← 返回 Skills 市场
blacker521

chrome-bookmark-folder-summarizer

作者 blacker521 · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
230
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install chrome-bookmark-folder-summarizer
功能描述
Reads Chrome bookmarks and extracts URLs by a user-provided folder name, then generates batch webpage summaries. Use when the user mentions Chrome bookmarks/...
使用说明 (SKILL.md)

Chrome Bookmark Summarizer

Extract webpages from a Chrome bookmark folder (based on the user-provided folder name) and produce structured summaries.

When to Use

  • The user mentions "Chrome bookmarks", "favorites", "bookmark folder", or "summarize saved links"
  • You need to batch-read links by folder name and produce summaries
  • You need to filter URLs from a local bookmarks file before summarizing webpage content

Workflow

  1. Confirm input parameters

    • Required: target folder name (for example, AI Research)
    • Optional: match mode (exact or contains)
    • Optional: whether to recurse into subfolders (default: recursive)
  2. Run the extraction script (JSON output)

python3 "scripts/extract_chrome_bookmarks.py" --folder "AI Research"

Common options:

# Fuzzy folder-name matching
python3 "scripts/extract_chrome_bookmarks.py" --folder "AI" --match-mode contains

# If multiple folders share the same name, return only the first match
python3 "scripts/extract_chrome_bookmarks.py" --folder "AI Research" --pick-first

# Extract only direct links (no subfolders)
python3 "scripts/extract_chrome_bookmarks.py" --folder "AI Research" --non-recursive
  1. Parse output and handle errors

    • ok=false: return a clear error to the user (folder not found, invalid path, etc.)
    • ok=true: read results[].urls[] for downstream summarization
  2. Batch webpage summarization

    • Fetch page content for each URL (prefer full body text; fall back to title + short description on failure)
    • Recommended output structure:
      • Page title
      • Core takeaway (1-2 sentences)
      • Key points (2-4 bullets)
      • Relevance to user goal (one sentence)
  3. Final aggregation

    • Keep the original bookmark order
    • Add a cross-page comparison at the end:
      • Shared themes
      • Differing viewpoints
      • Recommended reading order

Output Template

## Folder: {folder_name}

### 1) {page_title}
- URL: {url}
- Core takeaway: {summary}
- Key points:
  - {point_1}
  - {point_2}
  - {point_3}
- Relevance: {relevance}

### 2) {page_title}
...

## Cross-Page Summary
- Shared themes: ...
- Differences: ...
- Suggested reading order: ...

Notes

  • Default Chrome bookmarks path on macOS:
    • ~/Library/Application Support/Google/Chrome/Default/Bookmarks
  • If the user has multiple Chrome profiles, ask for a specific Bookmarks file path and pass it with --bookmarks.
  • Duplicate folder names may exist; by default all matches are returned. Use --pick-first to keep only one.
安全使用建议
This skill reads your local Chrome Bookmarks file and extracts URLs from the folder you specify; it doesn't ask for credentials or install anything. Before running: (1) confirm the bookmarks file path if you use multiple Chrome profiles, (2) be aware that summarization requires fetching each URL (network requests) and those page contents may be sent to whatever summarization engine the agent uses (potential privacy exposure), and (3) review the extracted JSON output locally before sharing it. If you are concerned about sensitive URLs, run the script yourself in a safe environment and inspect results locally rather than sending raw page content to external services.
功能分析
Type: OpenClaw Skill Name: chrome-bookmark-folder-summarizer Version: 1.0.1 The skill is designed to extract and summarize URLs from a user-specified Chrome bookmark folder. The Python script `scripts/extract_chrome_bookmarks.py` correctly identifies standard bookmark paths across macOS, Windows, and Linux, parses the JSON data, and outputs the results to stdout for the agent to process. There is no evidence of data exfiltration to unauthorized endpoints, obfuscation, or malicious instructions in `SKILL.md`.
能力评估
Purpose & Capability
Name/description match the implementation. The included Python script reads the Chrome Bookmarks JSON, finds folders by name, and returns URLs. Required resources (local Bookmarks file, optional path override) are what you'd expect for a bookmark-folder summarizer.
Instruction Scope
SKILL.md stays on scope: run the extraction script, parse its JSON, then fetch and summarize each URL. One notable point: the instructions tell the agent to 'fetch page content' for summarization but do not constrain where that fetching/summarization happens — fetching pages will perform network requests and the page contents may be sent to the model or external services for summarization. This is expected for the described task but is a privacy consideration rather than an incoherence.
Install Mechanism
No install spec; the skill is instruction + a small local script. Nothing is downloaded or written by an installer, which is low-risk and proportionate.
Credentials
No environment variables, credentials, or special config paths are required. The script uses Path.home() and (optionally) the LOCALAPPDATA env var on Windows to locate Chrome's default Bookmarks file — this aligns with the stated purpose.
Persistence & Privilege
always is false, the skill does not request persistent/global privileges, and it does not modify other skills or system-wide settings. It only reads the specified bookmarks file when invoked.
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 chrome-bookmark-folder-summarizer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /chrome-bookmark-folder-summarizer 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
- Updated script paths in documentation from ".cursor/skills/chrome-bookmark-summarizer/scripts/" to "scripts/" for improved clarity and portability. - No functional or behavior changes; documentation only.
v1.0.0
- Initial release of Chrome Bookmark Summarizer. - Extracts URLs from a Chrome bookmark folder by user-supplied name (with exact or partial matching). - Supports recursive and non-recursive extraction, with options for handling duplicate folder names. - Generates structured, batch webpage summaries for each extracted URL. - Includes cross-page aggregation: shared themes, main differences, and suggested reading order. - Provides clear workflow guidelines, parameter explanations, and template for results
元数据
Slug chrome-bookmark-folder-summarizer
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

chrome-bookmark-folder-summarizer 是什么?

Reads Chrome bookmarks and extracts URLs by a user-provided folder name, then generates batch webpage summaries. Use when the user mentions Chrome bookmarks/... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 230 次。

如何安装 chrome-bookmark-folder-summarizer?

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

chrome-bookmark-folder-summarizer 是免费的吗?

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

chrome-bookmark-folder-summarizer 支持哪些平台?

chrome-bookmark-folder-summarizer 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 chrome-bookmark-folder-summarizer?

由 blacker521(@blacker521)开发并维护,当前版本 v1.0.1。

💬 留言讨论