ClaudeSuperPower
SubmitLog in

tavily-dynamic-search

Skill

Programmatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific information — without polluting your context window with raw HTML and boilerplate. This is the default skill for web research. Triggered by "sea

0Frontend

Install

git clone https://github.com/tavily-ai/skills.git ~/.claude/skills/tavily-dynamic-search

What is tavily-dynamic-search?

Programmatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific information — without polluting your context window with raw HTML and boilerplate. This is the default skill for web research. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or "extract the key details" — any case where the user wants curated, noise-free content.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Run shell commands

Declares Bash

~145 tokens of context used while enabled, before you invoke anything

All declared tools (1)
Bash

Documentation

README · ~9 min read

Tavily Dynamic Search

Search the web, filter results, and extract content so that raw search data never enters your context window. Only your curated print() output comes back.

Why this matters

A typical tvly search --include-raw-content returns 8 results × 30-50K chars each = ~300K characters of raw page content. If this enters your context window, you burn tokens reading navigation bars, cookie banners, and boilerplate — and your reasoning quality degrades under the noise. By processing results inside a Python script, only your print() output enters context — typically 1-3K characters of pure signal. That's a 100-200x reduction.

Background: Programmatic Tool Calling (PTC)

This skill replicates the architecture of Anthropic's Programmatic Tool Calling (PTC) for web search. PTC lets the model write code that orchestrates tool calls inside a sandbox — intermediate results stay in the sandbox, and only the final print() output reaches the model's context window.

This skill applies the same principle using local Python execution. The Python process is the sandbox. Variables in memory hold the raw data. Only what you print() crosses into your context window. You write the filtering logic — you decide what matters for each query.

Before running any command

If tvly is not found on PATH, install it first:

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Subagents

All subagents →

code-architect

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

32.8K stars

claude-security

The dedicated Claude Security orchestrator. Hand it an unattended job — "fully scan this repository and patch what you find; I understand it will use a lot of tokens" — and it runs the whole thing itself: capturing the revision, driving the multi-agent scan through the claude-security:scan workflow,

32.8K stars

plugin-validator

Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Examples: <example> Context: User f

32.8K stars