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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。