Find the best CLAUDE.md, AGENTS.md and Claude skills

MicrosoftReads credentialsAGENTS.md

generative-ai-for-beginners / zh-MO

microsoft/generative-ai-for-beginners/translations/zh-MO/AGENTS.md

這個儲存庫包含一個全面的 21 課程綱要，教授生成式 AI 的基礎知識及應用開發。課程設計適合初學者，涵蓋從基本概念到建立可投入生產的應用程式。 關鍵技術： - Python 3.9+ 與函式庫：openai、python-dotenv、tiktoken、azure-ai-inference、pandas、numpy、matplotlib - TypeScript/JavaScript 搭配 Node.js 及函式庫：openai（透過 v1 端點及 Responses API 使用 Azure OpenAI）、@azure-rest/ai-inference（微軟 Foundry 模型） - Azure OpenAI 服務、OpenAI API 與微軟 Foundry 模型（GitHub Models 將於 2026 年 7 月底退休） - 用於互動學習的 Jupyter 筆記本 - 用於一致性開發環境的 Dev Containers 儲存庫結構： - 21 個編號課程目錄（00-21），包含 README、代碼範例及作業 - 多種實作：Python、TypeScript，有時也包含 .NET 範例 - 翻譯目錄包含 40 多種語言版本 - 透過 .env 檔案集中管理設定（使用 .env.copy 作為範本） 本儲存庫包含 .devcontainer 設定檔，可用於 GitHub Codespaces 或 VS Code Dev Containers： 所有需存取 API 的課程皆使用 .env 中定義的環境變數：

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

generative-ai-for-beginners / zh-TW

microsoft/generative-ai-for-beginners/translations/zh-TW/AGENTS.md

本儲存庫包含一個完整的21課程綱要，教導生成式 AI 的基礎和應用開發。此課程專為初學者設計，涵蓋從基礎概念到建立可投入生產的應用程式。 核心技術： - Python 3.9+，搭配以下套件：openai、python-dotenv、tiktoken、azure-ai-inference、pandas、numpy、matplotlib - TypeScript/JavaScript，搭配 Node.js 及套件：openai（Azure OpenAI 透過 v1 端點和 Responses API）、@azure-rest/ai-inference（Microsoft Foundry 模型） - Azure OpenAI 服務、OpenAI API 與 Microsoft Foundry 模型（GitHub Models 將於2026年7月底停用） - 使用 Jupyter 筆記本進行互動式學習 - 使用開發容器以保持一致的開發環境 儲存庫結構： - 21 個按序號命名的課程目錄（00-21），包含 README、程式碼範例和作業 - 多種實作版本：Python、TypeScript，有時也有 .NET 範例 - translations 目錄中有 40 多種語言版本 - 統一使用 .env 檔案做設定管理（可使用 .env.copy 作為範本） 本儲存庫提供 .devcontainer 設定，適用於 GitHub Codespaces 或 VS Code 的開發容器： 所有需要 API 訪問的課程均使用 .env 檔案定義的環境變數：

No other project uses it yet

MicrosoftCopilot instructions

TypeScript

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

This repository contains the native TypeScript compiler and language server. The source directories of interest that we have are: Most compiler development takes place in tsc/internal, and most behaviors can be tested via compiler tests. Most development on the codebase is in Go. Standard Go commands and practices apply, but we primarily use a tool called hereby to build, run tests, and other tasks. Run npx hereby --tasks to see all available commands. Always make sure code is formatted, linted,…

No other project uses it yet

MicrosoftSkill

api-client

microsoft/TypeScript/.github/skills/api-client/SKILL.md

Instructions for working on the API client in ./packages/typescript

MicrosoftSkill

compiler-and-fourslash-tests

microsoft/TypeScript/.github/skills/compiler-and-fourslash-tests/SKILL.md

How to write, run, and debug compiler tests and fourslash (LSP) tests in the TypeScript repository. Covers test file formats, directives, markers, baseline management, and the fourslash verification API.

No other project uses it yet

MicrosoftSkill

mcfly

microsoft/TypeScript/.github/skills/mcfly/SKILL.md

Only invoke when explicitly instructed to

No other project uses it yet

MicrosoftSkill

security-report-check

microsoft/TypeScript/.github/skills/security-report-check/SKILL.md

Are you doing security research on this repo? This document covers what guarantees and non-guarantees are provided. Consult this document before reporting a security issue or conducting security research.

