Crw Dynamic Search

Programmatic web search and scrape with context isolation. Use for any research task where you need to search the web, filter results, and extract specific information — without flooding your context window with raw HTML and boilerplate. This is the single biggest token-saver in the crw skill set. 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 any task where you suspect the raw output will be large (multi-page scrapes, news aggregatio

1,268 stars 102 forksData & Analytics Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add fastcrw/crw

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add fastcrw/crw --skill crw-dynamic-search
Manual install
git clone --depth 1 https://github.com/fastcrw/crw.git /tmp/crw
mkdir -p ~/.claude/skills
cp -r /tmp/crw/skills/crw-dynamic-search ~/.claude/skills/crw-dynamic-search

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# crw-dynamic-search — Programmatic Tool Calling for Web Research

Search the web and scrape pages so that **raw web data never enters your context
window**. Only your curated `print()` output comes back — pure signal, no noise.

## Why this matters

A typical `crw search --json` returns 10 results × 300-600 chars of description
each = ~5K characters. That sounds manageable — until you add `scrapeOptions` to
fetch full page markdown, which can be 20-50K chars per result. **A 10-result
search with full content ≈ 200-500K characters.** If that floods your context, you
burn tokens reading cookie banners, navigation menus, and boilerplate — and your
reasoning quality degrades under the noise.

By processing results inside a Python subprocess, only your `print()` output enters
context — typically **1-3K characters of pure signal.** That's a 100-200x reduction.

## Background: the PTC sandbox pattern

[Anthropic's Programmatic Tool Calling](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/programmatic-tool-calling)
lets a model write code that orchestrates tool calls inside a sandbox. Intermediate
results live in the sandbox; only `print()` output crosses into the context window.

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

## Core Rule
Read the full skill on GitHub

Details

Skill name
crw-dynamic-search
Repository
fastcrw/crw
Path
skills/crw-dynamic-search/SKILL.md
License
AGPL-3.0
Repo updated
18 November 2026

FAQ

What does the Crw Dynamic Search skill do?

Programmatic web search and scrape with context isolation. Use for any research task where you need to search the web, filter results, and extract specific information — without flooding your context window with raw HTML and boilerplate. This is the single biggest token-saver in the crw skill set. 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 any task where you suspect the raw output will be large (multi-page scrapes, news aggregatio

How do I install the Crw Dynamic Search skill?

Claude Code plugin: /plugin marketplace add fastcrw/crw. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Crw Dynamic Search popular?

It lives in fastcrw/crw, which has 1,268 GitHub stars and 102 forks, and is included in 1 curated skill list.

Related skills

Crw

1.3k

fastcrw/crw

Scrape, crawl, map, and search the web using fastCRW's native /v1 API. Use when the user needs web page content, site-wide extraction, URL discovery, or web search results. Single binary, 14 MB RAM; /v2 exists separately for Firecrawl migration.

Writing & ContentIn 1 list102

Crw

1.3k

fastcrw/crw

Scrape, crawl, map, search, parse, and extract web data with fastCRW — the open-source, self-hostable Firecrawl alternative (single Rust binary, ~14 MB RAM, Firecrawl-compatible /v1 + /v2 API). Use whenever the user needs page content, site-wide extraction, URL discovery, web search, PDF parsing, structured JSON from pages, or change tracking. Also use when the user mentions Firecrawl, Tavily, Crawl4AI, or "scrape/crawl/map/fetch/get the page/read this site/search the web" — crw is a drop-in for the Firecrawl SDKs.

Data & AnalyticsIn 1 list102

Crw Best Practices

1.3k

fastcrw/crw

Reference skill for building production-ready crw integrations. Covers verb selection, call surfaces (CLI/MCP/REST), post-filtering strategies, context-window hygiene, Hybrid RAG patterns, common pitfalls, and crw-specific operational considerations (search backend limits, renderer pool, proxy rotation). Load this when writing application code that embeds crw, designing a multi-step agent workflow, or debugging an integration that isn't behaving as expected.

AI, LLMs & AgentsIn 1 list102

Crw Map

1.3k

fastcrw/crw

Discover all URLs on a website without fetching content — fast, low-cost URL inventory via sitemap.xml + link extraction BFS. Use when you need to know which pages exist before deciding what to scrape or crawl: "list all pages", "find URLs on this site", "discover links", "what pages does this site have", "map the site". Step 3 of the crw workflow ladder.

Data & AnalyticsIn 1 list102

Crw Crawl

1.3k

fastcrw/crw

Crawl an entire website or section and extract content from every page. Use when you need content from many pages under a common URL prefix: "crawl the whole site", "get all docs pages", "scrape every blog post", "download the full docs for RAG", "extract all pages under /api". Async BFS — starts a job and polls for results. Step 4 of the crw workflow ladder.

Data & AnalyticsIn 1 list102

Crw Scrape

1.3k

fastcrw/crw

Scrape a single known URL into clean markdown / HTML / links / structured JSON with fastCRW. Use when you already have the URL and want the page content — "scrape", "grab", "fetch", "pull", "read this page", "get the content of". Handles JavaScript-rendered SPAs automatically. Step 2 of the crw workflow ladder.

Data & AnalyticsIn 1 list102

Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.