Web Search & Investigation
Protocols for thorough web searching and deep investigation.
Skill by TACH04
Chalk Labs
Need help deploying Web Search & Investigation?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tach04-web-search-investigation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/web-search-investigation
What's inside
- Skill name
Web Search & Investigation- Description
- Protocols for thorough web searching and deep investigation. Use for factual lookups, deep dives, and comprehensive research tasks.
- License
- MIT
- Instructions
- 40 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Web Search & Investigation" does not match folder "web_search"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Web Search & Investigation Skill This skill provides a rigorous protocol for gathering and verifying information from the web. Follow these guidelines to ensure your answers are accurate, up-to-date, and comprehensive. ## Tool Hierarchy You have three main tools for investigation. Choose based on the complexity of the task: 1. **`search_web`**: Use for quick facts, current news headlines, or finding specific URLs. 2. **`scrape_url`**: Use when you have a specific, relevant source (e.g., a documentation page, a deep-dive article) that you need to read in its entirety to extract detailed information. 3. **`deep_research`**: Use for complex questions that require synthesizing data from multiple sources, broad exploration of a topic, or when the user explicitly asks for a "comprehensive report". ## The Investigation Protocol ### 1. Be Thorough (The Multi-Query Strategy) Never rely on a single search query if the topic has any complexity. - If the first query doesn't yield definitive results, **rephrase and try again**. - Use "search operators" if needed (though plain queries usually work well). - If one source seems biased or incomplete, search for a second opinion. ### 2. Follow the Trail (Deep Reading) `search_web` only gives you snippets. - If a snippet looks promising but doesn't have the full answer, **use `scrape_url`** to read the full content of that page. - Do not guess or hallucinate details that are missing from snippets. ### 3. Synthesis and Quality - Cross-reference facts between different sources. - Check the "freshness" of the information (especially for technology or news). - If you find conflicting information, present both views or look for a tie-breaking source. ## When to use Simple vs Deep Research - **Simple Search (`search_web`)**: "What time is the game tonight?", "Who is the CEO of Apple?", "Current price of Bitcoin". - **Deep Research sub-agent (`deep_research`)**: "Compare the pros and cons of three different LLM providers", "Research the historical development of the Renaissance in Italy", "Give me a comprehensive report on the current state of fusion energy". ## Reporting to the User - Always cite your findings if possible (e.g., "According to [Source Name]..."). - If you can't find an answer after thorough searching, be honest about it. Do not invent facts.
From TACH04/BrolympusBot, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 9, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TACH04/BrolympusBot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TACH04
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Web Search & Investigation running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Web Search & Investigation skill. Agent Mart. https://agentmart.dev/skills/tach04-web-search-investigation (last updated 2026-10-24)