openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > Books For Agents

Access and search a structured open source knowledge base of book summaries optimized for AI agents via the MCP protocol.

数据与表格

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v0.1.0

统计:⭐ 0 · 386 · 2 current installs · 2 all-time installs

0

安装量(当前) 2

🛡 VirusTotal :良性 · OpenClaw :良性

Package:danpalmieri/books-for-agents

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill is internally coherent: it instructs an agent to connect to a remote MCP server (booksforagents.com) to search, read, generate, and publish structured book summaries; it requires no credentials or installs and does not ask for unrelated system access.

目的

Name/description match the instructions: the SKILL.md configures an MCP server and exposes book-related RPCs (search_books, get_book, generate_book, submit_book, etc.). Minor inconsistency: the instructions show a shell command using a 'claude' CLI (claude mcp add ...) but the skill declares no required binaries. The CLI call is optional (an example), but the skill should ideally declare that a compatible MCP client/CLI is expected.

说明范围

Instructions stay within the stated purpose (searching/reading/generating/publishing book summaries). They do direct networked requests to an external endpoint (https://booksforagents.com/mcp) which is expected for this functionality — be aware queries and any generated/submitted content will be sent to that remote service. The skill does not instruct reading local files, environment variables, or other system-wide config beyond optionally edi…

安装机制

Instruction-only skill with no install spec or archive downloads. Nothing is written to disk by the skill itself beyond the user optionally editing their MCP config; low install risk.

证书

No environment variables, credentials, or config paths are requested. This is proportional to a read/search/publish knowledge-base skill. The only implicit requirement is network access to the listed MCP URL and (optionally) an MCP client/CLI.

持久

always:false and no special privileges requested. The skill does not request permanent system presence or modify other skills' configuration; autonomous invocation is allowed by default but not combined with other concerning privileges.

综合结论

This skill appears to do what it says: connect to a remote MCP server to query and manage book summaries. Before installing, consider: (1) it will send your queries and any generated content to https://booksforagents.com — avoid submitting sensitive or private data; (2) the SKILL.md demonstrates a 'claude' CLI command but doesn't declare that a compatible MCP client must be installed — ensure your agent environment provides an MCP client if yo…

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Books For Agents」。简介:Access and search a structured open source knowledge base of book summaries opt…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/danpalmieri/books-for-agents/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

# Books for Agents

An open source knowledge base of structured book summaries, available to any AI agent via MCP.

## Setup

1. If you don't have the `books-for-agents` MCP server installed, add it:

```
claude mcp add --transport http books-for-agents https://booksforagents.com/mcp
```

Or add to your MCP config file:

```json
{
  "mcpServers": {
    "books-for-agents": {
      "url": "https://booksforagents.com/mcp"
    }
  }
}
```

2. Once connected, you have access to all tools below.

## What you can do

### Search for books

Use `search_books` to find books by topic, keyword, or question. Supports hybrid search (full-text + semantic vector embeddings).

```
search_books({ query: "how to build better habits" })
search_books({ query: "leadership", category: "business" })
search_books({ query: "cognitive biases and decision making", limit: 3 })
```

### Read a book summary

Use `get_book` to retrieve the full structured summary of a specific book by slug or title (partial match supported).

```
get_book({ slug: "atomic-habits" })
get_book({ title: "Deep Work" })
```

### Read a specific section

Use `get_book_section` to retrieve only one section of a book — saves tokens when you don't need the full summary. Available sections: `ideas`, `frameworks`, `quotes`, `connections`, `when-to-use`.

```
get_book_section({ slug: "the-lean-startup", section: "frameworks" })
get_book_section({ slug: "clean-code", section: "quotes" })
get_book_section({ slug: "thinking-fast-and-slow", section: "when-to-use" })
```

### Browse categories

Use `list_categories` to see all available categories and how many books each one has.

```
list_categories()
```

### Suggest a new book

Use `suggest_book` to add a book to the generation backlog. Checks for duplicates against published books and existing backlog entries.

```
suggest_book({ title: "Thinking in Bets", author: "Annie Duke", category: "psychology" })
```

### See the backlog

Use `list_backlog` to see all pending books waiting to be generated, along with their status.

```
list_backlog()
```

### Generate a book summary

Use `generate_book` to get the template, example, metadata, and instructions needed to generate the next book summary. You can specify a title or let it pick the next pending one.

```
generate_book()
generate_book({ title: "Never Split the Difference" })
```

After generating the content, call `submit_book` to publish it.

### Publish a book summary

Use `submit_book` to publish a generated summary directly to the knowledge base. Call this after generating content with `generate_book`.

```
submit_book({
  slug: "never-split-the-difference",
  title: "Never Split the Difference",
  author: "Chris Voss",
  category: "business",
  content: "---ntitle: "Never Split the Difference"n..."
})
```

## Tips

- Use `get_book_section` instead of `get_book` when you only need one part — it saves significant tokens.
- Use `search_books` with natural language queries — the semantic search understands meaning, not just keywords.
- When generating a book, follow the template and instructions returned by `generate_book` exactly. All content must be in English.
- Connections between books use `[[slug]]` format and must reference existing books only.