MicrosoftCopilot instructionsfluentui-blazor
microsoft/fluentui-blazor/.github/copilot-instructions.md
No summary in the file. Open it to read it.
Find the best CLAUDE.md, AGENTS.md and Claude skills
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Most stars first · from page 34Worked for most · soon
MicrosoftCopilot instructionsMicrosoftSkillcsharp-naming-conventions
microsoft/fluentui-blazor/.github/skills/csharp-naming-conventions/SKILL.md
C# and .NET naming conventions, coding best practices, layout rules, unit testing, and Blazor component guidelines. Use when writing, reviewing, or refactoring C# / .NET / Blazor code or writing unit tests with xUnit and bUnit.
MicrosoftCopilot instructionsmsquic
microsoft/msquic/.github/copilot-instructions.md
MsQuic is Microsoft's cross-platform C implementation of the IETF QUIC protocol. It also has C++ API wrappers and Rust/C# interop layers. The codebase targets Windows (user & kernel mode), Linux, macOS, and FreeBSD. The primary language is C (C17), with C++ (C17) for tests/tools, Rust bindings, and C# interop. Build system: CMake + PowerShell scripts. Key files: CMakeLists.txt (root build), version.json (version info), .clang-format (C/C++ style), src/.editorconfig (editor settings), Cargo.toml (Rust crate config), rust-toolchain.toml (Rust 1.93.1). Always use PowerShell 7+…
MicrosoftSkillcherry-pick-to-release
microsoft/msquic/.github/skills/cherry-pick-to-release/SKILL.md
Cherry-pick a merged main-branch PR onto a MsQuic release branch (release/X.Y).
MicrosoftSkillinvestigate-ci-failure
microsoft/msquic/.github/skills/investigate-ci-failure/SKILL.md
Guide systematic investigation of MsQuic CI test failures reported by GitHub Actions.
MicrosoftCopilot instructionsperfview
microsoft/perfview/.github/copilot-instructions.md
PerfView is a Windows performance-analysis tool for investigating CPU and memory issues, built on the TraceEvent library for parsing ETW and EventPipe trace data. The solution (PerfView.sln) contains the WPF GUI application, the cross-platform TraceEvent library, and several supporting libraries. Follow existing patterns — when in doubt, match the surrounding code.
MicrosoftAGENTS.mdWindowsAppSDK
microsoft/WindowsAppSDK/AGENTS.md
Comprehensive guidance for AI contributions to the Windows App SDK. The SDK follows this organization: For C#/C++/IDL files: For XAML files:
MicrosoftCopilot instructionsWindowsAppSDK
microsoft/WindowsAppSDK/.github/copilot-instructions.md
Windows App SDK AI contributor guidance
MicrosoftSkillissue-triage-report
microsoft/WindowsAppSDK/.github/skills/issue-triage-report/SKILL.md
Generate comprehensive GitHub Feature Area Status reports for the Windows App SDK repository. Use when asked to create triage reports, identify high-priority issues, analyze feature area health, find issues needing attention, or generate status dashboards. Triggers on requests involving issue triage, area status, priority analysis, bug tracking reports, or engineering team focus areas.
MicrosoftSkilltriage-meeting-prep
microsoft/WindowsAppSDK/.github/skills/triage-meeting-prep/SKILL.md
Prepare weekly triage meeting summary for WinAppSDK Needs-Triage issues. Use when preparing for triage meetings, reviewing Needs-Triage issues, generating diff reports since last triage, summarizing new or updated issues, or creating action item recommendations. Triggers on requests involving triage preparation, Needs-Triage review, meeting summary, triage diff, or weekly issue analysis.
MicrosoftSkillworktree-manager
microsoft/WindowsAppSDK/.github/skills/worktree-manager/SKILL.md
Create and manage Git worktrees for parallel development workflows. Use when multiple self-contained issues should NOT be fixed in a single branch, when human-Copilot iteration requires isolated environments with separate chat history and commits, or when parallel work items need independent build/test results. Triggers on requests involving branch isolation, work item separation, parallel development, or avoiding messy branch switching.
