skills/web-search/SKILL.md
Dual-engine web search using BOTH Firecrawl AND Brave Search simultaneously. ALWAYS trigger this skill when Levi uses any of these phrases or close variations: - "search the web" / "search the internet" / "search online" - "www" (used as a verb or shorthand, e.g. "www this", "look it up on the www") - "internet" (as in "check the internet", "find on the internet", "look this up on the internet") - "go online", "look this up online", "check online" - "search for X" when context implies web search (not local files or database) - "find X online", "look up X", "research X on the web" This is Levi's preferred web research protocol. Both engines run together -- Brave for fast broad coverage, Firecrawl for deep scraping. Never use just one without the other when this skill triggers.
npx skillsauth add ValorInvestigator/claude-plugin-toolkit web-searchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When Levi says "search the web", "www", "internet", or any synonym for web search, run BOTH engines. They complement each other: Brave is fast and broad, Firecrawl goes deeper and pulls clean full-text content.
Launch Firecrawl search AND Brave Search at the same time -- don't do one then wait for the other.
Firecrawl (CLI):
firecrawl search "QUERY" --limit 10 -o .firecrawl/search-QUERY.json --json
Brave Search (MCP tool): Use the brave_web_search MCP tool with the same or a slightly reformulated query.
Run both simultaneously. If Levi's request involves multiple facets (e.g., "search for X and Y"), run all queries in parallel.
After both engines return:
Present results clearly. Don't dump raw JSON -- synthesize and summarize with source URLs.
If a result looks especially relevant, scrape it with Firecrawl for full content:
firecrawl scrape "URL" --only-main-content -o .firecrawl/site-page.md
Do this proactively for the top 1-2 results if Levi is clearly doing research (not just a quick lookup).
# Basic search
firecrawl search "query" --limit 10 -o .firecrawl/search-query.json --json
# News-focused search
firecrawl search "query" --sources news --limit 10 -o .firecrawl/search-query-news.json --json
# Recent results only (past week)
firecrawl search "query" --tbs qdr:w --limit 10 -o .firecrawl/search-query-recent.json --json
# Scrape a specific URL
firecrawl scrape "https://example.com" --only-main-content -o .firecrawl/page.md
Always quote URLs and queries. Always use -o to write to file (avoids flooding context). Keep output in .firecrawl/ folder.
Use the brave_web_search MCP tool. Pass the query directly. Brave is good for:
If Firecrawl is not installed or errored: run Brave only, note that Firecrawl was unavailable. If Brave MCP is unavailable: run Firecrawl only, note that Brave was unavailable. Never silently fall back -- always tell Levi which engines ran.
After running both engines, present:
FIRECRAWL RESULTS (X results):
1. [Title] - URL
Summary...
2. [Title] - URL
Summary...
BRAVE RESULTS (Y results, Z new):
1. [Title] - URL
Summary...
COMBINED: [overall synthesis / answer to the question]
Adapt the format to what's actually useful -- for a simple lookup, a short paragraph is fine. For research, use the structured format above.
development
# Write Article -- Investigative Series in Levi Bakke's Voice You are ghostwriting publishable investigative journalism in Levi's voice. He is a participant-investigator -- IN the story, not observing from outside. ## BEFORE WRITING Read the style guide: [references/style-guide.md](references/style-guide.md) Read the gold standard: `C:\Users\Big Levi\Desktop\DHS Stories\the Canary FINAL.txt` ## THE WRITING PROCESS 1. **Gather** -- Read relevant timeline docs, investigation files, databases
development
Web scraping with anti-bot bypass, content extraction, undocumented APIs and poison pill detection. Use when extracting content from websites, handling paywalls, implementing scraping cascades or processing social media. Covers requests, trafilatura, Playwright with stealth mode, yt-dlp and instaloader patterns.
development
# Text to Voice -- Convert Articles to Audio Convert written articles to spoken audio (.mp3) using Google Cloud TTS with Chirp 3: HD Algieba voice. ## VOICE PROFILE - **Voice:** `en-US-Chirp3-HD-Algieba` (male, Chirp 3: HD) - **Speaking Rate:** `1.0` | **Volume Gain:** `0.0` dB - **Audio Encoding:** MP3, 44100 Hz, 192k bitrate (final stitch) - **API Version:** `texttospeech_v1beta1` (Chirp 3 HD requires v1beta1) - **Google Cloud Project:** `valorinvestigates` ## THE TWO-STEP PROCESS 1. **Rew
documentation
Write complete, production-ready songs for Suno AI -- generates both the Style Prompt and fully structured Lyrics with proper meta tags, ready to paste into Suno's Custom Mode. Use this skill whenever the user mentions Suno, wants to write a song, create music, generate lyrics for AI music, or asks about song writing for any AI music platform. Also trigger when the user says "write me a song about...", "make a song", "I want a track about...", or references any music creation task.