SkillPress
Compiles websites, docs, and repositories into agent-ready SKILL.md packages for AI coding agents.
README
SkillPress
Compile websites, docs, and repositories into agent-ready skill packs.
SkillPress turns scattered source material into a clean SKILL.md package with references, source maps, and a maintenance trail. It is built for people who want Claude, Codex, Cursor, and other coding agents to understand a project, product, API, policy, or knowledge base without pasting the same context again and again.
pip install skillpress
skillpress build https://example.com/docs ./README.md \
--name "Example Docs" \
--description "Use when a user asks about Example's public documentation."
Or expose it to an MCP-compatible agent client:
{
"mcpServers": {
"skillpress": {
"command": "skillpress",
"args": ["mcp"]
}
}
}
Output:
skillpress-output/
example-docs/
SKILL.md
skillpress.json
references/
source-notes.md
sources.json
Why It Exists
AI agents are powerful, but they still waste time when knowledge is trapped in long docs, scattered repository files, PDFs, internal notes, or web pages. SkillPress gives that material a portable shape:
SKILL.mdfor agent instructions.references/source-notes.mdfor readable context.references/sources.jsonfor traceability.skillpress.jsonfor regeneration and maintenance.
It is not a web-scraping bypass tool. It is a public-source and local-document compiler for responsible agent workflows.
Features
- Build a skill from URLs, files, or folders.
- Scan common text/code formats from repositories.
- Extract readable text from HTML with no heavy dependencies.
- Generate source-grounded references for agent answers.
- Validate a skill pack before sharing it.
- Zip a skill pack for release or installation.
- Run a stdio MCP server for agent clients.
- Works with Python standard library only.
Commands
Create a skill from public docs and local files:
skillpress build https://example.com/docs ./docs \
--name "Example Product" \
--description "Use when answering questions about Example Product."
Create an empty skeleton:
skillpress new "Support Playbook" \
--description "Use when drafting support replies from the team playbook."
Inspect a skill:
skillpress inspect skillpress-output/example-product
skillpress inspect skillpress-output/example-product --json
Package a skill:
skillpress pack skillpress-output/example-product
Run the MCP server:
skillpress mcp
Use Cases
- Turn a GitHub repository into an onboarding skill.
- Turn product docs into a support-agent skill.
- Turn an API reference into a coding-agent skill.
- Turn research notes into a repeatable analysis skill.
- Turn a public website into a compact knowledge pack.
Design Goals
- Portable: the output is just files.
- Transparent: sources are traceable.
- Local-first: no account or hosted service required.
- Agent-friendly: instructions are written for tools that can read
SKILL.md. - Responsible: built for authorized local files and public documentation.
Roadmap
- PDF and DOCX source support.
- Better source ranking and deduplication.
- Browser-rendered page capture for JavaScript-heavy documentation.
- Remote MCP transport for hosted deployments.
- Skill templates for support, API docs, repo onboarding, and research briefs.
- Gallery of high-quality example skill packs.
Documentation
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.