skills
vercel-labs/skills/docs/agents.md
Back to the README Skills can be installed to any of these agents:
Steady5 mentions in 2 weeks
1 project uses a version of this
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
vercel-labs/skills/docs/agents.md
Back to the README Skills can be installed to any of these agents:
Steady5 mentions in 2 weeks
1 project uses a version of this
docker/compose/AGENTS.md
All agents must conform to AI_POLICY.md and the Compose-specific rules in CONTRIBUTING.md. - Build: make build - Test all: make test - Test unit: go test ./pkg/... — needs no Docker daemon; the e2e suite is gated behind the e2e build tag and is not picked up - Test single: go test ./pkg/compose/ -run TestFunctionName - E2E tests: go test -tags e2e ./pkg/e2e/ -run TestName — requires a Docker daemon and the locally built binary (make build) - New e2e…
vercel-labs/add-skill/AGENTS.md
This file provides guidance to AI coding agents working on the skills CLI codebase. skills is the CLI for the open agent skills ecosystem. Aliases: skills a works for add. skills i, skills install (no args) restore from skills-lock.json. skills ls works for list. skills experimental_install restores from skills-lock.json. skills experimental_sync reads skills from npm dependencies (sync remains a compatibility alias).
block/buzz/AGENTS.md
This guide is for AI agents contributing to the Buzz codebase. It covers agent-specific context and conventions. For general contributor info (setup, code style, PR process, architecture), see CONTRIBUTING.md. Before planning or reviewing a non-trivial change: 1. Read VISION.md. 2. Read the VISION_*.md documents relevant to the affected product surface. 3. Read the applicable guidance in TESTING.md and any package-local TESTING.md. 4. For any change to migrations/, schema/, or schema-dependent buzz-db queries, read docs/database.md: no new triggers, functions, or foreign…
Steady4 mentions in 2 weeks
No other project uses it yet
block/buzz/crates/buzz-push-gateway/migrations/AGENTS.md
Read docs/database.md before changing anything here. The existing push_gateway_* tables are also duplicated in the relay schema (migrations/ and schema/); until that duplication is removed, a change to them goes there too. The target is for the gateway to own its tables alone, so put new gateway tables only here. Never edit a merged migration.
Steady4 mentions in 2 weeks
1 project uses a version of this
block/buzz/desktop/src/features/agents/AGENTS.md
Scope: desktop/src/features/agents/ (config surfaces, shared config renderer, and the agent config core). Read this before changing how harness / provider / model / effort configuration is modeled, rendered, persisted, or applied. Plan of record: Buzz/Harness-Provider-Model.md in Morgan's Obsidian vault (PR sequence, decisions log). PRs: #2140 (rename), #2148 (flag reduction), #2156 (honest model states), #2158 (Agent Config Core). Harness capability facts have exactly one source: the Rust runtime catalog. KnownAcpRuntime (desktop/src-tauri/src/managed_agents/discovery/runtime_metadata.rs) declares each harness's model/provider/effort env keys and capabilities. Spawn applies…
block/buzz/migrations/AGENTS.md
Before changing anything in this directory, read docs/database.md. In short: - Add no triggers, functions, procedures, rules, or foreign keys. There are no exceptions, including the community write-fence attachment. - Put no data backfills in migrations: no UPDATE, INSERT, or DELETE over existing rows. Use the backfill framework in docs/data-backfills.md, or, until it ships, a reviewed one-off script in scripts/maintenance/. - Make each change in every schema location: migrations/, schema/tables/public/, the schema/ manifest and sibling directories, scripts/reconcile-schema-after-pgschema.sql where it applies,…
Steady4 mentions in 2 weeks
1 project uses a version of this
block/buzz/schema/AGENTS.md
This directory follows the same rules as migrations/. Read docs/database.md and migrations/AGENTS.md before changing anything here.
Steady4 mentions in 2 weeks
1 project uses a version of this
huggingface/pytorch-image-models/AGENTS.md
No summary in the file. Open it to read it.
