@seanyao/roll 0.5.0 → 2.602.2

package/skills/roll-research/scripts/md_to_pdf.py

@@ -1,289 +0,0 @@
-#!/usr/bin/env python3
-"""
-Deep Research Report: Markdown to PDF converter (WeasyPrint)
-Usage: python md_to_pdf.py input.md output.pdf [--title "Report Title"] [--author "Author"]
-
-Dependencies: pip install weasyprint markdown --break-system-packages
-"""
-
-import sys
-import os
-import re
-import argparse
-import markdown
-
-# ── CSS Styles ──
-CSS_TEMPLATE = """
-@page {
-    size: A4;
-    margin: 25mm 20mm 20mm 20mm;
-
-    @top-center {
-        content: "HEADER_TEXT";
-        font-family: "Droid Sans Fallback", Helvetica, Arial, sans-serif;
-        font-size: 8pt;
-        color: #95a5a6;
-        border-bottom: 0.5pt solid #ecf0f1;
-        padding-bottom: 3mm;
-    }
-
-    @bottom-center {
-        content: "Page " counter(page);
-        font-family: "Droid Sans Fallback", Helvetica, Arial, sans-serif;
-        font-size: 8pt;
-        color: #95a5a6;
-        border-top: 0.8pt solid #1a5276;
-        padding-top: 2mm;
-    }
-}
-
-@page :first {
-    @top-center { content: none; }
-    @bottom-center { content: none; }
-}
-
-body {
-    font-family: "Droid Sans Fallback", Helvetica, Arial, sans-serif;
-    font-size: 10.5pt;
-    line-height: 1.75;
-    color: #2c3e50;
-    text-align: justify;
-}
-
-/* Cover page */
-.cover {
-    page-break-after: always;
-    text-align: center;
-    padding-top: 45%;
-}
-.cover h1 {
-    font-size: 28pt;
-    color: #1a5276;
-    margin-bottom: 8mm;
-    font-weight: bold;
-    letter-spacing: 2pt;
-}
-.cover .subtitle {
-    font-size: 14pt;
-    color: #95a5a6;
-    margin-bottom: 6mm;
-}
-.cover .meta {
-    font-size: 11pt;
-    color: #95a5a6;
-    margin-bottom: 4mm;
-}
-.cover .divider {
-    width: 60%;
-    margin: 8mm auto;
-    border: none;
-    border-top: 1.5pt solid #1a5276;
-}
-
-/* H1 */
-h1 {
-    font-size: 20pt;
-    color: #1a5276;
-    margin-top: 16mm;
-    margin-bottom: 6mm;
-    padding-bottom: 3mm;
-    border-bottom: 2pt solid #1a5276;
-    page-break-before: always;
-    font-weight: bold;
-}
-
-/* H2 */
-h2 {
-    font-size: 14pt;
-    color: #1e8449;
-    margin-top: 10mm;
-    margin-bottom: 5mm;
-    font-weight: bold;
-}
-
-/* H3 */
-h3 {
-    font-size: 12pt;
-    color: #2e86c1;
-    margin-top: 6mm;
-    margin-bottom: 3mm;
-    font-weight: bold;
-}
-
-h4 {
-    font-size: 11pt;
-    color: #5b2c6f;
-    margin-top: 5mm;
-    margin-bottom: 2mm;
-    font-weight: bold;
-}
-
-/* Paragraphs */
-p {
-    margin-top: 1.5mm;
-    margin-bottom: 1.5mm;
-    orphans: 3;
-    widows: 3;
-}
-
-/* Blockquotes */
-blockquote {
-    margin: 4mm 0;
-    padding: 4mm 4mm 4mm 10mm;
-    background: #f8f9fa;
-    border-left: 3pt solid #1a5276;
-    color: #5d6d7e;
-    font-size: 10pt;
-}
-blockquote p {
-    margin: 1mm 0;
-}
-
-/* Bold */
-strong, b {
-    font-weight: bold;
-    color: #1a252f;
-}
-
-/* Inline code */
-code {
-    font-family: "Courier New", Courier, monospace;
-    background: #fdf2e9;
-    color: #c0392b;
-    padding: 0.5mm 1.5mm;
-    border-radius: 2pt;
-    font-size: 9.5pt;
-}
-
-/* Tables */
-table {
-    width: 100%;
-    border-collapse: collapse;
-    margin: 4mm 0;
-    font-size: 9.5pt;
-}
-thead th {
-    background: #1a5276;
-    color: white;
-    padding: 3mm;
-    text-align: left;
-    font-weight: bold;
-}
