Skip to main content
Glama
devinat1

Skillify

by devinat1
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

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/skillify

with this environment variable:

FIRECRAWL_API_KEY=fc-your-key

The 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: Crawl4AI MCP

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 typecheck

License

MIT

Available Tools

1 tool
skillifyA

Turn a public website into one portable Codex and Claude Code skill.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesPublic HTTP(S) website URL to turn into a portable skill.

Output Schema

ParametersJSON Schema
NameRequiredDescription
skill_markdownYes
next_action_instructionYes

TDQS

A3.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the transformation outcome and does not disclose network fetching behavior, where the skill is written, whether existing files are overwritten, or any rate/auth limitations. This is a meaningful gap for a tool operating on external URLs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence with no filler. It communicates the operation, the input type, and the output format in minimal space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with a complete schema and an output schema present, the description is largely sufficient for an agent to invoke it correctly. The only notable gap is the lack of operational side-effect disclosure, but the low complexity keeps the overall completeness high.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the URL parameter already described as a 'Public HTTP(S) website URL to turn into a portable skill.' The tool description reinforces the purpose but does not add meaningful detail beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Turn') with a clear resource ('a public website') and a concrete outcome ('one portable Codex and Claude Code skill'). It is immediately obvious what the tool does and it does not rely on the tool name to carry meaning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description establishes the appropriate use case: converting a public website into a portable skill. Since there are no sibling tools and the scope is tightly defined, explicit alternatives and exclusions are less necessary. The 'public' qualifier also implicitly excludes private/internal URLs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count3/5

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.

Completeness5/5

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

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Crawl4AI MCP

    laurentvv
    A
    license
    B
    quality
    A
    maintenance
    Enables AI assistants to crawl websites, extract dynamic content, navigate links, and save structured Markdown files via the MCP protocol, with support for anti-bot bypass, CSS selectors, and custom JavaScript execution.
    1
    41
    MIT

  • icecrawl MCP server

    MrGreenlaw
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables scraping single pages or crawling entire websites, converting content to markdown and optionally extracting structured data with Claude.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/devinat1/skillify'

If you have feedback or need assistance with the MCP directory API, please join our Discord server