agent-webFetch any public web page and get back clean, LLM-ready markdown (polite, robots-respecting)
Install via ClawdBot CLI:
clawdbot install foomworks/agent-webGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://agent-web.foomworks.workers.devAudited Oct 7, 2026 · audit v1.0
Generated Oct 7, 2026
A journalist or analyst needs to quickly digest a long-form article from a news site or blog. They paste the URL into an AI agent that uses this skill to pull clean markdown and generate a summary. The agent can then answer follow-up questions or extract key facts without the user touching raw HTML.
A developer wants an LLM to answer questions about a specific library's docs page or changelog. The skill fetches the page, converts it to markdown, and feeds it into the agent's context. This enables accurate, source-grounded answers about APIs, configuration, or migration steps.
A product manager tracks competitor pricing pages, feature announcements, or blog posts. An agent periodically fetches these public pages and converts them to markdown for comparison and summarization. The polite-reader guarantees keep the scraping compliant and low-impact.
A researcher finds a publicly accessible paper or policy report online and wants an AI assistant to extract methodology, findings, or citations. The skill turns the page into structured markdown, making it easy to query, quote, and cross-reference within the agent workflow.
A support agent or chatbot needs to read a public help-center article to answer a user's question accurately. The skill fetches the article as markdown, letting the agent summarize steps or troubleshoot issues without hallucinating details from memory.
Offer the core read_url and preview endpoints for free up to a daily request limit, then charge for higher throughput, priority queues, and JavaScript-rendered page support. The service holds no keys and has low marginal cost per static fetch, making a generous free tier viable.
Position the service as a native MCP server that agent platforms and frameworks integrate directly. Charge platform vendors for verified integration, dedicated endpoints, or white-label markdown extraction within their agent marketplaces.
Bundle the markdown extraction service into existing developer tools like note-taking apps, research assistants, or low-code workflow builders via a paid API key. Developers pay for convenience and compliance without building their own robots-respecting scraper.
💬 Integration Tip
Use the MCP endpoint for native agent integration, or call the REST /read endpoint with a simple curl or HTTP client for quick prototypes; always check /policy and robots-respecting behavior before fetching URLs in production.
Scored Oct 7, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...