MicrosoftCLAUDE.mdSqlScriptDOM
microsoft/SqlScriptDOM/CLAUDE.md
No summary in the file. Open it to read it.
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Most stars first · from page 3Worked for most · soon
MicrosoftCLAUDE.mdMicrosoftCLAUDE.mdfinnts
microsoft/finnts/CLAUDE.md
No summary in the file. Open it to read it.
MicrosoftCLAUDE.mdSico / frontend
microsoft/Sico/frontend/CLAUDE.md
The canonical Sico frontend lives in frontend/ inside the Sico monorepo. It is a pnpm + Turborepo workspace for the application and shared frontend packages. React 19 + TypeScript 5.9, Vite 6 + SWC, Tailwind v4, tsgo + oxlint + ESLint + oxfmt, Vitest + RTL + Playwright, Storybook 9, @tanstack/react-router, jotai + immer, react-query + axios, zod, react-error-boundary. Dependency chain: @sico/app → @sico/shared → @sico/ui → @sico/config. pnpm install → pnpm dev / pnpm lint / pnpm test (turbo-orchestrated…
MicrosoftCLAUDE.mdSico / app
microsoft/Sico/frontend/packages/app/CLAUDE.md
Sico frontend application — TanStack Router file-based routing, Jotai state, react-query + axios data layer, zod validation. npm run dev / build / preview / lint / test / test:build / e2e (Playwright builds first). Depends on: @sico/ui, @sico/shared, @sico/config (dev) · Depended on by: none (leaf).
MicrosoftCLAUDE.mdSico / config
microsoft/Sico/frontend/packages/config/CLAUDE.md
Shared engineering configuration. Contains no runtime code and has no scripts — consumed by other packages only. Do not modify these config files casually. They are the single source of truth for engineering standards — every change ripples to every consumer. If a package needs different behavior, override at the consumer instead of editing the base: Depends on: none (zero deps) · Depended on by: @sico/ui, @sico/shared, @sico/app.
MicrosoftCLAUDE.mdSico / shared
microsoft/Sico/frontend/packages/shared/CLAUDE.md
Cross-app code that's not pure UI — hooks, atoms, services, schemas, composer components, and full feature implementations. DWP (superset app) consumes features from here directly. npm run dev (Storybook :6007) / lint / test / build-storybook. Depends on: @sico/config (dev), @sico/ui · Depended on by: @sico/app.
MicrosoftCLAUDE.mdSico / ui
microsoft/Sico/frontend/packages/ui/CLAUDE.md
Design tokens + Atomic components for SICO. React 19 + Tailwind CSS v4 + shadcn/ui restyles. npm run dev (Storybook :6006) / lint / test / build-storybook. Each component is a 4-file unit: Development is driven by skills. Always invoke the relevant skill before writing code. Depends on: @sico/config (dev) · Depended on by: @sico/shared, @sico/app.
MicrosoftCLAUDE.mdDataverse-skills
microsoft/Dataverse-skills/CLAUDE.md
This repo ships a plugin for Claude Code and GitHub Copilot that provides AI-assisted Dataverse / Power Platform development. The plugin consists of skill files (SKILL.md) that teach the agent how to use the Python SDK, PAC CLI, MCP server, and Dataverse Web API. The plugin is loaded via: Skill files live under .github/plugins/dataverse/skills/<skill-name>/SKILL.md. Run the static eval suite. It checks every skill file for code correctness, auth pattern compliance, and routing consistency: Exit code 0 = all checks pass.…
MicrosoftCLAUDE.mdAutoSaddler / autosaddler
microsoft/AutoSaddler/src/autosaddler/v1/proposer/autosaddler/CLAUDE.md
A harness is the agent codebase that wraps an LLM to solve benchmark tasks — it includes the system prompt, tool definitions (docstrings), tool implementations, agent loop logic, and hook configurations. The harness determines how the LLM perceives tools, plans actions, and handles edge cases. A candidate is a specific version of this harness codebase, stored as an isolated git worktree. This pipeline iteratively optimizes a harness to improve its performance on a target benchmark. Each iteration evaluates a candidate…
MicrosoftCLAUDE.mdP.808
microsoft/P.808/CLAUDE.md
Before making any changes to this repository, read and follow the coding standards in .github/copilot-instructions.md. This repository defines reusable agent runbooks in .github/agents/. When a user asks to create a study, run a test, or set up a subjective quality experiment, follow the instructions in the relevant agent file. When triggered, read the full agent file and execute its workflow step by step.