MicrosoftAGENTS.md

terminal

microsoft/terminal/AGENTS.md

These rules apply to all public contributions and interactions, no matter how they're done. The entity operating or authorizing the contributions and interactions is responsible for them. AI assistance does not relieve contributors of responsibility for their work. "The AI did it" is not an excuse. Violations may result in contributions being closed without further comment. Cases of deception, evasion, or repeat violations may result in account bans. Allowed: - All AI usage that remains non-public (e.g. questions, reviews, local…

No other project uses it yet

MicrosoftAGENTS.md

playwright

microsoft/playwright/AGENTS.md

playwright-chromium, playwright-firefox, playwright-webkit — per-browser distributions. playwright-browser-chromium, playwright-browser-firefox, playwright-browser-webkit — binary packages. Assume watch is running and code is up to date. Generated files (types, channels, validators) are produced by watch automatically. Runs all lint checks in parallel: eslint, tsc, doclint, check-deps, generate_channels, generate_types, lint-tests, test-types, lint-packages, code-snippet linting, check-dependency-age (every version in package-lock.json must be at least 7 days old). Run flint only before you upload a PR, and only after npm run build. Do not run it before…

No other project uses it yet

MicrosoftReads credentialsSkill

api-review

microsoft/playwright/.claude/skills/api-review/SKILL.md

Produce the "Playwright 1.xx API Review" artifact for a range of commits - the public API additions and the breaking or behavior changes that affect existing users since the last API review or since the last release, ordered by impact, each with links, before/after snippets and a documentation check. Covers microsoft/playwright (Node.js) and the Python, Java and .NET ports. Use when asked for an API review, to review API changes, or to check what changed in the public API since a release or since the last review.

MicrosoftSkill

playwright-audit-deps

microsoft/playwright/.claude/skills/playwright-audit-deps/SKILL.md

Roll the runtime dependencies that npm audit flags with a moderate or higher advisory to safe versions that are at least 8 days old, and commit them with a table of every package the lock file change touched (old and new version, publish date, weekly downloads). Use when asked to fix audit findings, bump vulnerable or outdated runtime dependencies, or update package-lock.json for an advisory.

No other project uses it yet

MicrosoftSkill

playwright-cherry-pick

microsoft/playwright/.claude/skills/playwright-cherry-pick/SKILL.md

Cherry-pick a commit or PR from main into a release branch (release-<version>) and retitle it as cherry-pick(#<pr>): <original title>. Use when asked to cherry-pick, backport, or port a change into a release.

No other project uses it yet

MicrosoftSkill

playwright-devops

microsoft/playwright/.claude/skills/playwright-devops/SKILL.md

DevOps workflows for Playwright - CI failure analysis, workflow debugging, and release operations.

No other project uses it yet

MicrosoftSkill

playwright-dev

microsoft/playwright/.claude/skills/playwright-dev/SKILL.md

Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.

MicrosoftSkill

playwright-release-notes

microsoft/playwright/.claude/skills/playwright-release-notes/SKILL.md

Write the release notes for a Playwright release - the Node.js notes in docs/src/release-notes-js.md together with the Python, Java and .NET translations, and the GitHub markdown for each language's release. Use when asked to write, translate or publish release notes.

No other project uses it yet

MicrosoftReads credentialsSkill

playwright-test-results

microsoft/playwright/.claude/skills/playwright-test-results/SKILL.md

Query Playwright CI test results from the aggregated DuckDB database. Answers questions about flaky tests, failure rates, slow tests, and per-run/SHA/PR results without hunting through GitHub artifacts.

No other project uses it yet

MicrosoftSkill

playwright-triage

microsoft/playwright/.claude/skills/playwright-triage/SKILL.md

Triage and fix one microsoft/playwright issue, or do a maintainer's task, unattended inside the Issue triage GitHub Actions workflow (.github/workflows/triage.yml), which a needs-triage, needs-triage-mac or needs-triage-win label starts, or a maintainer starts by hand with an issue, a task or both. Reproduces the issue on the runner, then leaves a verified fix proposal for the workflow to open as a draft PR, a test that covers a scenario that did not reproduce, an investigation note for it to post on the issue, or a browser bug report for it to file in microsoft/playwright-browsers or for a maintainer to file at crbug.com. Only for that workflow.

MicrosoftCopilot instructions

playwright

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

When reviewing pull requests:

No other project uses it yet

MicrosoftSkill

playwright-cli

microsoft/playwright/packages/playwright-core/src/tools/skills/playwright-cli/SKILL.md

Automate browser interactions, test web pages and work with Playwright tests.

Often used withfabric-sdk·ecosystem-reference·fractal-delegation

MicrosoftReads credentialsSkill

playwright-component-testing

microsoft/playwright/packages/playwright-core/src/tools/skills/playwright-component-testing/SKILL.md

Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.