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 21Worked for most · soon
MicrosoftAGENTS.md

mcp-for-beginners / tl

microsoft/mcp-for-beginners/translations/tl/AGENTS.md

MCP para sa Mga Baguhan ay isang open-source na pang-edukasyong kurikulum para matutunan ang Model Context Protocol (MCP) - isang pinagsanib na balangkas para sa mga interaksyon sa pagitan ng mga AI model at mga kliyenteng aplikasyon. Ang repository na ito ay nagbibigay ng malawak na materyales sa pag-aaral kasama ang mga halimbawa ng kodigo sa maraming programming languages. Ito ay isang dokumentasyong nakatuon na repository. Karamihan sa setup ay ginagawa sa mga indibidwal na halimbawang proyekto at mga labs.

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / tr

microsoft/mcp-for-beginners/translations/tr/AGENTS.md

Yeni Başlayanlar için MCP, Model Context Protocol (MCP) - AI modelleri ile istemci uygulamalar arasındaki etkileşimler için standart bir çerçeve olan MCP'yi öğrenmek için açık kaynaklı bir eğitim müfredatıdır. Bu depo, birden çok programlama dilinde pratik kod örnekleriyle kapsamlı öğrenme malzemeleri sunar. Bu, belge odaklı bir depodur. Çoğu kurulum bireysel örnek projeler ve laboratuvarlar içinde gerçekleşir. Örnek projeler aşağıdaki konumlardadır: - 03-GettingStarted/samples/ - Dil spesifik örnekler - 03-GettingStarted/01-first-server/solution/ - İlk sunucu uygulamaları - 03-GettingStarted/02-client/solution/ - İstemci uygulamaları - 11-MCPServerHandsOnLabs/ -…

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / uk

microsoft/mcp-for-beginners/translations/uk/AGENTS.md

MCP для початківців — це відкритий навчальний курс для вивчення Протоколу Контексту Моделі (MCP) — стандартизованої рамки для взаємодії між AI-моделями та клієнтськими додатками. Цей репозиторій надає комплексні навчальні матеріали з практичними прикладами коду на кількох мовах програмування. Це репозиторій, орієнтований на документацію. Більшість налаштувань відбувається у кожному окремому прикладі проекту та лабораторії. Прикладні проєкти знаходяться в: - 03-GettingStarted/samples/ - Приклади для конкретних мов - 03-GettingStarted/01-first-server/solution/ - Перші реалізації серверів - 03-GettingStarted/02-client/solution/ - Клієнтські реалізації - 11-MCPServerHandsOnLabs/ - Комплексні лабораторії…

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / ur

microsoft/mcp-for-beginners/translations/ur/AGENTS.md

MCP برائے مبتدیان ماڈل کانٹیکسٹ پروٹوکول (MCP) سیکھنے کے لیے ایک اوپن سورس تعلیمی نصاب ہے - جو AI ماڈلز اور کلائنٹ ایپلیکیشنز کے مابین تعاملات کے لیے ایک معیاری فریم ورک ہے۔ یہ ریپوزٹری مختلف پروگرامنگ زبانوں میں عملی کوڈ کی مثالوں کے ساتھ جامع تعلیمی مواد فراہم کرتی ہے۔ یہ ایک دستاویزی مرکزیت والی ریپوزٹری ہے۔ زیادہ تر سیٹ اپ نمونہ پروجیکٹس اور لیبز کے اندر ہوتا ہے۔ نمونہ پروجیکٹس درج ذیل جگہوں پر موجود ہیں: - 03-GettingStarted/samples/…

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / vi

microsoft/mcp-for-beginners/translations/vi/AGENTS.md

MCP dành cho người mới bắt đầu là một chương trình học mở nguồn về giao thức Model Context Protocol (MCP) - một khuôn khổ tiêu chuẩn hóa cho sự tương tác giữa các mô hình AI và các ứng dụng khách. Kho lưu trữ này cung cấp tài liệu học tập toàn diện với các ví dụ mã thực hành trên nhiều ngôn ngữ lập trình. Đây là kho tài liệu tập trung. Hầu hết việc thiết lập diễn…