-tbody td {
-    padding: 2.5mm 3mm;
-    border-bottom: 0.5pt solid #bdc3c7;
-}
-tbody tr:nth-child(even) {
-    background: #f8f9fa;
-}
-
-/* Horizontal rule */
-hr {
-    border: none;
-    border-top: 0.5pt solid #bdc3c7;
-    margin: 4mm 0;
-}
-
-/* Lists */
-ul, ol {
-    margin: 2mm 0;
-    padding-left: 8mm;
-}
-li {
-    margin-bottom: 1mm;
-}
-
-/* Links */
-a {
-    color: #2e86c1;
-    text-decoration: none;
-}
-"""
-
-
-def md_to_html(md_text, title="Deep Research Report", subtitle="Let's roll",
-               meta_line="", author="roll"):
-    """Convert Markdown to HTML with cover page"""
-
-    # Convert body with markdown library
-    html_body = markdown.markdown(
-        md_text,
-        extensions=['tables', 'fenced_code', 'nl2br'],
-        output_format='html5'
-    )
-
-    # Extract first H1 for cover (remove from body)
-    first_h1_match = re.search(r'<h1>(.*?)</h1>', html_body)
-    if first_h1_match:
-        extracted_title = first_h1_match.group(1)
-        if not title or title == "Deep Research Report":
-            title = extracted_title
-        html_body = html_body.replace(first_h1_match.group(0), '', 1)
-
-    # Replace header placeholder in CSS
-    css = CSS_TEMPLATE.replace("HEADER_TEXT", f"{title}  |  Deep Research Report")
-
-    # Build cover page
-    cover_html = f"""
-    <div class="cover">
-        <h1 style="page-break-before: avoid; border: none;">{title}</h1>
-        <div class="subtitle">{subtitle}</div>
-        {"<div class='meta'>" + meta_line + "</div>" if meta_line else ""}
-        <hr class="divider">
-        <div class="meta">Author: {author}</div>
-    </div>
-    """
-
-    full_html = f"""<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <style>{css}</style>
-</head>
-<body>
-{cover_html}
-{html_body}
-</body>
-</html>"""
-
-    return full_html
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Deep Research Report: Markdown to PDF")
-    parser.add_argument("input", help="Input Markdown file path")
-    parser.add_argument("output", help="Output PDF file path")
-    parser.add_argument("--title", default=None, help="Report title")
-    parser.add_argument("--author", default="roll", help="Author name")
-    parser.add_argument("--subtitle", default="Let's roll", help="Report subtitle")
-    args = parser.parse_args()
-
-    with open(args.input, "r", encoding="utf-8") as f:
-        md_text = f.read()
-
-    # Extract metadata line
-    meta_line = ""
-    for line in md_text.split("\n"):
-        stripped = line.strip().lstrip(">").strip()
-        if "research date" in stripped.lower() or "field:" in stripped.lower() or "subject type" in stripped.lower():
-            meta_line = stripped
-            break
-
-    html = md_to_html(md_text, title=args.title or "Deep Research Report",
-                      subtitle=args.subtitle, meta_line=meta_line, author=args.author)
-
-    # Save intermediate HTML (for debugging)
-    html_path = args.output.replace('.pdf', '.html')
-    with open(html_path, 'w', encoding='utf-8') as f:
-        f.write(html)
-    print(f"[OK] HTML generated: {html_path}")
-
-    # Convert to PDF
-    from weasyprint import HTML
-    HTML(string=html).write_pdf(args.output)
-    size_kb = os.path.getsize(args.output) / 1024
-    print(f"[OK] PDF generated: {args.output} ({size_kb:.1f} KB)")
-
-
-if __name__ == "__main__":
-    main()