Steady12 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/AGENTS.md
Data Science for Beginners is a comprehensive 10-week, 20-lesson curriculum created by Microsoft Azure Cloud Advocates. The repository is a learning resource that teaches foundational data science concepts through project-based lessons, including Jupyter notebooks, interactive quizzes, and hands-on assignments. Key Technologies: - Jupyter Notebooks: Primary learning medium using Python 3 - Python Libraries: pandas, numpy, matplotlib for data analysis and visualization - Vue.js 2: Quiz application (quiz-app folder) - Docsify: Documentation site generator for offline access - Node.js/npm: Package management…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/ar/AGENTS.md
"علم البيانات للمبتدئين" هو منهج شامل لمدة 10 أسابيع و20 درسًا تم إنشاؤه بواسطة Microsoft Azure Cloud Advocates. المستودع هو مورد تعليمي يشرح مفاهيم علم البيانات الأساسية من خلال دروس قائمة على المشاريع، بما في ذلك دفاتر Jupyter، اختبارات تفاعلية، وتكليفات عملية. التقنيات الرئيسية: - دفاتر Jupyter: الوسيلة التعليمية الأساسية باستخدام Python 3 - مكتبات Python: pandas، numpy، matplotlib لتحليل البيانات وتصويرها - Vue.js 2: تطبيق الاختبارات (مجلد quiz-app) - Docsify: مولد مواقع التوثيق للوصول دون اتصال - Node.js/npm: إدارة…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/bg/AGENTS.md
"Data Science for Beginners" е обширна 10-седмична учебна програма с 20 урока, създадена от Microsoft Azure Cloud Advocates. Репозиторият е учебен ресурс, който преподава основни концепции за анализ на данни чрез уроци, базирани на проекти, включително Jupyter notebooks, интерактивни тестове и практически задачи. Основни технологии: - Jupyter Notebooks: Основен учебен инструмент, използващ Python 3 - Python библиотеки: pandas, numpy, matplotlib за анализ и визуализация на данни - Vue.js 2: Приложение за тестове (папка quiz-app) - Docsify: Генератор на документация за…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/bn/AGENTS.md
ডেটা সায়েন্স ফর বিগিনার্স হলো একটি বিস্তৃত ১০-সপ্তাহের, ২০-লেসনের কারিকুলাম যা মাইক্রোসফট আজুর ক্লাউড অ্যাডভোকেটদের দ্বারা তৈরি। এই রিপোজিটরি একটি শিক্ষামূলক সম্পদ যা প্রকল্প-ভিত্তিক পাঠের মাধ্যমে মৌলিক ডেটা সায়েন্স ধারণাগুলি শেখায়, যার মধ্যে রয়েছে জুপিটার নোটবুক, ইন্টারঅ্যাকটিভ কুইজ এবং হাতে-কলমে অ্যাসাইনমেন্ট। মূল প্রযুক্তি: - জুপিটার নোটবুক: পাইথন ৩ ব্যবহার করে প্রধান শিক্ষার মাধ্যম - পাইথন লাইব্রেরি: pandas, numpy, matplotlib ডেটা বিশ্লেষণ এবং ভিজ্যুয়ালাইজেশনের জন্য - Vue.js 2: কুইজ অ্যাপ্লিকেশন (quiz-app ফোল্ডার) - Docsify: অফলাইন অ্যাক্সেসের জন্য ডকুমেন্টেশন সাইট জেনারেটর -…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/cs/AGENTS.md
Data Science for Beginners je komplexní desetitýdenní kurz s 20 lekcemi vytvořený týmem Microsoft Azure Cloud Advocates. Tento repozitář slouží jako vzdělávací zdroj, který učí základní koncepty datové vědy prostřednictvím projektově orientovaných lekcí, včetně Jupyter notebooků, interaktivních kvízů a praktických úkolů. Klíčové technologie: - Jupyter Notebooks: Hlavní výukové médium využívající Python 3 - Python knihovny: pandas, numpy, matplotlib pro analýzu a vizualizaci dat - Vue.js 2: Aplikace pro kvízy (složka quiz-app) - Docsify: Generátor dokumentačních stránek pro offline přístup -…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/da/AGENTS.md
Data Science for Beginners er et omfattende 10-ugers, 20-lektions pensum skabt af Microsoft Azure Cloud Advocates. Repositoriet er en læringsressource, der underviser i grundlæggende data science-koncepter gennem projektbaserede lektioner, herunder Jupyter-notebooks, interaktive quizzer og praktiske opgaver. Nøgleteknologier: - Jupyter Notebooks: Primært læringsmedium ved brug af Python 3 - Python-biblioteker: pandas, numpy, matplotlib til dataanalyse og visualisering - Vue.js 2: Quiz-applikation (quiz-app-mappe) - Docsify: Dokumentationsgenerator til offline adgang - Node.js/npm: Pakkehåndtering til JavaScript-komponenter - Markdown: Alt lektionsindhold og dokumentation Arkitektur: -…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/de/AGENTS.md