MicrosoftCopilot instructionsPyRIT
microsoft/PyRIT/.github/copilot-instructions.md
PyRIT (Python Risk Identification Tool for generative AI) is an open-source framework for security professionals to proactively identify risks in generative AI systems. PyRIT uses a modular pluggable-brick design. doc/code/framework.md is the canonical reference for how these pieces fit together. It defines each component's responsibilities — what it owns and, critically, what it does not own — and how scenarios, attack techniques, executors, and the core/shared layers relate. Read it before adding or reviewing components so new code lands in…
MicrosoftCopilot instructionsFLAML
microsoft/FLAML/.github/copilot-instructions.md
FLAML (Fast Library for Automated Machine Learning & Tuning) is a lightweight Python library for efficient automation of machine learning and AI operations. It automates workflow based on large language models, machine learning models, etc. and optimizes their performance. Key Components: The repository uses pre-commit hooks for:
MicrosoftCopilot instructionsApplicationInspector
microsoft/ApplicationInspector/.github/copilot-instructions.md
Microsoft Application Inspector is a source code characterization tool that identifies coding features based on well-known library/API calls using regex patterns and rules. It supports multiple programming languages and generates reports in HTML, JSON, SARIF, and text formats. Version Tracking: This project uses Nerdbank.GitVersioning (nbgv) for version tracking, which requires a deep clone of the repository. Shallow clones will not work correctly with version generation. NuGet Packages: The repository uses a custom nuget.config that points to a private Azure DevOps…
MicrosoftSkillflint-chart-author
microsoft/flint-chart/agent-skills/flint-chart-author/SKILL.md
Use when: the user asks to make or render charts with flint-chart, visualize tabular data, generate a ChartAssemblyInput, validate/render through MCP, or add Flint to a JS/TS project. Author the semantic spec, transform data before Flint when needed, install/import Flint only when executable code is needed, and reserve backend-specific style tweaks for after compiling from Flint.
MicrosoftSkillflint-theme-author
microsoft/flint-chart/agent-skills/flint-theme-author/SKILL.md
Use when: creating, translating, refining, reviewing, or validating a custom Flint ThemeSpec from brand guidelines, websites, slide decks, publication references, design tokens, or an existing visual identity. Produce a reusable ThemeSpec JSON object for Flint Theme Lab without inventing fields or changing chart semantics.
MicrosoftSkillflint-chart-author
microsoft/flint-chart/.github/extensions/flint-chart/skills/flint-chart-author/SKILL.md
Use when: the user asks to make or render charts with flint-chart, visualize tabular data, generate a ChartAssemblyInput, validate/render through MCP, or add Flint to a JS/TS project. Author the semantic spec, transform data before Flint when needed, install/import Flint only when executable code is needed, and reserve backend-specific style tweaks for after compiling from Flint.
MicrosoftSkillagentic-workflows
microsoft/AI-Engineering-Coach/.github/skills/agentic-workflows/SKILL.md
Route gh-aw workflow create/debug/upgrade requests to the right prompts.
MicrosoftCopilot instructionsskill-recorder
microsoft/skill-recorder/.github/copilot-instructions.md
Ongoing work in this repository lands on the current release branch, not main. Release branches are named release/<semver> — currently release/0.3.0, the highest-versioned release/* branch on origin. main trails the release branch and only advances when a version is cut and merged (see RELEASING.md). Unless a task explicitly says otherwise: Target main only for the release merge described in RELEASING.md.
MicrosoftSkillapm-spec-guardian
microsoft/apm/.agents/skills/apm-spec-guardian/SKILL.md
Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-*.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/*.schema.json), or the conformance fixture seed (tests/fixtures/spec-conformance/**). The panel fans out to four spec-ecosystem reviewers (swagger-openapi-editor, oci-distribution-editor, pkgmgr-registry-contract-editor, w3c-tag-architect), each running in its own agent thread, and a spec-editor synthesizer that produces a fold-now / defer-v0.1.1 / defer-v0.2 / reject list plus a ship decision keyed off a 1..10 shocked_meter scale. The orchestrator is the sole writer to the PR: ONE consolidated comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes folds, and renders a ship recommendation that the maintainer weighs.
Agent instruction files
What are agent instruction files?
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.