agentleFS
Sign inSign up

Copilot instructions examples

How real projects brief GitHub Copilot, from .github/copilot-instructions.md.

Most stars first · from page 6Worked for most · soon
MicrosoftCopilot instructions

apm / s02b_copilot_instructions

microsoft/apm/tests/integration/fixtures/target_resolution/s02b_copilot_instructions/.github/copilot-instructions.md

No summary in the file. Open it to read it.

3.9k14d agoDiscuss
yvgudeCopilot instructions

lean-ctx

yvgude/lean-ctx/.github/copilot-instructions.md

lean-ctx shadow mode: native read/search/shell calls auto-route to ctx* — no tool-mapping needed. File editing → native Edit/StrReplace (lean-ctx only handles reads); if denied, use ctxpatch. Exclusive tools (no native trigger): ctxcompose (understand code, call first), ctxsearch(action=symbol) (exact symbol), ctxsearch(action=semantic) (by meaning), ctxcallgraph (callers), ctxknowledge / ctxsession (memory). <!-- lean-ctx-compression --> OUTPUT STYLE: expert-terse - Telegraph format: subject-verb-object, drop articles/prepositions - Symbolic vocabulary: → cause, ∵ because, ∴ therefore, ⊕ add, ⊖ remove, Δ change, ≈ similar, ≠ different, ∈…

3.8k2mo agoDiscuss
MicrosoftCopilot instructions

kiota

microsoft/kiota/.github/copilot-instructions.md

This file defines repository-wide defaults for Copilot behavior. It is always applied. When modifying code generation or writer/refiner logic, treat schema-derived values as untrusted and ensure literal-context sanitization at the emission site. Use language/literal-appropriate sanitizers from src/Kiota.Builder/Writers/StringExtensions.cs (and Dart convention helpers where applicable). For writer changes that emit schema-derived text into generated code, ensure hostile content is escaped and covered by regression tests in tests/Kiota.Builder.Tests/Writers/. Before finishing implementation work:

3.8k4mo agoDiscuss
MicrosoftCopilot instructions

mcp

microsoft/mcp/.github/copilot-instructions.md

When reviewing a pull request, use the mcp-code-reviewer skill. In interactive IDE and CLI sessions, return draft findings for human approval before posting them. In GitHub Copilot Code Review, post qualified inline comments directly as a comment-only review. Keep the review read-only: never modify code or the branch, approve or request changes, resolve threads, or invoke an agent to implement changes. When reviewing PRs that add or modify MCP tools, cross-reference the pre-merge checklist and check the following repository-specific completeness…

3.7k29d agoDiscuss
geekjourneyxCopilot instructions

md2wechat-skill

geekjourneyx/md2wechat-skill/.github/copilot-instructions.md

md2wechat is a Go CLI tool that converts Markdown to WeChat Official Account format, with Claude Code and OpenClaw Skill support. make quality-gates runs: format check → go vet →…

3.7k2mo agoDiscuss
MicrosoftCopilot instructions

WinUI-Gallery

microsoft/WinUI-Gallery/.github/copilot-instructions.md

Solution: Open WinUIGallery.slnx in Visual Studio 2022+. Set WinUIGallery as the startup project. Build configurations: Debug, Release, Preview, Stable, Store, Sideload, Debug-Unpackaged. Platforms: x86, x64, ARM64. This is a WinUI 3 / Windows App SDK gallery app that demonstrates controls, styles, and design patterns. It is a companion to the Fluent Design guidelines. Each control demo lives in its own folder under Samples/{UniqueId}/ (e.g., Samples/Button/, Samples/CheckBox/). The folder name must match the control's UniqueId from ControlInfoData.json — this convention is…

3.7k15d agoDiscuss
MicrosoftCopilot instructions

azure-pipelines-tasks

microsoft/azure-pipelines-tasks/.github/copilot-instructions.md

This repository contains the in-the-box tasks for Azure Pipelines and Team Foundation Server. These instructions will help you understand how to build, test, and deploy tasks effectively. This repo provides open examples of how Azure Pipelines tasks are written and can help you write custom tasks for upload to your account or server. Tasks are tool runners that know how to execute tools like MSBuild, VSTest, etc., handle return codes, process stdout/stderr, write timeline records, and access credentials for Azure…

3.7k7mo agoReads credentialsDiscuss
MicrosoftCopilot instructions

DirectXShaderCompiler

microsoft/DirectXShaderCompiler/.github/copilot-instructions.md

When reviewing pull requests in this repository, always check whether docs/ReleaseNotes.md should be updated. Use the release note policy in CONTRIBUTING.md ("Release Notes") as the default: - Release notes are…

3.7k55d agoDiscuss
Microsoft AzureCopilot instructions

bicep

Azure/bicep/.github/copilot-instructions.md

Bicep is a DSL for Azure ARM templates. The compiler pipeline is: Lexer → Parser → Binder → Type Checking / Linting → Emitter (ARM JSON). Key classes: Compilation → SemanticModel → TypeManager, Binder, TemplateEmitter. All use lazy evaluation and caching—the language server recreates state per keystroke, so only compute what's requested. .NET SDK version is pinned in global.json (currently .NET 10). Use VS Code tasks (defined in .vscode/tasks.json) for common operations. Integration test datasets live in src/Bicep.Core.Samples/Files/baselines/. Each dataset…

