@heylemon/lemonade 0.2.2 → 0.2.3

package/skills/tavily-search/scripts/extract.mjs

@@ -0,0 +1,59 @@
+#!/usr/bin/env node
+
+function usage() {
+  console.error(`Usage: extract.mjs "url1" ["url2" ...]`);
+  process.exit(2);
+}
+
+const args = process.argv.slice(2);
+if (args.length === 0 || args[0] === "-h" || args[0] === "--help") usage();
+
+const urls = args.filter(a => !a.startsWith("-"));
+
+if (urls.length === 0) {
+  console.error("No URLs provided");
+  usage();
+}
+
+const apiKey = (process.env.TAVILY_API_KEY ?? "").trim();
+if (!apiKey) {
+  console.error("Missing TAVILY_API_KEY");
+  process.exit(1);
+}
+
+const resp = await fetch("https://api.tavily.com/extract", {
+  method: "POST",
+  headers: {
+    "Content-Type": "application/json",
+  },
+  body: JSON.stringify({
+    api_key: apiKey,
+    urls: urls,
+  }),
+});
+
+if (!resp.ok) {
+  const text = await resp.text().catch(() => "");
+  throw new Error(`Tavily Extract failed (${resp.status}): ${text}`);
+}
+
+const data = await resp.json();
+
+const results = data.results ?? [];
+const failed = data.failed_results ?? [];
+
+for (const r of results) {
+  const url = String(r?.url ?? "").trim();
+  const content = String(r?.raw_content ?? "").trim();
+
+  console.log(`# ${url}\n`);
+  console.log(content || "(no content extracted)");
+  console.log("\n---\n");
+}
+
+if (failed.length > 0) {
+  console.log("## Failed URLs\n");
+  for (const f of failed) {
+    console.log(`- ${f.url}: ${f.error}`);
+  }
+}

package/skills/tavily-search/scripts/search.mjs

@@ -0,0 +1,101 @@
+#!/usr/bin/env node
+
+function usage() {
+  console.error(`Usage: search.mjs "query" [-n 5] [--deep] [--topic general|news] [--days 7]`);
+  process.exit(2);
+}
+
+const args = process.argv.slice(2);
+if (args.length === 0 || args[0] === "-h" || args[0] === "--help") usage();
+
+const query = args[0];
+let n = 5;
+let searchDepth = "basic";
+let topic = "general";
+let days = null;
+
+for (let i = 1; i < args.length; i++) {
+  const a = args[i];
+  if (a === "-n") {
+    n = Number.parseInt(args[i + 1] ?? "5", 10);
+    i++;
+    continue;
+  }
+  if (a === "--deep") {
+    searchDepth = "advanced";
+    continue;
+  }
+  if (a === "--topic") {
+    topic = args[i + 1] ?? "general";
+    i++;
+    continue;
+  }
+  if (a === "--days") {
+    days = Number.parseInt(args[i + 1] ?? "7", 10);
+    i++;
+    continue;
+  }
+  console.error(`Unknown arg: ${a}`);
+  usage();
+}
+
+const apiKey = (process.env.TAVILY_API_KEY ?? "").trim();
+if (!apiKey) {
+  console.error("Missing TAVILY_API_KEY");
+  process.exit(1);
+}
+
+const body = {
+  api_key: apiKey,
+  query: query,
+  search_depth: searchDepth,
+  topic: topic,
+  max_results: Math.max(1, Math.min(n, 20)),
+  include_answer: true,
+  include_raw_content: false,
+};
+
+if (topic === "news" && days) {
+  body.days = days;
+}
+
+const resp = await fetch("https://api.tavily.com/search", {
+  method: "POST",
+  headers: {
+    "Content-Type": "application/json",
+  },
+  body: JSON.stringify(body),
+});
+
+if (!resp.ok) {
+  const text = await resp.text().catch(() => "");
+  throw new Error(`Tavily Search failed (${resp.status}): ${text}`);
+}
+
+const data = await resp.json();
+
+// Print AI-generated answer if available
+if (data.answer) {
+  console.log("## Answer\n");
+  console.log(data.answer);
+  console.log("\n---\n");
+}
+
+// Print results
+const results = (data.results ?? []).slice(0, n);
+console.log("## Sources\n");
+
+for (const r of results) {
+  const title = String(r?.title ?? "").trim();
+  const url = String(r?.url ?? "").trim();
+  const content = String(r?.content ?? "").trim();
+  const score = r?.score ? ` (relevance: ${(r.score * 100).toFixed(0)}%)` : "";
+
+  if (!title || !url) continue;
+  console.log(`- **${title}**${score}`);
+  console.log(`  ${url}`);
+  if (content) {
+    console.log(`  ${content.slice(0, 300)}${content.length > 300 ? "..." : ""}`);
+  }
+  console.log();
+}