package/tools/roll-fetch/SKILL.md

@@ -1,182 +0,0 @@
----
-hidden: true
-name: roll-fetch
-description: Web page fetching and crawling for AI agents. Extract content from URLs for research, documentation, and competitive analysis.
----
-
-# Roll Fetch - Web Content Extraction
-
-Extract content from web pages for research and analysis.
-
-## When to Use
-
-- Product research (competitor analysis)
-- Technical documentation gathering
-- Code examples and best practices
-- Full site crawling for backup/analysis
-
-## Environment Setup
-
-Configure API keys per machine:
-
-```bash
-# Required for Tavily
-export TAVILY_API_KEY=tvly-dev-...
-
-# Optional for cloud browser fallback
-export BROWSER_USE_API_KEY=bu-...
-```
-
-Or create `.env` file in project root:
-```
-TAVILY_API_KEY=tvly-dev-...
-BROWSER_USE_API_KEY=bu-...
-```
-
-## Methods
-
-### 1. Tavily API (Recommended)
-
-Best quality extraction, requires `TAVILY_API_KEY`.
-
-```bash
-# Using Tavily CLI or API
-curl -X POST https://api.tavily.com/extract \
-  -H "Content-Type: application/json" \
-  -d '{
-    "urls": ["https://example.com"],
-    "api_key": "your_tavily_api_key"
-  }'
-```
-
-**Pros**: AI-optimized extraction, handles complex layouts
-**Cons**: Requires API key, rate limited
-
-### 2. LLM Native Fetch (Default)
-
-Use your built-in URL fetching capability directly.
-
-**When to use**: When Tavily is unavailable or for quick checks.
-
-**Note**: Most modern AI agents (Kimi, Codex, Claude) have native URL fetching. Use `FetchURL` tool or equivalent.
-
-### 3. Browser Automation (Fallback)
-
-Local browser automation for stubborn pages using **[browser-use](https://github.com/browser-use/browser-use)**.
-
-**How to Choose:**
-
-| If | Then Use | Why |
-|----|---------|-----|
-| `BROWSER_USE_API_KEY` in env | **Cloud** | Managed browsers, less setup |
-| No API key, but `browser-use` installed | **Local** | Free, no external dependency |
-| Neither | Skip to manual extraction | Tell user "Need browser automation setup" |
-
-**Option A: Local (Free, No API Key)**
-```python
-from browser_use import Agent, Browser, BrowserConfig
-import asyncio
-
-async def fetch_page(url):
-    # Pure local, no API key needed
-    browser = Browser(config=BrowserConfig(headless=True))
-    await browser.start()
-    page = await browser.get_current_page()
-    await page.goto(url)
-    content = await page.content()
-    await browser.stop()
-    return content
-
-# Run
-content = asyncio.run(fetch_page("https://example.com"))
-```
-
-**Option B: Cloud API**
-```python
-from browser_use import Agent
-
-agent = Agent(
-    task=f"Extract the main content from {url} and return as markdown",
-    llm="moonshot"  # or openai, anthropic
-)
-result = await agent.run()
-```
-
-**Setup** (Local):
-```bash
-pip install browser-use
-playwright install chromium
-```
-
-## Usage
-
-### CLI Usage (via smart-web-fetch.js)
-
-```bash
-# Auto mode (Tavily → Native → Browser)
-node smart-web-fetch.js fetch https://example.com
-
-# Explicit method
-node smart-web-fetch.js fetch https://example.com tavily
-node smart-web-fetch.js fetch https://example.com native
-node smart-web-fetch.js fetch https://example.com browser
-
-# Search
-node smart-web-fetch.js search "Python async" 5
-```
-
-### Programmatic Usage
-
-```javascript
-const { smartFetch, smartSearch } = require('./smart-web-fetch.js');
-
-// Fetch a page
-const result = await smartFetch('https://example.com');
-console.log(result.content);
-
-// Search
-const searchResult = await smartSearch('OpenAI GPT-5', 5);
-console.log(searchResult.results);
-```
-
-### Single Page Fetch
-
-```
-User: "Fetch https://docs.example.com/api"
-→ Use smart-web-fetch.js with auto mode
-→ Return clean markdown content
-```
-
-### Full Site Crawl
-
-```
-User: "Crawl https://docs.example.com"
-→ Use smart-web-fetch.js recursively
-→ Extract all internal links
-→ Recursively fetch up to max depth (default: 2)
-→ Save each page as separate markdown file
-```
-
-## Output Format
-
-Always return clean Markdown:
-- Extract main content only (remove nav, ads, footers)
-- Preserve code blocks and tables
-- Include source URL as header
-
-## Quality Check
-
-Validate extracted content:
-- Min length: 500 chars (reject if shorter)
-- Check for captcha/error messages
-- Verify main content structure (headings, paragraphs)
-
-## Examples
-
-| Task | Method | Command |
-|------|--------|---------|
-| Quick article | Auto | `node smart-web-fetch.js fetch https://blog.example.com` |
-| API docs | Tavily | `node smart-web-fetch.js fetch https://docs.example.com tavily` |
-| SPA site | Browser | `node smart-web-fetch.js fetch https://spa.example.com browser` |
-| Search | Tavily | `node smart-web-fetch.js search "Python async" 5` |
-| Fallback test | Native | `node smart-web-fetch.js fetch https://example.com native` |

package/tools/roll-fetch/package.json

@@ -1,15 +0,0 @@
-{
-  "name": "smart-web-fetch",
-  "version": "1.0.0",
-  "description": "Intelligent web fetching with automatic Tavily → Scrapling fallback",
-  "main": "smart-web-fetch.js",
-  "bin": {
-    "smart-web-fetch": "./smart-web-fetch.js"
-  },
-  "scripts": {
-    "test": "node smart-web-fetch.js fetch https://example.com"
-  },
-  "keywords": ["web-scraping", "tavily", "scrapling", "fallback"],
-  "author": "R0_lobster",
-  "license": "MIT"
-}