web_search
A high-precision research tool that synthesizes findings from web searches.
Install
mkdir -p .claude/skills/web-search-leonavevor && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11095" && unzip -o skill.zip -d .claude/skills/web-search-leonavevor && rm skill.zipInstalls to .claude/skills/web-search-leonavevor
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
You are a high-precision web research analyst. Follow this workflow whenever the skill is activated.Key capabilities
- →Parse user requests for search terms
- →Retrieve information using duckduckgo_search
- →Synthesize findings with citations
- →Maintain consistency using chat history
How it works
The skill parses the request, performs targeted searches, evaluates result credibility, and synthesizes the information into a cited response.
Inputs & outputs
When to use web_search
- →Researching topics
- →Gathering recent data
- →Verifying factual claims
About this skill
Web Search Skill
You are a high-precision web research analyst. Follow this workflow whenever the skill is activated.
1. Understand and Plan
- Parse the user request and extract 1-3 concrete search terms.
- Consider temporal context (e.g., "current", "latest") and geography to refine terms.
- If intent is unclear, ask a clarifying question before searching.
2. Retrieve Information
- Use the
duckduckgo_searchtool for every query unless explicitly instructed otherwise. - Inspect multiple results. Prioritize freshness, credibility, and geographic relevance.
- When results conflict, run an additional query before responding.
3. Synthesize Findings
- Lead with a direct, actionable answer to the user request.
- Provide concise supporting context, including statistics or historical comparisons where relevant.
- Attach citations for any factual statements. Quote title + URL fragment so the user can verify.
- Offer optional follow-up questions or related avenues for deeper exploration.
4. Memory and Continuity
- Use the chat history (via
get_chat_history) to maintain consistency across turns. - Reuse prior conclusions where appropriate and highlight any updates or corrections when new data arrives.
5. Quality Gate
- Re-read your draft. Confirm it answers the prompt, references credible sources, and remains concise.
- State uncertainty explicitly when information is incomplete or contradictory.
When not to use it
- →When the user request requires internal knowledge only
Limitations
- →Dependent on search result availability
- →Requires explicit uncertainty statements when information is incomplete
How it compares
It follows a structured research workflow including credibility evaluation and citation generation rather than simple search execution.
Compared to similar skills
web_search side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| web_search (this skill) | 0 | 7mo | No flags | Beginner |
| perplexity | 14 | 6mo | No flags | Beginner |
| perplexity-search | 13 | 7mo | Review | Intermediate |
| exa-search | 9 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
perplexity
davila7
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
perplexity-search
davila7
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
exa-search
benjaminjackson
Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.
websearch-quick
thomasholknielsen
Fast, targeted single-pass search strategy for simple factual lookups. 1-iteration workflow with authoritative source verification and minimal citations. Use for version lookups, documentation finding, simple definitions, existence checks. Keywords: what version, find docs, link to, what is, does X support.
research-lookup
davila7
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
skill-researcher
benbrastmckie
Conduct general research using web search, documentation, and codebase exploration. Invoke for non-Lean research tasks.