agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/web-browsing/skills/web-search/SKILL.md

Web Search

Skill3 starsChanged 5 months agoApache-2.0View on GitHub

Quick web scanning — discover pages, get snippets, find URLs. For orientation only, not substantive analysis.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. kellyvv/PhoneClaw★ 1.3ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when you need to:

    line 23
  2. Distinctive:

    Use whichever web-search MCP is configured — check availability yourself.

    line 34
  3. Distinctive:

    If more than one is active, try them in the order listed below.

    line 35
  4. Distinctive:

    Use specific, targeted keywords

    line 68
  5. Distinctive:

    Consider time filters if the provider supports them

    line 69
  6. Distinctive:

    Consider result count: 5-20 results (default ~10)

    line 70
  7. Distinctive:

    Call the configured provider's search tool with ~10 results per call.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Web Search SOP

Layer Rules

  • Layer: sop — wraps MCP tools directly
  • Called by: Any tactic or strategy requiring quick web orientation
  • Calls: configured web-search MCP tools (never calls other SOPs)

Purpose

Fast orientation search. Understand what pages and sources exist on a topic. Suitable for quick fact-checking, getting an overview of a landscape, or finding URLs for deeper research via web-research.

Use this when you need to:

  • Find what pages exist on a topic
  • Get a rough overview of available information
  • Discover URLs for deeper research (via web-research)
  • Quick fact-check with snippet-level confidence
  • Monitor recent news on a topic

This skill returns snippets only. For full-page content analysis, use web-research.

Provider Selection

Use whichever web-search MCP is configured — check availability yourself. If more than one is active, try them in the order listed below. This order is just the writing order, not a hard priority — any active provider is equally valid.

  • Brave — see Provider Details § Brave
  • Tavily — see Provider Details § Tavily

Set the result count to ~10 per call (provider-specific parameter named in each Provider Details subsection).

HARD-GATE

<HARD-GATE> **Web search returns snippets only (1-3 sentences per result).**

Snippets are NOT authoritative content. They are orientation signals.

PROHIBITED:

  • Drawing substantive conclusions from snippets alone
  • Treating snippet content as verified facts
  • Completing a research task using only search results
  • Presenting snippet summaries as thorough analysis

REQUIRED:

  • Label all results as "snippets for orientation"
  • For any analysis requiring full content, escalate to web-research
  • Make clear to the user that snippets provide direction, not answers</HARD-GATE>

Workflow

Step 1: Formulate Query

  • Use specific, targeted keywords
  • Consider time filters if the provider supports them
  • Consider result count: 5-20 results (default ~10)
  • For news: use news-specific search if available
  • For location-based: use local search if available

Step 2: Execute Search

Call the configured provider's search tool with ~10 results per call. See Provider Details for exact tool name and parameters.

Step 3: Return Structured Results

For each result, present:

  • Title — page title
  • URL — full URL (for reference or escalation to web-research)
  • Snippet — 1-3 sentence description (orientation only, not authoritative)
  • Date — when available (especially for news)

Provider Details

Brave

Available tools:

ToolPurposeReturns
brave_web_searchGeneral web searchURL, title, description snippet
brave_news_searchRecent news articlesURL, title, snippet, date
brave_video_searchVideo content discoveryURL, title, description, duration
brave_image_searchImage searchURL, title, image properties
brave_local_searchLocal businesses/placesName, address, rating, hours
brave_summarizerAI-generated summary (Pro only)Summarized text with references

Key parameters:

  • brave_web_search:
    • query (required): search terms, max 400 chars
    • count: 1-20 results (default 10)
    • offset: pagination, 0-9 (default 0)
    • freshness: pd (24h), pw (7d), pm (31d), py (365d), or YYYY-MM-DDtoYYYY-MM-DD
    • safesearch: off / moderate / strict (default moderate)
    • search_lang: language code (default en)
    • country: 2-letter country code (default US)
    • result_filter: array of types to include (web, news, videos, etc.)
  • brave_news_search: same core parameters, better for time-sensitive queries
  • brave_video_search: returns duration and thumbnail_url
  • brave_image_search: count 1-200 (default 50)
  • brave_local_search: for "near me" queries, returns business details
  • brave_summarizer: requires Pro plan, must first run brave_web_search with summary=true

Examples:

Quick fact check:

brave_web_search(query="Claude 3.5 Sonnet release date", count=5)

News monitoring:

brave_news_search(query="transformer architecture breakthroughs", freshness="pm", count=10)

Landscape scan:

brave_web_search(query="MCP server frameworks comparison 2025", count=15)

Tavily

Available tools:

ToolPurposeReturns
tavily_searchLLM-optimized web searchURL, title, content snippet, score

Key parameters:

  • tavily_search:
    • query (required): search terms
    • max_results: number of results (default 10)
    • search_depth: basic or advanced (default basic)
    • include_domains: restrict to specific domains
    • exclude_domains: exclude specific domains

Examples:

Quick fact check:

tavily_search(query="Claude 3.5 Sonnet release date", max_results=5)

Landscape scan:

tavily_search(query="MCP server frameworks comparison 2025", max_results=10)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free