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / zh-CN

microsoft/mcp-for-beginners/translations/zh-CN/AGENTS.md

MCP入门指南 是一个开源的教育课程,用于学习模型上下文协议(MCP)——一种用于 AI 模型与客户端应用之间交互的标准化框架。本仓库提供了涵盖多种编程语言的详尽学习资料和实操代码示例。 这是一个以文档为主的仓库。大多数环境配置均在各个示例项目和实验中进行。 示例项目位于: - 03-GettingStarted/samples/ - 语言特定示例 - 03-GettingStarted/01-first-server/solution/ - 第一个服务器实现 - 03-GettingStarted/02-client/solution/ - 客户端实现 - 11-MCPServerHandsOnLabs/ - 综合数据库集成实验 每个示例项目内均包含其独立的设置说明: - [x] <strong>新贡献者指导清晰</strong>:该文件定义了仓库目的、 结构、贡献规则及示例设置路径。 - [x] 构建/测试/代码风格检查命令及精确参数: - 仓库文档代码风格检查: npx --yes markdownlint-cli2 "*/.md" "#nodemodules" "#translations" "#translatedimages" - 仓库文档链接模式审计: find . -name ".md" -not -path "/node_modules/" -not -path "./translations/" -not -path "./translated_images/" -print0 | xargs -0 grep -En "\[.\]\(.*\)" - TypeScript 示例验证: cd 03-GettingStarted/samples/typescript && npm ci && npm test && npm run build - Python 示例验证: cd…

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / zh-HK

microsoft/mcp-for-beginners/translations/zh-HK/AGENTS.md

MCP for Beginners 是一個開源教育課程,用於學習模型上下文協議(MCP)——一個 AI 模型與客戶端應用之間互動的標準化框架。本存儲庫提供包含多種程式語言的完整學習資料和實作範例。 本存儲庫以文件為主。大部分設定在各個範例專案與實驗中完成。 範例專案位置: - 03-GettingStarted/samples/ — 依語言分別的範例 - 03-GettingStarted/01-first-server/solution/ — 首個伺服器實作 - 03-GettingStarted/02-client/solution/ — 客戶端實作 - 11-MCPServerHandsOnLabs/ — 完整資料庫整合實驗室 每個範例專案附有其設置說明: 因本存儲庫主要為文件,測試重點為: 各語言範例皆有其測試方式: 本存儲庫文件託管使用 GitHub Pages 或類似平台(如適用)。主分支變更時觸發: 本存儲庫主要為 Markdown 文檔,不需編譯或建置步驟。 各範例專案可能有部署說明: - 參見 03-GettingStarted/09-deployment/ 中 MCP 伺服器部署指引 - Azure 容器應用部署範例在 11-MCPServerHandsOnLabs/

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / zh-MO

microsoft/mcp-for-beginners/translations/zh-MO/AGENTS.md

MCP for Beginners 是一個開源的教育課程,用於學習模型上下文協議(MCP)——一個標準化的框架,用於 AI 模型與客戶端應用程序之間的互動。本倉庫提供多種程式語言的綜合學習資料和實作範例代碼。 此倉庫以文件為主。大部分設置工作於個別範例專案與實驗室中進行。 範例專案位於: - 03-GettingStarted/samples/ - 依語言區分的範例 - 03-GettingStarted/01-first-server/solution/ - 首個伺服器實作 - 03-GettingStarted/02-client/solution/ - 客戶端實作 - 11-MCPServerHandsOnLabs/ - 全面資料庫整合實驗室 每個範例專案都含有各自的設置說明: 由於此為主要文件倉庫,測試重點為: 各語言範例附帶專屬的測試方法: 本倉庫使用 GitHub Pages 或類似服務來托管文件(如適用)。main 分支的變更會觸發: 此倉庫主要包含 Markdown 文件,核心課程內容不需編譯或建置。 個別範例專案可能含有部署說明: - 請參閱 03-GettingStarted/09-deployment/ 的 MCP 伺服器部署指南 - 11-MCPServerHandsOnLabs/ 中的 Azure Container Apps 部署範例