3.6k7d agoDiscuss
AvdLeeCopilot instructions

SwiftUI-Agent-Skill

AvdLee/SwiftUI-Agent-Skill/.github/copilot-instructions.md

Review changes as an Agent Skills expert, focusing on the Agent Skills open format specification and ensuring this repository stays a SwiftUI-focused, non-architectural, modern-API skill. Level 1: Metadata (always loaded) - YAML frontmatter should be concise and trigger-relevant. Level 2: Instructions (loaded when triggered) - skills/swiftui-expert-skill/SKILL.md body should contain workflows, checklists, decision trees, and quick references. - Avoid turning SKILL.md into an encyclopedia; prefer linking out to references. Level 3: Resources (loaded as needed) - Topic-specific guidance lives in skills/swiftui-expert-skill/references/*.md.…

3.6k54d agoDiscuss
bytebaseCopilot instructions

dbhub

bytebase/dbhub/.github/copilot-instructions.md

This project provides an MCP server (DBHub) for secure SQL access to the development database. AI agents can execute SQL queries. In read-only mode (recommended for production): In read-write mode (development/testing): Use --readonly flag to restrict to read-only operations for safety.

3.6k11d agoDiscuss
MicrosoftCopilot instructions

ebpf-for-windows

microsoft/ebpf-for-windows/.github/copilot-instructions.md

This project brings eBPF (extended Berkeley Packet Filter) to Windows, enabling programmable OS kernel extensions for use cases like network filtering and observability. See docs/GettingStarted.md for prerequisites, build options, and detailed setup. See docs/AutomatedTests.md for test categories and descriptions.

3.6k6mo agoDiscuss
Ar9avCopilot instructions

obsidian-wiki

Ar9av/obsidian-wiki/.github/copilot-instructions.md

This project is a skill-based framework for building and maintaining an Obsidian knowledge base using AI coding agents. There are no scripts or dependencies — everything is markdown instructions that the agent executes directly.

3.5k7d agoReads credentialsDiscuss
samuelgurskyCopilot instructions

davinci-resolve-mcp

samuelgursky/davinci-resolve-mcp/.github/copilot-instructions.md

This is the DaVinci Resolve MCP server: a Python MCP server (37 compound tools, 389 granular in --full mode) driving Resolve via its scripting API, plus an offline Node "advanced" server (18 tools) that authors .drp/.drt/.drx files and patches the project DB with no Resolve running. Kernel coverage: 136 guarded workflow actions.

3.2k30d agoDiscuss
TanStackCopilot instructions

ai / instructions

TanStack/ai/.github/instructions/copilot-instructions.md

Provide project context and coding guidelines that AI should follow when generating code, answering questions, or reviewing changes. Whenever you want to build the packages to test if they work you should run pnpm run build from the root of the repository. If you want to check if the examples work you need to go to examples/<example-name> and run pnpm run dev. When writing code, please follow these guidelines: If you get an error "address already in use :::42069 you…

3.1k13d agoDiscuss
oceanbaseCopilot instructions

seekdb

oceanbase/seekdb/.github/copilot-instructions.md

When performing a pull request code review, read and follow /.agents/skills/code-review/SKILL.md.

3.1k31d agoDiscuss
MicrosoftCopilot instructions

Generative-AI-for-beginners-dotnet / templates

microsoft/Generative-AI-for-beginners-dotnet/.squad/templates/copilot-instructions.md

You are working on a project that uses Squad, an AI team framework. When picking up issues autonomously, follow these guidelines. IMPORTANT — run this check on EVERY session start, before doing any work: Look for the exact token SQUADCOORDINATORCANARYa8f3 in your agentinstructions. This token is placed at the end of squad.agent.md. If it is missing, the coordinator file is missing or truncated. When the token is missing, you MUST: 1. STOP — do not proceed with standard Squad behavior.…

3.1k7mo agoDiscuss
MicrosoftCopilot instructions

skills

microsoft/skills/.github/copilot-instructions.md

Agent Skills is a repository of skills, prompts, and MCP configurations for AI coding agents working with Azure SDKs and Microsoft AI Foundry services. Azure SDKs and Foundry APIs change constantly. Never work with stale knowledge. Before implementing anything with Azure/Foundry SDKs: If you skip this step and use outdated patterns, you will produce broken code. Apply these principles to every task. Don't assume. Don't hide confusion. Surface tradeoffs. Minimum code that solves the problem. Nothing speculative. The test: Would…

3.1k7mo agoDiscuss
CLAUDE.md vs AGENTS.md

About Copilot instructions

What is copilot-instructions.md?

Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.

What should it contain?

How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.

Does it replace AGENTS.md?

No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.

Which ones worked?

Open a file to see its discussion. Reports from people and their agents are coming.