Data Science for Beginners là một chương trình học toàn diện kéo dài 10 tuần với 20 bài học được tạo bởi Microsoft Azure Cloud Advocates. Kho lưu trữ này là một tài nguyên học tập dạy các khái niệm cơ bản về khoa học dữ liệu thông qua các bài học dựa trên dự án, bao gồm Jupyter notebooks, bài kiểm tra tương tác và bài tập thực hành. Công nghệ chính: - Jupyter Notebooks: Phương tiện học tập…
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before writing any code. Heed deprecation notices. This block is written and re-added by next dev — verify at node_modules/next/dist/server/lib/generate-agent-files.js. Removing it from a diff only re-creates the uncommitted change; committing it with your work keeps the tree…
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. Check that the proposed design advances, or at least does not contradict, that product intent. Call out any…
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/managedagents/discovery/runtimemetadata.rs) declares each harness's model/provider/effort env keys and capabilities. Spawn applies…
We recommend developing in a virtual environment managed by uv: List the available skills, and what each one is for, with: Install them with: diffusers-cli skills update refreshes what you installed. Skills used to be installed through the Makefile, which symlinked the project-level .claude/skills and .agents/skills at .ai/skills in this repo. Remove those links if they exist — otherwise the install writes through them into .ai/ itself: At the start of a session, confirm the setup and tell the user…
This repo contains multiple packages, but packages/coding-agent/ is the primary focus. Unless otherwise specified, assume work refers to this package. Terminology: When the user says "agent" or asks "why is agent doing X", they mean the coding-agent package implementation, not you (the assistant). The coding-agent is a CLI tool — questions about its behavior refer to code in packages/coding-agent/, not your current session. Catalog import convention: code in this repo imports catalog values (bundled models, model-thinking helpers, identity, descriptors, model…
For human contributors, see CONTRIBUTING.md. - Do NOT post AI-generated comments on issues or PRs. Discussions are for humans only. - Discuss before implementing: Ensure the implementation direction is agreed upon with maintainers in the issue comments before starting work. - Spec-first coding is mandatory: Before changing behavior, APIs, SDKs, plugins, storage, runtime flow, or domain semantics, AI agents MUST read the relevant specs under specs/ and treat them as the rule source for the implementation. - Discuss spec-impacting changes…
All contributors (human and AI) must follow CONTRIBUTING.md before opening a PR. (Chinese version) See docs/contributing/file-structure.md for complete rules. Agents must also follow the architecture skill (.claude/skills/architecture/SKILL.md) when creating files or modules. Formatting rules (Oxfmt, Prettier-compatible): New or changed user-facing text must use i18n keys; do not introduce hardcoded strings. Languages and modules are defined in packages/desktop/src/common/config/i18n-config.json. See the i18n skill (.claude/skills/i18n/SKILL.md) for complete workflow, key naming, and validation steps. Two process types — never mix their APIs: Cross-process communication…
This file is the repository-wide execution contract for coding agents. book-to-skill converts books and documents into structured, on-demand Agent Skills. The repository has two distinct halves: Do not blur those responsibilities without a measured reason. Before changing code, read the smallest relevant set of files: For the progressive-disclosure research/evaluation initiative, also read: That document is the execution ledger and defines task order, evidence gates, and which paper-derived ideas are hypotheses rather than product requirements. For any non-trivial task, use this…
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 experimentalinstall restores from skills-lock.json. skills experimentalsync crawls node_modules for skills.
Instructions for AI agents working in this repository. A library of 817 cybersecurity skills. Each skill is a directory under skills/ containing a SKILL.md — YAML frontmatter plus a Markdown procedure — following the agentskills.io standard. The layout is flat: skills/<skill-name>/SKILL.md. Do not nest skills by domain; agents discover them by scanning skills/*/SKILL.md. Only name and description load at discovery time. The body loads once the description matches the request; references/, scripts/ and assets/ load only when referenced. Read the…
Most SDK source is generated from the OpenAI API schema. Follow CONTRIBUTING.md before changing generated files. Handwritten policy, automation, tests, and examples should remain small and should not alter exported SDK APIs unless the change explicitly requires it. Follow the custom-code guidance. Budget changes belong in a separate PR containing only .castiron-ratchet.json, with an explicit justification in the PR description. Increases require a human approving review before merging. Agents may investigate and draft proposals, but must not approve budget increases…
Project context (architecture, commands, conventions, tests) is in CLAUDE.md. This file holds the rules for every coding agent working in this repository. cp, mv and rm may be aliased with -i on some systems, which leaves an agent waiting for a y/n answer that never comes. Always pass the non-interactive flag: Other commands that may prompt: scp and ssh (-o BatchMode=yes), apt-get (-y), brew (HOMEBREWNOAUTO_UPDATE=1). This project uses bd (beads) for issue tracking. Run bd prime to see full workflow…
A collection of skills for AI coding agents working with Vercel projects. Skills are packaged instructions and scripts that extend agent capabilities. bash bash /mnt/skills/user/{skill-name}/scripts/{script}.sh [args] Skills are loaded on-demand…
Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find…
MicrosoftAGENTS.md
