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:
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…
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…
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…
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.
Perform a deep adversarial review of C/C++ changes between an active branch and a baseline branch in ebpf-for-windows. Produce both a detailed review report and a point-by-point fix list.
Build the eBPF for Windows repository — entire solution or specific components. Use this skill when asked to build, compile, rebuild, restore, or clean the project or any of its components (drivers, libraries, tools, tests, etc.).
Build and test the PREVAIL verifier (external/ebpf-verifier) standalone. Use this skill when asked to build, test, or iterate on the PREVAIL verifier, run YAML verification tests, or work with the verifier's cmake build system.
Download and analyze crash dumps from CI failures using CDB/WinDbg. Use this skill when asked to debug crashes, analyze dump files, set up WinDbg/CDB, investigate fault injection failures, or start mcp-windbg.
Generate a Markdown triage report for open, non-draft pull requests in microsoft/ebpf-for-windows, including CI, freshness, sign-offs, and next-owner routing.
Build and verify eBPF programs for the ebpf-for-windows project. Use this skill when asked to compile a .c BPF source to .o, verify a .o ELF file with bpf2c, or diagnose verification failures. Covers the full clang→bpf2c pipeline.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.