MicrosoftCLAUDE.mdAgents-for-python
microsoft/Agents-for-python/CLAUDE.md
This is the Microsoft 365 Agents SDK for Python, a framework for building enterprise-grade conversational agents for M365, Teams, Copilot Studio, and other platforms. The SDK replaces the legacy Bot Framework SDK (botbuilder packages) with a modern, modular architecture. Important: Python imports use underscores (microsoft_agents), not dots (microsoft.agents). Quick setup (Linux/macOS): Quick setup (Windows): Manual setup (from repository root): Python version: Requires Python 3.10+, supports 3.10-3.14. Recommended: Python 3.11+ The SDK follows a layered, modular architecture with clear separation of…
MicrosoftCLAUDE.mdrust-guidelines
microsoft/rust-guidelines/CLAUDE.md
This repository contains the Pragmatic Rust Guidelines - a collection of design guidelines for Rust developers, published as an mdBook at https://microsoft.github.io/rust-guidelines. Requires mdbook to be installed. Each guideline has a unique identifier in the form M-FOO-BAR and resides in its own markdown file M-FOO-BAR.md within the src/guidelines/ directory. Guidelines follow this structure: Guidelines should be beneficial for safety/COGs/maintenance, agreeable to experienced Rust developers, and comprehensible to novices. Titles should follow the style of the Rust API Guidelines, such as:
MicrosoftCLAUDE.mdAgents-for-net
microsoft/Agents-for-net/CLAUDE.md
See .github/copilot-instructions.md for build commands, architecture, conventions, and coding guidelines for this repository.
MicrosoftCLAUDE.mdfabric-cli / context
microsoft/fabric-cli/.ai-assets/context/CLAUDE.md
Context for Claude Code helping users work with the Fabric CLI. Copy or symlink to CLAUDE.md or .claude/CLAUDE.md. Fabric CLI (fab) is a command-line tool for Microsoft Fabric with interactive (REPL) and command-line modes. Filesystem-like hierarchy with dot entity suffixes: Switch: fab config set mode interactive or fab config set mode cli Dot-prefixed, not shown by default. Use ls -a to view. Config files in ~/.config/fab/: - cache.bin - encrypted token cache - config.json - CLI settings - auth.json -…
MicrosoftCLAUDE.mdsimplechat
microsoft/simplechat/CLAUDE.md
SimpleChat is a Flask web application using Azure Cosmos DB, Azure AI Search, and Azure OpenAI. It supports personal, group, and public workspaces for document management and AI-powered chat. **Every…
MicrosoftCLAUDE.mdvscode-copilotstudio
microsoft/vscode-copilotstudio/CLAUDE.md
Shared AI-agent guidance for this repository lives in AGENTS.md. Claude Code users and agents should follow AGENTS.md.
MicrosoftCLAUDE.mdagentic-agile-template / claude
microsoft/agentic-agile-template/platform-adapters/agent-tools/claude/CLAUDE.md
This is an agent context file. It provides AI coding agents (GitHub Copilot, Claude, Cursor, or any LLM-based development tool) with the information they need to work effectively in your repository. Think of it as onboarding documentation, but optimized for agents: structured, explicit, and maintained alongside your code. WHY DOES IT MATTER? Without an agent context file, every agent session starts from zero. The agent must infer your conventions, guess your architecture, and hope its assumptions match yours. With a…
MicrosoftCLAUDE.mdthinkingbox
microsoft/thinkingbox/Claude.md
A test case includes: - definition of a task for an agent to complete - test code to verify that the task was completed successfully Test cases are part of a ThinkingBox dataset, they are distinct from unit tests. This section only applies to test cases. You'll see tests like this: There are several parts to this test: Good tests should test meaningful side effects from running the test case. They should allow the model to be flexible in how…
MicrosoftCLAUDE.mdazure-devops-rust-api
microsoft/azure-devops-rust-api/CLAUDE.md
Auto-generates a Rust Azure DevOps API crate (azuredevopsrust_api) from the Azure DevOps OpenAPI spec (vsts-rest-api-specs, included as a git submodule). The pipeline is: Do NOT edit generated files directly — they are overwritten by ./build.sh: - azuredevopsrustapi/src/<module>/mod.rs — generated API operations - azuredevopsrustapi/src/<module>/models.rs — generated model types Hand-written source (edit these directly): - azuredevopsrustapi/src/auth.rs — Credential enum (PAT + OAuth) - azuredevopsrustapi/src/datetime.rs — datetime serde helpers - azuredevopsrustapi/src/telemetry.rs — telemetry pipeline policy - azuredevopsrustapi/src/headers.rs — common header helpers - azuredevopsrustapi/src/artifacts_download/…
MicrosoftCLAUDE.mdteams.py
microsoft/teams.py/CLAUDE.md
Microsoft Teams Python SDK — a UV workspace with multiple packages providing APIs, common utilities, and integrations for Microsoft Teams. Imports - ALL imports MUST be at the top of the file — no imports inside functions, classes, or conditional blocks - Avoid TYPE_CHECKING blocks unless absolutely necessary (genuine circular imports that can't be restructured) - Avoid dynamic/deferred imports unless absolutely necessary - Relative imports within the same package, absolute for external packages Models - Pydantic with ConfigDict(aliasgenerator=tocamel) — snakecase…
About CLAUDE.md
What is CLAUDE.md?
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.