17k22d agoDiscuss
MicrosoftAGENTS.md

mcp-for-beginners / zh-TW

microsoft/mcp-for-beginners/translations/zh-TW/AGENTS.md

初學者 MCP 是一個開源的教學課程,用於學習模型上下文協議 (Model Context Protocol, MCP)——一個 AI 模型與客戶端應用程式之間交互的標準化框架。本儲存庫提供涵蓋多種程式語言的實作程式碼範例的完整學習材料。 這是一個以文件為主的儲存庫,大多數設定工作發生在各個範例專案與實驗室中。 範例專案位置為: - 03-GettingStarted/samples/ - 特定語言範例 - 03-GettingStarted/01-first-server/solution/ - 第一個伺服器實作 - 03-GettingStarted/02-client/solution/ - 客戶端實作 - 11-MCPServerHandsOnLabs/ - 全面性資料庫整合實驗室 每個範例專案都有自己的設定說明: - [x] <strong>新貢獻者清晰度</strong>:此文件定義儲存庫目的、 結構、貢獻規則及範例設定路徑。 - [x] 精確標記的建置/測試/程式碼風格檢查指令: - 儲存庫文件風格檢查: npx --yes markdownlint-cli2 "*/.md" "#nodemodules" "#translations" "#translatedimages" - 儲存庫文件連結模式稽核: find . -name ".md" -not -path "/node_modules/" -not -path "./translations/" -not -path "./translated_images/" -print0 | xargs -0 grep -En "\[.\]\(.*\)" - TypeScript 範例驗證: cd 03-GettingStarted/samples/typescript && npm ci && npm test && npm run…

17k22d agoDiscuss
MicrosoftSkill

skillopt-sleep

microsoft/SkillOpt/plugins/claude-code/skills/skillopt-sleep/SKILL.md

Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated CLAUDE.md/SKILL.md behind a held-out gate.

17k49d agoDiscuss
MicrosoftSkill

skillopt-sleep

microsoft/SkillOpt/plugins/codex/skills/skillopt-sleep/SKILL.md

Use when the user wants Codex to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, wants Codex to review past sessions, learn preferences, consolidate memory/skills, run dry-run/run/adopt/status for SkillOpt-Sleep, or schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated memory + skills behind a held-out gate.

17k49d agoDiscuss
MicrosoftSkill

skillopt-sleep

microsoft/SkillOpt/plugins/cursor/skills/skillopt-sleep/SKILL.md

Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into a Cursor skill, or requests SkillOpt-Sleep status, harvest, dry-run, run, scheduling, review, or adoption. Drives the validation-gated skillopt_sleep engine with Cursor transcripts and the optional Cursor Agent CLI backend.

17k49d agoDiscuss
MicrosoftSkill

skillopt-sleep

microsoft/SkillOpt/plugins/dsh/skills/skillopt-sleep/SKILL.md

Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, skill/memory consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine through the skillopt_* tools: harvest past sessions -> mine recurring tasks -> replay via a selected backend -> consolidate validated skills behind a held-out gate.

17k49d agoDiscuss
MicrosoftSkill

skillopt-sleep

microsoft/SkillOpt/plugins/openclaw/SKILL.md

Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.

17k49d agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/backend-test-conventions.mdc

Backend Python test conventions (pytest)

17k5mo agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/dataframe-serialization.mdc

All DataFrame-to-records conversion for API responses, streaming events, or frontend-visible data MUST use the centralized helpers in dataformulator.datalake.parquetutils: pandas.DataFrame.tojson(orient='records') defaults to dateformat='epoch', which serializes datetime columns as epoch milliseconds (e.g. 1773532800000). The frontend interprets these as plain numbers and renders them with commas (1,773,532,800,000) instead of formatted dates. dftosaferecords enforces dateformat='iso' and default_handler=str, ensuring datetimes become ISO-8601 strings and exotic types degrade gracefully. Internal data processing that never reaches the frontend or JSON serialization (e.g. Kusto SDK metadata parsing, Vega-Lite…

17k5mo agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/dev-guides-first.mdc

Require reading dev-guides before development and keeping docs in sync

17k5mo agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/error-response-safety.mdc

Prevent information exposure through exception messages in HTTP responses

17k5mo agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/frontend-test-conventions.mdc

Frontend TypeScript test conventions (Vitest)

17k5mo agoDiscuss
MicrosoftCursor rule

data-formulator / rules

microsoft/data-formulator/.cursor/rules/i18n-no-hardcoded-strings.mdc

No hardcoded UI strings — use i18n translation keys

17k5mo 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.