# Spark by Entire VC

> Spark is an open-source marketplace and workflow library for AI-native builders. Curated collection of Claude Skills, AI agents, prompt templates, prompt chains, and MCP (Model Context Protocol) servers — free to download and ready to install in Claude Code, Cursor, Codex, Gemini CLI and other AI tools.

## What is Spark

Spark is a free catalog at https://spark.entire.vc that aggregates AI-native workflow assets from open-source repositories and the community. Every asset is reviewed for quality and properly attributed back to its original author. Users can search, download, copy, and install assets directly into their AI coding tools.

The MCP server `evc-spark-mcp` lets AI assistants search and install assets programmatically:

```
npx evc-spark-mcp
claude mcp add spark -- npx -y evc-spark-mcp
```

## Asset types

- **Claude Skills** (`/skills`) — reusable AI capabilities packaged as `SKILL.md` files. Extend agent functionality with domain-specific knowledge, methodologies, and tool usage patterns. Compatible with Claude Code, Cursor, OpenClaw.
- **AI Agents** (`/agents`) — pre-configured autonomous agents for specific tasks. Examples: code reviewers, security auditors, technical writers, SEO specialists.
- **Prompt Templates** (`/prompts`) — tested prompts for common AI workflows. Carefully crafted, free, organized by use case.
- **Prompt Chains** (`/prompt-chains`) — multi-step prompt sequences for complex workflows.
- **MCP Servers** (`/mcps`) — Model Context Protocol server packages that connect Claude/Cursor/etc. to external services (databases, APIs, file systems, third-party tools).
- **Bundles** (`/bundles`) — curated collections combining skills, agents, prompts and MCPs for end-to-end workflows.

## Catalog structure

- Catalog index: https://spark.entire.vc/catalog
- Skills: https://spark.entire.vc/skills (Claude Skills Marketplace)
- Agents: https://spark.entire.vc/agents
- MCPs: https://spark.entire.vc/mcps
- Prompts: https://spark.entire.vc/prompts
- Prompt chains: https://spark.entire.vc/prompt-chains
- Bundles: https://spark.entire.vc/bundles

Every asset has a canonical detail page at `/{type}/{slug}` (e.g. `/skills/vb-seo-expert`, `/mcps/spark-mcp-server`) with a `SoftwareApplication` JSON-LD schema, install instructions, and a one-click download.

## Install endpoints (CLI-friendly, public)

- `https://spark.entire.vc/get/{slug}` — bash install script (curl | bash)
- `https://spark.entire.vc/raw/{slug}` — raw asset content (markdown)

These are public for convenience and intentionally do not require auth for free assets.

## Sitemaps

- Index: https://spark.entire.vc/sitemap.xml
- Static pages: https://spark.entire.vc/sitemap-static.xml
- Asset pages (paginated, 10k each): https://spark.entire.vc/sitemap-assets-1.xml

## Sources

Spark imports and curates assets from open-source repositories with proper attribution:
- VibeBaza, MCP Servers directory, PromptFlow, LlamaIndex, CrewAI, Promptfoo, Instructor, OpenAI Cookbook, CAMEL, LangGraph, Semantic Kernel, Antigravity, NeuralDeep, Publora and more.
- Original authors can claim their assets via GitHub OAuth at `/claim/{slug}`.

## Compatibility

Spark assets work with: Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, ChatGPT (via MCP bridge), Anthropic API, OpenAI API.

## License & attribution

Most assets are CC-BY-4.0 or MIT. Each asset page lists its original source URL and license. Authors retain full credit.

## Contact

- Site: https://spark.entire.vc
- Parent organization: https://entire.vc (Entire VC)
- MCP server (npm): https://www.npmjs.com/package/evc-spark-mcp
- MCP server source: https://github.com/entire-vc/evc-spark-mcp