do-wdr-cli

name	do-wdr-cli
description	Use the do-wdr (Web Documentation Resolver) CLI binary to resolve URLs and queries into markdown documentation. Use when you need fast command-line access to web documentation resolution, prefer compiled binary over Python, or need to integrate do-wdr into shell scripts and automation.
license	MIT
compatibility	Rust stable, cross-platform Linux/macOS/Windows
allowed-tools	Bash(do-wdr:*) Read
metadata	{"author":"d-oit","version":"0.1.0","source":"https://github.com/d-oit/do-web-doc-resolver/tree/main/cli"}

WDR CLI Skill

Fast compiled Rust CLI for resolving web URLs and queries into markdown documentation.

When to use this skill

Activate this skill when you need to:

• Resolve a URL or query to markdown from the command line
• Integrate documentation resolution into shell scripts
• Get faster performance than the Python implementation
• Use CLI-specific features (metrics, cache stats, provider selection)
• Build automation workflows with do-wdr

Prerequisites

Build the CLI first:

cd cli && cargo build --release
# Binary: cli/target/release/do-wdr

Or ensure do-wdr is in your PATH.

Commands

resolve

Resolve a URL or query to markdown documentation.

do-wdr resolve <INPUT> [OPTIONS]

Arguments:

• <INPUT>: URL or query string to resolve

Options:

• -o, --output <FILE>: Output file (stdout if not specified)
• -p, --provider <PROVIDER>: Specific provider to use
• --skip <PROVIDERS>: Skip providers (comma-separated)
• --providers-order <PROVIDERS>: Custom provider order
• --max-chars <N>: Maximum output characters
• --min-chars <N>: Minimum content length
• --profile <PROFILE>: Execution profile (free, balanced, fast, quality)
• --json: Output as JSON
• --metrics-json: Output metrics as JSON
• --metrics-file <FILE>: Save metrics to file
• --skip-cache: Skip semantic cache
• --synthesize: Synthesize multiple results using AI
• --quality-threshold <F>: Quality threshold for content scoring
• --max-provider-attempts <N>: Maximum provider attempts
• --max-paid-attempts <N>: Maximum paid provider attempts
• --max-total-latency-ms <MS>: Maximum total latency in milliseconds
• --disable-routing-memory: Disable routing memory

providers

List all available providers and their status.

do-wdr providers

config

Show current configuration.

do-wdr config

cache-stats

Show semantic cache statistics.

do-wdr cache-stats

Available Providers

Provider	Type	Free	Description
exa_mcp	Query	Yes	Exa MCP (free, no key)
exa	Query	No	Exa SDK (requires API key)
tavily	Query	No	Tavily comprehensive search
serper	Query	No	Google search via Serper
duckduckgo	Query	Yes	DuckDuckGo search
mistral_websearch	Query	No	Mistral AI search
llms_txt	URL	Yes	llms.txt structured docs
jina	URL	Yes	Jina Reader
firecrawl	URL	No	Firecrawl extraction
direct_fetch	URL	Yes	Direct HTML fetch
mistral_browser	URL	No	Mistral browser agent
docling	URL	No	Docling document processing
ocr	URL	No	OCR text extraction

Execution Profiles

Profile	Description
free	Use only free providers (exa_mcp, duckduckgo, llms_txt, jina, direct_fetch)
balanced	Balance between free and paid providers
fast	Prioritize speed over cost
quality	Prioritize quality over cost

References

Topic	File
Usage examples	references/examples.md
Output formats	references/output-format.md
Configuration	references/configuration.md
Script integration	references/integration.md

Related Skills

• do-web-doc-resolver: Python implementation with same functionality
• agent-browser: Browser automation for complex web interactions