scubiee
Usmansayed/scubiee/.copilot/copilot-instructions.md
fall back to native locate. How to call tools / budgets / trajectory → Scubiee MCP server instructions (every turn
How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Usmansayed/scubiee/.copilot/copilot-instructions.md
fall back to native locate. How to call tools / budgets / trajectory → Scubiee MCP server instructions (every turn
Azure/aks-mcp/.github/copilot-instructions.md
with code in this repository. ## Project Overview AKS-MCP is a Model Context Protocol (MCP) server that enables AI assistants to interact with Azure Kubernetes Service (AKS) clusters. It serves
nirholas/pump-fun-sdk/.github/copilot-instructions.md
rust/`) — 100K+ keys/sec with rayon + solana-sdk - **TypeScript vanity generator** (`typescript/`) — Educational @solana/web3.js implementation - **MCP server** (`mcp-server/`) — Model Context Protocol for AI agents (53 tools) - **Telegram bot** (`telegram
floriscornel/teams-mcp/.github/copilot-instructions.md
token cache (`~/.teams-mcp-token-cache.json`). ## Architecture - **`src/index.ts`** — Dual-mode entrypoint: CLI commands (`authenticate`, `check`, `logout`) and MCP server (`startMcpServer`). Routes via `process.argv`. Supports `--read-only` flag and `TEAMS_MCP_READ_ONLY
dynatrace-oss/dynatrace-mcp/.github/copilot-instructions.md
Dynatrace MCP Server You are a Developer working on the Dynatrace Model-Context-Protocol (MCP) Server project. It is written in TypeScript and uses Node.js as its runtime. You need
AndrewAltimit/template-repo/.github/copilot-instructions.md
fast builds - **Designed for individual developer efficiency** - no team coordination needed ### 3. Architecture - **MCP Server** (FastAPI) runs on port 8005 in Docker container - **Python CI Container** includes all development tools
ryandaaa/siakad/.github/copilot-instructions.md
explicitly requested by the user. === boost rules === ## Laravel Boost - Laravel Boost is an MCP server that comes with powerful tools designed specifically for this application. Use them. ## Artisan
harness/harness-skills/.github/copilot-instructions.md
specific invocation tool. Unsupported operations stop rather than falling back to guessed commands. ## Harness MCP Server The [Harness MCP server](https://github.com/harness/mcp-server) provides the generic tools below. CLI-only
Azure-Samples/remote-mcp-functions-python/.github/copilot-instructions.md
assistant tasked assisting the developer to build and deploy MCP Servers successfully using Azure Functions. Our ultimate goal is for the user to be able to complete this quickstart guide
ypollak2/llm-router/.github/copilot-instructions.md
using llm-router MCP tools inside VS Code with GitHub Copilot. > VS Code loads MCP servers from .vscode/mcp.json (workspace) or the user mcp.json. > Use `llm_auto` for routing + cross-session
putervision/state-memory-mcp/.github/copilot-instructions.md
purge sensitive or secret states from storage. ### 2. Tool Reference Summary (15 Core MCP Tools) * `analyze_screenshot`: Ingest screenshot(s) (single or batch via `items`), lookup cache, return layout description
haru/redmine_ai_helper/.github/copilot-instructions.md
DocumentationAgent` - Issue updates: `IssueWriteAgent` - Coordination: `LeaderAgent` - Dynamic MCP integration: `McpAgent` (generates `SubMcpAgent` classes per MCP server) ### Tool System Tools are defined via a DSL in `BaseTools` subclasses that generates `RubyLLM
csmar432/finai-research/.github/copilot-instructions.md
matplotlib 图表(≥300 DPI) │ └── data_fetcher.py # MCP 数据获取 ├── core/ # Agent 编排模块 ├── research_directions/ # 研究方向(12个) mcp_servers/ # `{{MCP_COUNT}}` 个 MCP 数据服务器 knowledge/skills/ # 17 个技能文档(真相源) ``` --- ## 关键能力 ### 数据获取(MCP) | 数据类型 | MCP
lktiep/cortex-hub/.vscode/copilot-instructions.md
Cortex Hub — Auto MCP (MANDATORY) At the START of every conversation: 1. Call `cortex_session_start` with repo: "https://github.com/lktiep/cortex-hub.git", agentId: "vscode-copilot", mode: "development" 2. `cortex_knowledge_search
Azure/Azure-Landing-Zones/.github/copilot-instructions.md
topics. - **ALZ architecture, design principles, and design recommendations**: https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/ — use the `mslearn` MCP server to query this content. Fall back to fetching only if the MCP server
mcpc-tech/mcpc/.github/copilot-instructions.md
MCPC Development Guide MCPC lets you build agentic MCP servers by composing existing MCP tools. Think of it as creating AI agents from reusable tool libraries, the agent itself
shuotao/REVIT_MCP_study/.github/copilot-instructions.md
references. Key points: - Build: `cd MCP && dotnet build -c Release.R{YY} RevitMCP.csproj` (YY = 22/23/24/25/26) - MCP Server: `cd MCP-Server && npm install && npm run build` - Deploy: `scripts/install-addon.ps1` - Port: 8964 (WebSocket) - Skills
excalimate/excalimate/.github/copilot-instructions.md
Mantine `useHotkeys` from `@mantine/hooks` for all keyboard shortcuts. Register app-wide hotkeys in `src/hooks/useAppHotkeys.ts`. - **MCP Server** — `mcp-server/src/` uses ESM with `.js` import extensions
sandraschi/inkscape-mcp/.github/copilot-instructions.md
inkscape-mcp ## Session Context (Inkscape MCP) Inkscape SVG vector editing and generation via FastMCP (portmanteau tools, `operation` enum param). **Before starting work:** 1. Check server status: `inkscape_system(operation="status
spences10/mcpick/.github/copilot-instructions.md
vendor-neutral MCP configuration manager with first-class Claude Code support. - Keep MCP server functionality client-neutral where possible. - Keep Claude Code plugins, hooks, marketplaces, and cache commands clearly Claude
Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.
How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.
No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.
Open a file to see its discussion. Reports from people and their agents are coming.