Data Science for Beginners ist ein umfassender 10-wöchiger, 20-teiliger Lehrplan, der von den Microsoft Azure Cloud Advocates erstellt wurde. Das Repository dient als Lernressource, die grundlegende Konzepte der Datenwissenschaft durch projektbasierte Lektionen vermittelt, einschließlich Jupyter-Notebooks, interaktiver Quizze und praktischer Aufgaben. Wichtige Technologien: - Jupyter-Notebooks: Hauptmedium für das Lernen mit Python 3 - Python-Bibliotheken: pandas, numpy, matplotlib für Datenanalyse und Visualisierung - Vue.js 2: Quiz-Anwendung (Ordner quiz-app) - Docsify: Generator für Dokumentationsseiten für den Offline-Zugriff - Node.js/npm: Paketverwaltung für JavaScript-Komponenten -…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/el/AGENTS.md
Το "Data Science for Beginners" είναι ένα ολοκληρωμένο πρόγραμμα σπουδών διάρκειας 10 εβδομάδων και 20 μαθημάτων, που δημιουργήθηκε από τους Microsoft Azure Cloud Advocates. Το αποθετήριο αποτελεί εκπαιδευτικό πόρο που διδάσκει βασικές έννοιες της επιστήμης δεδομένων μέσω μαθημάτων βασισμένων σε έργα, περιλαμβάνοντας Jupyter notebooks, διαδραστικά κουίζ και πρακτικές ασκήσεις. Κύριες Τεχνολογίες: - Jupyter Notebooks: Κύριο μέσο εκμάθησης με χρήση Python 3 - Βιβλιοθήκες Python: pandas, numpy, matplotlib για ανάλυση και οπτικοποίηση δεδομένων - Vue.js 2: Εφαρμογή κουίζ (φάκελος quiz-app) -…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/en/AGENTS.md
Data Science for Beginners is a comprehensive 10-week, 20-lesson curriculum developed by Microsoft Azure Cloud Advocates. This repository serves as a learning resource to teach foundational data science concepts through project-based lessons, including Jupyter notebooks, interactive quizzes, and hands-on assignments. Key Technologies: - Jupyter Notebooks: Primary learning tool using Python 3 - Python Libraries: pandas, numpy, matplotlib for data analysis and visualization - Vue.js 2: Quiz application (located in the quiz-app folder) - Docsify: Documentation site generator for offline access…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/es/AGENTS.md
Data Science for Beginners es un plan de estudios completo de 10 semanas y 20 lecciones creado por los Azure Cloud Advocates de Microsoft. El repositorio es un recurso de aprendizaje que enseña conceptos fundamentales de ciencia de datos a través de lecciones basadas en proyectos, incluyendo notebooks de Jupyter, cuestionarios interactivos y tareas prácticas. Tecnologías Clave: - Jupyter Notebooks: Medio principal de aprendizaje utilizando Python 3 - Bibliotecas de Python: pandas, numpy, matplotlib para análisis y visualización de datos…
Steady48 mentions in 2 weeks
No other project uses it yet
microsoft/Data-Science-For-Beginners/translations/et/AGENTS.md
Andmeteadus algajatele on Microsoft Azure Cloud Advocates'i loodud põhjalik 10-nädalane, 20-õppetunniga õppekava. Repositoorium on õppevahend, mis õpetab projektipõhiste tundide kaudu andmeteaduse põhikontseptsioone, sealhulgas Jupyteri märkmikke, interaktiivseid teste ja praktilisi ülesandeid. Peamised tehnoloogiad: - Jupyteri märkmikud: Peamine õppevahend, kasutades Python 3 - Python'i teegid: pandas, numpy, matplotlib andmete analüüsimiseks ja visualiseerimiseks - Vue.js 2: Testirakendus (quiz-app kaust) - Docsify: Dokumentatsiooni saidi generaator võrguühenduseta kasutamiseks - Node.js/npm: JavaScripti komponentide paketihaldus - Markdown: Kõik õppetundide sisu ja dokumentatsioon Arhitektuur: - Mitmekeelne õppe repositoorium…
Steady48 mentions in 2 weeks
No other project uses it yet
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.