Test

Created By
treea year ago
Overview

What is the Project?

This project is a comprehensive collection of system prompts, tools, and AI models, including insights into their structure and functionality. It features over 6,500 lines of extracted prompts from various AI tools such as Manus, Cursor, and Replit Agent.

How to Use the Project?

Users can explore the available files and folders containing system prompts and tools. For feedback and roadmap suggestions, users are directed to the dedicated feedback platform.

Key Features of the Project?

  • Extensive collection of AI system prompts and tools.
  • Security notice for AI startups to protect their data.
  • Roadmap and feedback system for user suggestions.

Use Cases of the Project?

  1. AI startups can utilize the prompts for developing their models.
  2. Researchers can analyze the structure of AI prompts for academic purposes.
  3. Developers can integrate these prompts into their applications for enhanced functionality.

FAQ from the Project?

  • What types of prompts are included?

The project includes prompts from various AI tools like Manus, Cursor, and Replit Agent.

  • Is there a security notice for AI startups?

Yes, there is a security notice advising startups to secure their data against potential leaks.

  • How can I support the project?

You can support the project through PayPal or cryptocurrency contributions.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
tree
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago