agentleFS
Sign inSign up

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 40Worked for most · soon
MicrosoftAGENTS.md

PhiCookBook / zh-HK

microsoft/PhiCookBook/translations/zh-HK/AGENTS.md

PhiCookBook 是一個全面的食譜庫,包含了 Microsoft Phi 系列小語言模型(SLMs)的實作範例、教學及文件。此庫展示了包括推論、微調、量化、RAG 實現及多模態應用於不同平台與框架的多種使用案例。 關鍵技術: - 語言: Python、C#/.NET、JavaScript/Node.js - 框架: ONNX Runtime、PyTorch、Transformers、MLX、OpenVINO、Semantic Kernel - 平台: Microsoft Foundry、GitHub Models、Hugging Face、Ollama - 模型類型: Phi-3、Phi-3.5、Phi-4(文字、視覺、多模態、推理變體) 倉庫結構: - /code/ - 工作代碼範例與示範實作 - /md/ - 詳細文件、教學及操作指南 - /translations/ - 多語言翻譯(通過自動化工作流程支持超過50種語言) - /.devcontainer/ - 開發容器設定(含 Python 3.12 與 Ollama) Prerequisites: - Python 3.12 or later - .NET 8.0 SDK (for C# examples) - Node.js 18+ and npm (for JavaScript examples) - 16GB RAM minimum recommended Installation: For Python Examples: Navigate to specific example directories…

3.9k7mo agoDiscuss
MicrosoftAGENTS.md

PhiCookBook / zh-MO

microsoft/PhiCookBook/translations/zh-MO/AGENTS.md

PhiCookBook 是一個全面的廚房書庫,包含針對微軟 Phi 系列小型語言模型(SLMs)進行操作的實務範例、教學和文件。該庫展示了多種使用案例,包括推理、微調、量化、RAG 實作以及跨不同平台與框架的多模態應用。 主要技術: - 語言: Python、C#/.NET、JavaScript/Node.js - 框架: ONNX Runtime、PyTorch、Transformers、MLX、OpenVINO、Semantic Kernel - 平台: Microsoft Foundry、GitHub Models、Hugging Face、Ollama - 模型類型: Phi-3、Phi-3.5、Phi-4(文本、視覺、多模態、推理變體) 倉庫結構: - /code/ - 實作程式碼範例及樣本 - /md/ - 詳細的文件、教程和操作指南 - /translations/ - 多語言翻譯(50 多種語言通過自動化工作流程) - /.devcontainer/ - 開發容器配置(Python 3.12 搭配 Ollama) 先決條件: - Python 3.12 或更新版本 - .NET 8.0 SDK(用於 C# 範例) - Node.js 18+ 及 npm(用於 JavaScript 範例) - 建議最低 16GB RAM Python 範例: 進入指定範例目錄並安裝依賴: JavaScript/Web 範例: 大多數範例以 Jupyter 筆記本形式提供: 本倉庫包含範例代碼及教程,而非傳統帶有單元測試的軟件項目。驗證通常通過以下方式完成: 常見驗證方式: - 在目標環境中測試範例執行 - 驗證依賴安裝正確…

3.9k7mo agoDiscuss
MicrosoftAGENTS.md

PhiCookBook / zh-TW

microsoft/PhiCookBook/translations/zh-TW/AGENTS.md

PhiCookBook 是一個綜合性的食譜存放庫,包含針對 Microsoft Phi 系列小型語言模型(SLMs)的實作範例、教學與文件。此存放庫展示多種使用案例,涵蓋推論、微調、量化、RAG 實作,以及跨不同平台和框架的多模態應用。 主要技術: - 語言: Python、C#/.NET、JavaScript/Node.js - 框架: ONNX Runtime、PyTorch、Transformers、MLX、OpenVINO、Semantic Kernel - 平台: Microsoft Foundry、GitHub Models、Hugging Face、Ollama - 模型類型: Phi-3、Phi-3.5、Phi-4(文本、視覺、多模態、推理變種) 存放庫結構: - /code/ - 可操作的程式碼範例與示範實作 - /md/ - 詳細文件、教學與操作指南 - /translations/ - 多語言翻譯(超過50種語言透過自動化工作流程) - /.devcontainer/ - 開發容器配置(Python 3.12 與 Ollama) 前置需求: - Python 3.12 或更新版本 - .NET 8.0 SDK(用於 C# 範例) - Node.js 18+ 與 npm(用於 JavaScript 範例) - 建議記憶體至少16GB Python 範例: 進入特定範例目錄並安裝相依套件: JavaScript/網頁範例: 大部分範例均為 Jupyter 筆記本形式: 本存放庫提供的是範例程式碼與教學,而非傳統軟體專案單元測試。驗證通常透過: 常見驗證方式: - 在目標環境測試範例執行 - 確認套件正確安裝 - 驗證模型能下載/載入成功 -…

3.9k7mo 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
MicrosoftSkill

codegen-literal-security-scan

microsoft/kiota/.github/skills/codegen-literal-security-scan/SKILL.md

Detect and remediate code-generation literal injection risks in Kiota writer code (wire names, serialization names, URL templates, base URLs, defaults, and path parameter keys).

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…

3.7k30d agoDiscuss
MicrosoftSkill

agentic-workflows

microsoft/mcp/.github/skills/agentic-workflows/SKILL.md

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

3.7k30d agoDiscuss
MicrosoftSkill

mcp-code-reviewer

microsoft/mcp/.github/skills/mcp-code-reviewer/SKILL.md

Review MCP pull requests with repository-specific security, correctness, architecture, testing, and completeness checks. Use when: review PR, review pull request, code review, inspect PR, check PR, PR feedback.

3.7k30d agoDiscuss
MicrosoftSkill

resilience-management-operations

microsoft/mcp/.github/skills/resilience-management-operations/SKILL.md

Operate all Azure Resilience Management MCP tools for usage plans, enrollments, goals, drills, drill resources and runs, recovery plans, recovery resources, recovery jobs, failover, reprotect, readiness, validation, retry, resume, and finalize. Use when: list/get/create/update/delete resilience resources; configure, validate, run, resync, or end drills; include/exclude recovery resources; check readiness; validate or execute recovery operations; monitor, retry, or resume recovery jobs; implement, add, test, or record a Resilience Management tool.

3.7k30d agoDiscuss
MicrosoftSkill

azurebackup-telemetry-report

microsoft/mcp/tools/Azure.Mcp.Tools.AzureBackup/skills/azurebackup-telemetry-report/SKILL.md

Generate weekly telemetry reports and customer adoption reports for Azure Backup MCP tools. Runs KQL queries against the Kusto telemetry cluster, analyzes error patterns with 3-way classification (Customer/Azure Service/MCP Tool Bug), identifies customers via P360/C360 cross-cluster joins, compares week-over-week metrics, correlates with merged PRs and releases, and produces an Outlook-compatible HTML report. USE WHEN: weekly telemetry report, Azure Backup MCP telemetry, error analysis, telemetry bugs, weekly report, MCP tool success rate, backup telemetry, error classification, customer usage report, who is using Azure Backup MCP, backup adoption, customer report.

3.7k30d 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

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…

3.7k56d agoDiscuss
MicrosoftSkill

cherry-pick

microsoft/DirectXShaderCompiler/.github/skills/cherry-pick/SKILL.md

Cherry-pick a commit onto another branch and open the PR. Use when the user asks to cherry-pick or backport a commit or PR to a release branch.

3.7k56d 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
MicrosoftSkill

adversarial-branch-review

microsoft/ebpf-for-windows/.github/skills/adversarial-branch-review/SKILL.md

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.

3.6k6mo agoDiscuss
MicrosoftSkill

build-ebpf

microsoft/ebpf-for-windows/.github/skills/build-ebpf/SKILL.md

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.).

3.6k6mo agoDiscuss
MicrosoftSkill

build-prevail

microsoft/ebpf-for-windows/.github/skills/build-prevail/SKILL.md

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.

3.6k6mo agoDiscuss
MicrosoftSkill

debug-crash-dump

microsoft/ebpf-for-windows/.github/skills/debug-crash-dump/SKILL.md

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.

3.6k6mo agoDiscuss
MicrosoftSkill

pr-triage-report

microsoft/ebpf-for-windows/.github/skills/pr-triage-report/SKILL.md

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.

3.6k6mo agoDiscuss
MicrosoftSkill

verify-bpf

microsoft/ebpf-for-windows/.github/skills/verify-bpf/SKILL.md

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.

3.6k6mo agoDiscuss
CLAUDE.md vs AGENTS.md

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.