Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add idea2realClaw/myAgent --skill book-downloadergit clone --depth 1 https://github.com/idea2realClaw/myAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/idea2realclaw/myagent/book-downloader)<a href="https://agentmods.dev/skills/idea2realclaw/myagent/book-downloader"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/book-downloader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/idea2realclaw/myagent/book-downloader"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/book-downloader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.02093 |
| Opus 5 | $0.00043 | $0.01046 |
| Sonnet 5 | $0.00017 | $0.00419 |
| Haiku 4.5 | $0.00009 | $0.00209 |
Grade A, and why
book-downloader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
书籍下载 Skill v4（2026-04-04）
功能概述
| 步骤 | 功能 | 说明 |
|---|---|---|
| 1 | 搜索书籍 | Z-Library（推荐）、Project Gutenberg、鸠摩搜索 |
| 2 | 下载书籍 | 自动识别格式（PDF/EPUB/TXT） |
| 3 | PDF 转 TXT | 智能双路径：文字版直接提取，扫描件自动 OCR |
| 4 | 智能校对 | 通过 LLM 重写 OCR 文本，纠正错字乱码，生成通顺文字 |
依赖安装
# 核心（必须）
pip3 install pymupdf requests
# Z-Library SPA 搜索（必须，Playwright 动态页面）
pip3 install playwright
playwright install chromium # 首次运行前必须执行一次
# OCR（扫描件需要）
brew install tesseract tesseract-lang poppler
pip3 install pytesseract pdf2image
# 校对（需要 LLM API Key）
# 设置环境变量或使用参数 -k 传入
export OPENAI_API_KEY=sk-xxx
使用方法
一键完成（搜索 → 下载 → 转 TXT）
python3 ~/.workbuddy/skills/book-downloader/scripts/run.py "书名"
分步操作
# 仅搜索
python3 run.py "太极拳" --search-only
# 下载搜索结果的第N本（从0开始）
python3 run.py --download-only --index 1
# 直接将本地 PDF 转 TXT
python3 run.py --pdf ~/Downloads/book.pdf
# PDF 转 TXT（扫描件自动 OCR）
python3 run.py --pdf ~/Downloads/book.pdf --method ocr --ocr-lang chi_sim+eng
指定搜索源
| 参数 | 搜索源 | 说明 |
|---|---|---|
--source zlib |
Z-Library | 收录最全（默认），约 1500 万册 |
--source gutenberg |
Project Gutenberg | 公版书，约 7 万册 |
--source jiumo |
鸠摩搜索 | 国内资源 |
--source all |
全部 | 较慢 |
命令行参数
| 参数 | 说明 |
|---|---|
query |
搜索关键词（中文或英文） |
--search-only, -s |
仅搜索，不下载 |
--download-only, -d |
仅下载，使用上次搜索结果 |
--index, -i |
选择第几本书（从0开始，默认0） |
--output-dir, -o |
下载目录（默认 ~/Downloads/books） |
--lang, -l |
语言筛选 |
--source |
搜索源（默认 zlib） |
--pdf |
指定 PDF 文件直接转 TXT |
PDF 转 TXT 参数
| 参数 | 说明 |
|---|---|
--method auto |
智能（默认）：文字页直提，图片页自动 OCR |
--method pymupdf |
仅直提文字（快速，不含 OCR） |
--method ocr |
全量 OCR（适合纯扫描件，速度慢） |
--start, --end |
指定页码范围 |
--ocr-lang chi_sim+eng |
OCR 语言（中文+英文） |
--ocr-dpi 200 |
OCR 渲染清晰度（默认200，越高越清晰） |
输出位置
- 下载目录:
~/Downloads/books/ - 搜索结果缓存:
/tmp/book_search_results.json - TXT 文件: 与 PDF 同目录
经验总结（2026-04-04）
Z-Library SPA 技术要点
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 197 lines · 85 tokens per session scan A a9654f845bd7
book-downloader is a skill published in the GitHub repository idea2realClaw/myAgent (2 stars, last pushed 21d ago), licensed MIT. It adds 85 tokens to every session and 2,093 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.