copilot-collections  by TheSoftwareHouse

AI-powered toolchain for end-to-end product engineering

Created 4 months ago
253 stars

Top 99.3% on SourcePulse

GitHubView on GitHub
Project Summary

This repository offers opinionated, AI-enabled workflows for product engineering, designed to cover the entire development lifecycle from ideation through development to quality assurance. It provides a unified toolchain for teams using GitHub Copilot, VS Code, Jira, and Figma, aiming to streamline AI-assisted product development.

How It Works

The project structures AI-powered agents, skills, and workflows across three core phases: Product Ideation, Development, and Quality. A fourth track focuses on Copilot customization, enabling users to create their own agents, skills, prompts, and instructions. It heavily integrates with various MCP (Meta-Cognitive Process) servers, including Atlassian, Figma Dev Mode, Playwright, and Context7, to provide context-aware AI assistance. All custom artifacts use a tsh- prefix to avoid naming collisions with user-defined customizations.

Quick Start & Requirements

  • Primary install: Clone the repository (git clone <repo-url> copilot-collections).
  • Prerequisites: GitHub Copilot Pro license (or higher) is required for custom agents and MCP integrations. VS Code version 1.109 or later is necessary.
  • Setup: Configure VS Code User Settings (JSON) to point to the .github/prompts, .github/agents, and .github/skills directories within the cloned repository. Configure MCP servers by copying .vscode/mcp.json to your user profile or workspace.
  • Documentation: Official documentation links are not explicitly provided but can be inferred from the MCP server names.

Highlighted Details

  • Supports the full product development lifecycle: Product Ideation, Development, and Quality.
  • Integrates with Atlassian (Jira), Figma Dev Mode, Playwright, and Context7 MCPs for enhanced workflow capabilities.
  • Includes a dedicated track for creating and managing custom Copilot agents, skills, prompts, and instructions.
  • Utilizes a tsh- prefix for all provided artifacts to ensure namespace isolation.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or roadmap are present in the provided README.

Licensing & Compatibility

Licensed under the MIT License, which is permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

A GitHub Copilot Pro license or higher is a strict requirement for utilizing custom agents and MCP integrations. VS Code version 1.109 or later is also mandatory. Full workflow capabilities depend on the correct configuration of the various MCP servers.

Health Check
Last Commit

22 hours ago

Responsiveness

Inactive

Pull Requests (30d)
5
Issues (30d)
0
Star History
36 stars in the last 30 days

Explore Similar Projects

Starred by Peter Norvig Peter Norvig(Author of "Artificial Intelligence: A Modern Approach"; Research Director at Google).

codev by cluesmith

1.1%
273
AI-powered OS for human-agent software co-development
Created 8 months ago
Updated 12 hours ago
Feedback? Help us improve.