Claude Code Agent: Search Specialist

What This Agent Is For

Expert web researcher using advanced search techniques, multi-source synthesis, and iterative retrieval. Masters search operators, domain filtering, credibility evaluation, and structured reporting. Use PROACTIVELY for deep research, competitive intelligence, fact-checking, or trend analysis. Specifically:\n\n\nContext: A product team wants to understand the competitive landscape before launching a new developer tool\nuser: "Research the top five CI/CD tools for monorepos and summarize their pricing, integrations,

Category: AI Specialists. Expected tool surface: WebSearch, WebFetch.

Agent Activation Brief

Use this asset when a task needs a focused specialist for ai specialists work. Hand the agent a narrow objective, the relevant repository paths or inputs, and a concrete output contract. Ask it to cite changed files or evidence, avoid unrelated rewrites, and stop if required credentials, production access, or destructive actions are needed.

Operating Boundaries

• Treat this as a specialist agent, not a general chat prompt.
• Keep write scope explicit before using it in a coding session.
• Run normal project tests or verification after accepting its output.
• Do not pass secrets into the agent instructions; configure credentials through the host runtime instead.

Clean Source

• Source repository: https://github.com/davila7/claude-code-templates
• Source file: https://github.com/davila7/claude-code-templates/blob/main/cli-tool/components/agents/ai-specialists/search-specialist.md
• Source file SHA: f8e5f18f96171ef6fbfbe0bdcc34b5b7f1d2c956
• Upstream body hash: 8b6de342dc51c67ccf6534930e6ae6cea782d85e67ce5676a93903b34eb61524
• License: MIT
• Repository stars at publication check: 27403