent answer.
  4. Cite Sources: Always mention the file path and page number (if available) in your response.

Error Handling

  • If search returns "No results found", inform the user and ask if they want to index a specific directory using add.
  • If a path is not found during add, verify the path exists before retrying.
安全使用建议
This skill is coherent for local document search, but it relies on an external npm package you would install. Before installing or running it: (1) inspect the npm package and its GitHub repository (package.json, source, maintainers, open issues) to confirm it truly runs locally and has no telemetry; (2) prefer auditing the package code or running it in a sandbox/container before giving it access to sensitive folders; (3) when indexing, limit the paths you add so the tool only reads intended directories; (4) don't assume the SKILL.md privacy promise is enforceable — verify network activity (e.g., with firewall/packet capture) if you must ensure no data leaves your machine.
功能分析
Type: OpenClaw Skill Name: docsagent Version: 1.0.1 The docsagent skill bundle describes a local-first document indexing and search tool. The instructions in SKILL.md are consistent with its stated purpose of managing private PDF, PPTX, and DOCX files offline, and the bundle contains no evidence of data exfiltration, malicious execution, or harmful prompt injection. The use of a scoped npm package (@docsagent/docsagent) for installation is a standard practice for CLI toolkits.
能力评估
Purpose & Capability
Name, description, and instructions all describe a CLI tool to index and search local PDF/PPTX/DOCX files; required capabilities and declared requirements (none) match that purpose.
Instruction Scope
SKILL.md confines operations to indexing and searching local files and instructs only CLI commands (add, search, list, status, stop). However, it asserts a strong privacy guarantee (“100% local”) that cannot be verified from the instruction file alone — the actual runtime behavior depends on the external npm package it directs you to install.
Install Mechanism
The registry has no formal install spec (skill is instruction-only) but the README suggests installing @docsagent/docsagent from npm and links to a GitHub repo. npm packages are a normal distribution method for CLI tools but do introduce network/third-party code risk; the skill itself does not perform any install actions, so verifying the package source is your responsibility.
Credentials
The skill requests no environment variables, no credentials, and no configuration paths — consistent with a local-only document indexer.
Persistence & Privilege
Skill is not always-enabled and does not request elevated or persistent platform privileges. There is no instruction to modify other skills or global agent configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install docsagent
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /docsagent 触发
  4. 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
v1.0.1
- Improved skill description and usage guidelines for clarity, emphasizing local, private document search only. - Added details on supported file formats (PDF, DOCX, PPTX) and clarified the tool doesn’t perform web searches. - Included a new workflow section for answering questions using local docs, with guidance on citing sources. - Added error handling guidelines for common scenarios (no search results, missing paths). - Updated install instructions and provided a link for more information.
v1.0.0
DocsAgent 1.0.0 initial release: - Enables lightning-fast hybrid (text + semantic) search over your private local PDF, DOCX, and PPTX files. - Ensures all operations are performed 100% locally, guaranteeing complete privacy. - Provides CLI commands to add, search, list, check status of, and stop document indexing. - Suitable for managing and searching private documentation without data ever leaving your machine.
元数据
Slug docsagent
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

DocsAgent 是什么?

Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 116 次。

如何安装 DocsAgent?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install docsagent」即可一键安装,无需额外配置。

DocsAgent 是免费的吗?

是的,DocsAgent 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

DocsAgent 支持哪些平台?

DocsAgent 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 DocsAgent?

由 docsagent(@docsagent)开发并维护,当前版本 v1.0.1。

💬 留言讨论