This file is the single source of truth for agents entering this repository. Read this file first; after entering apps/, packages/, tools/, or e2e/, read that layer's AGENTS.md for module-level details. Do not copy module details back into the root file; root stays focused on cross-repository boundaries, workflow, and commands.
This directory holds design templates — packaged "shapes" the agent renders into a project artifact (decks, prototypes, image/video/audio templates, …). Each entry is a folder with a SKILL.md (same shape as functional skills) plus rendering side files (example.html, assets/, references/, …). If the entry primarily does work on user input — utilities, briefs, asset packagers, fidelity audits — it belongs under ../skills/ instead. See specs/current/skills-and-design-templates.md for the full split. - Listed under /api/design-templates. The shape mirrors /api/skills (same SkillSummary/SkillDetail types)…
Follow the root AGENTS.md first. This package owns user-level end-to-end smoke tests and Playwright UI automation only. For the current coverage posture, recent hardening work, grouped-run status, and known intentional gaps, see docs/testing/e2e-coverage/status.md. For the invariants new and repaired UI tests must hold under the sharded full pool, see UI test stability rules below.
This directory is still only partially standardized. Several historical workflows and helper locations do not yet follow one uniform shape. Do not copy old patterns blindly. For new work, bug fixes, and cleanup, use the ci.yml + comment.atom.yml + autofix.atom.yml + report.atom.yml + .github/scripts/handoff.py system as the reference topology unless a maintainer explicitly chooses a different boundary. Before changing GitHub automation, read the current versions of: If the change affects cross-workflow behavior, update the topology tests instead of relying only…
This directory owns OpenDesign plugin content and plugin authoring material. - When a bundled example's template.json declares format: "html" or carries referenceHtml, commit the real rendered sample as example.html. Do not use a screenshot or placeholder image as the canonical preview for an HTML artifact. - Point od.preview at that source with type: "html" and entry: "./example.html". Use motion: "scroll" for documents, motion: "deck" for slide navigation, and motion: "static" only for a fixed, non-scrolling surface. - Keep od.useCase.exampleOutputs and…
Follow the root AGENTS.md first. Shells are product carriers and user-entry adapters. They may depend on public package contracts, but must not import app-private source or redefine distribution and generation semantics.
This directory holds functional skills — capabilities the agent invokes mid-task to do work on user input. Each skill is a folder with a SKILL.md (frontmatter + body) and any side files (assets/, references/, scripts, …) the workflow needs. If the entry primarily renders a design artifact (deck, prototype, image/video/audio template) it belongs under ../design-templates/ instead. See specs/current/skills-and-design-templates.md for the full split. - Listed under /api/skills (functional only). User-imported skills shadow built-in entries with the same frontmatter name. - Asset…
This file is the root Codex contract for ruvnet/RuView. It complements CLAUDE.md; scoped AGENTS.md files may add local rules but must not weaken the security, evidence, or release requirements here. RuView is a camera-free RF perception system. Production Rust lives in v2/, the Python reference pipeline in archive/v1/, ESP32 firmware in firmware/, the portable contributor harness in harness/ruview/, and the focused Homecore metaharness in harness/homecore/. - Preserve unrelated changes in a dirty worktree. Use an isolated branch/worktree for broad work;…
Tool: mcpclaude-flowagent_list In Claude Code: 1. List all agents: Use tool mcpclaude-flowagentlist 2. Get specific agent metrics: Use tool mcpclaude-flowagentmetrics with parameters {"agentId": "coder-123"} 3. Monitor agent performance: Use tool mcpclaude-flowswarm_monitor with parameters {"interval": 2000}
Use this file as the local operating guide for the current codebase. Prefer the code and the current AGENTS.md over any older convention or remembered project shape.
This file provides guidance to Claude Code (claude.ai/code) when working with the RAGFlow frontend (web/). RAGFlow frontend is a React/TypeScript application built with UmiJS: When tests are grouped in a dedicated directory, that directory is always named tests/ — never tests/. Example: src/pages/agent/utils/tests/extractor-transform.test.ts for src/pages/agent/utils/extractor-transform.ts. Co-located foo.test.ts(x) files next to the source file are also fine. When you find an existing test under a tests/ directory, move it into tests/ (keep git history via git mv) rather than adding new…
The Everything Server is designed to be extended at well-defined points. See Extension Points and Project Structure. The server factory is src/everything/server/index.ts and registers all features during startup as well…
This is Machine Learning for Beginners, a comprehensive 12-week, 26-lesson curriculum covering classic machine learning concepts using Python (primarily with Scikit-learn) and R. The repository is designed as a self-paced learning resource with hands-on projects, quizzes, and assignments. Each lesson explores ML concepts through real-world data from various cultures and regions worldwide. Key components: - Educational Content: 26 lessons covering introduction to ML, regression, classification, clustering, NLP, time series, and reinforcement learning - Quiz Application: Vue.js-based quiz app with pre-…
هذا هو تعلم الآلة للمبتدئين، منهج شامل لمدة 12 أسبوعًا يتضمن 26 درسًا يغطي مفاهيم تعلم الآلة الكلاسيكية باستخدام Python (بشكل أساسي مع Scikit-learn) وR. تم تصميم المستودع كمورد تعليمي ذاتي مع مشاريع عملية، اختبارات، وتمارين. يستكشف كل درس مفاهيم تعلم الآلة من خلال بيانات واقعية من ثقافات ومناطق مختلفة حول العالم. المكونات الرئيسية: - المحتوى التعليمي: 26 درسًا تغطي مقدمة في تعلم الآلة، الانحدار، التصنيف، التجميع، معالجة اللغة الطبيعية، السلاسل الزمنية، والتعلم المعزز - تطبيق الاختبارات: تطبيق اختبارات يعتمد…
Това е Машинно обучение за начинаещи, цялостна 12-седмична програма с 26 урока, обхващаща класически концепции за машинно обучение с помощта на Python (основно със Scikit-learn) и R. Репозиторият е създаден като ресурс за самостоятелно обучение с практически проекти, тестове и задачи. Всеки урок разглежда концепции за машинно обучение чрез реални данни от различни култури и региони по света. Основни компоненти: - Образователно съдържание: 26 урока, обхващащи въведение в машинното обучение, регресия, класификация, клъстеризация, NLP, времеви серии и обучение чрез подсилване…
MicrosoftAGENTS.md