package/skills/youtube-watcher/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: youtube-watcher
+description: Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
+author: michael gathara
+version: 1.0.0
+triggers:
+  - "watch youtube"
+  - "summarize video"
+  - "video transcript"
+  - "youtube summary"
+  - "analyze video"
+metadata: {"lemonade":{"emoji":"📺","requires":{"bins":["yt-dlp"]},"install":[{"id":"brew","kind":"brew","formula":"yt-dlp","bins":["yt-dlp"],"label":"Install yt-dlp (brew)"},{"id":"pip","kind":"pip","package":"yt-dlp","bins":["yt-dlp"],"label":"Install yt-dlp (pip)"}]}}
+---
+
+# YouTube Watcher
+
+Fetch transcripts from YouTube videos to enable summarization, QA, and content extraction.
+
+## Usage
+
+### Get Transcript
+
+```bash
+python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"
+```
+
+## Examples
+
+**Summarize a video:**
+
+1. Get the transcript:
+   ```bash
+   python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+   ```
+2. Read the output and summarize it for the user.
+
+**Find specific information:**
+
+1. Get the transcript.
+2. Search the text for keywords or answer the user's question based on the content.
+
+## Notes
+
+- Requires `yt-dlp` to be installed and available in the PATH.
+- Works with videos that have closed captions (CC) or auto-generated subtitles.
+- If a video has no subtitles, the script will fail with an error message.

package/skills/youtube-watcher/scripts/get_transcript.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+import argparse
+import os
+import re
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+
+def clean_vtt(content: str) -> str:
+    """
+    Clean WebVTT content to plain text.
+    Removes headers, timestamps, and duplicate lines.
+    """
+    lines = content.splitlines()
+    text_lines = []
+    seen = set()
+
+    timestamp_pattern = re.compile(r'\d{2}:\d{2}:\d{2}\.\d{3}\s-->\s\d{2}:\d{2}:\d{2}\.\d{3}')
+
+    for line in lines:
+        line = line.strip()
+        if not line or line == 'WEBVTT' or line.isdigit():
+            continue
+        if timestamp_pattern.match(line):
+            continue
+        if line.startswith('NOTE') or line.startswith('STYLE'):
+            continue
+
+        if text_lines and text_lines[-1] == line:
+            continue
+
+        line = re.sub(r'<[^>]+>', '', line)
+
+        text_lines.append(line)
+
+    return '\n'.join(text_lines)
+
+def get_transcript(url: str):
+    with tempfile.TemporaryDirectory() as temp_dir:
+        cmd = [
+            "yt-dlp",
+            "--write-subs",
+            "--write-auto-subs",
+            "--skip-download",
+            "--sub-lang", "en",
+            "--output", "subs",
+            url
+        ]
+
+        try:
+            subprocess.run(cmd, cwd=temp_dir, check=True, capture_output=True)
+        except subprocess.CalledProcessError as e:
+            print(f"Error running yt-dlp: {e.stderr.decode()}", file=sys.stderr)
+            sys.exit(1)
+        except FileNotFoundError:
+            print("Error: yt-dlp not found. Please install it.", file=sys.stderr)
+            sys.exit(1)
+
+        temp_path = Path(temp_dir)
+        vtt_files = list(temp_path.glob("*.vtt"))
+
+        if not vtt_files:
+            print("No subtitles found.", file=sys.stderr)
+            sys.exit(1)
+
+        vtt_file = vtt_files[0]
+
+        content = vtt_file.read_text(encoding='utf-8')
+        clean_text = clean_vtt(content)
+        print(clean_text)
+
+def main():
+    parser = argparse.ArgumentParser(description="Fetch YouTube transcript.")
+    parser.add_argument("url", help="YouTube video URL")
+    args = parser.parse_args()
+
+    get_transcript(args.url)
+
+if __name__ == "__main__":
+    main()