Skillify
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Skillify convert https://www.grammarly.com to a SKILL.md file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Skillify
Turn a public website into one portable SKILL.md through MCP.
Run
Set a Firecrawl API key, then configure your MCP client to start:
npx -y @devinat1/skillifywith this environment variable:
FIRECRAWL_API_KEY=fc-your-keyThe server uses local stdio transport. A generic MCP configuration looks like:
{
"command": "npx",
"args": ["-y", "@devinat1/skillify"],
"env": {
"FIRECRAWL_API_KEY": "fc-your-key"
}
}Related MCP server: site-kg
Tool
skillify accepts exactly one argument:
{
"url": "https://www.grammarly.com"
}It returns:
{
"skill_markdown": "---\nname: ...\ndescription: ...\n---\n...",
"next_action_instruction": "Show the generated skill to the user, then ask whether they want to save, revise, or discard it."
}Skillify first asks Firecrawl Agent to inspect the site's public pages and produce a self-contained skill compatible with Codex and Claude Code. If the adaptive crawl does not finish quickly, it switches to Firecrawl's structured scrape. Calls return within 30 seconds; if Firecrawl is unavailable, Skillify returns a best-effort skill inferred from the URL.
Only public HTTP(S) URLs are accepted. Localhost, private-network addresses, non-HTTP URLs, and URLs containing credentials are rejected.
Develop
Requires Node.js 22.14 or newer.
npm install
npm test
npm run typecheckLicense
MIT
Available Tools
1 toolskillifyA
Turn a public website into one portable Codex and Claude Code skill.
Inputs: url (required). Returns: skill_markdown, next_action_instruction
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of overlap or confusion between tool purposes. An agent cannot mis-select because the entire server exposes exactly one operation.
There is no pattern conflict with a single tool. 'skillify' is a clear, action-oriented name that accurately signals the server's sole function, so consistency is effectively perfect.
One tool is a borderline count and gives the agent no supporting operations such as validation, listing generated skills, or configuration. However, the server appears intentionally scoped to a single conversion action, so it is not an extreme mismatch.
Within the stated domain of turning a public website into a portable skill, the single tool covers the complete workflow end-to-end. There are no obvious missing operations implied by the server's purpose.
Maintenance
Related MCP Connectors
Turn any public website into an MCP server for agents to search, read and navigate.
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web scraping / crawling / search…
Scrape, crawl, and search the web via Firecrawl’s official hosted MCP.
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- FlicenseBqualityBmaintenanceEnables MCP-compatible AI clients to extract live web content and convert it into structured Markdown for LLM ingestion, RAG pipelines, and agentic workflows.16-
- AlicenseBqualityBmaintenanceTurns any website URL into a crawled markdown corpus and knowledge graph, then exposes it to AI agents over MCP. Enables full-text search, full page retrieval, subgraph neighbor expansion, and site statistics so agents can answer questions grounded in a specific site's documentation.10MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to fetch webpages and crawl sites, extract main content, and convert it into clean Markdown with preserved links for fast, token-efficient scraping.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to fetch web pages or crawl sites and convert them into clean, token-efficient Markdown while preserving links.MIT