physical-ai-toolchain
microsoft/physical-ai-toolchain/.github/copilot-instructions.md
Required general instructions for entire codebase and project
How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
microsoft/physical-ai-toolchain/.github/copilot-instructions.md
Required general instructions for entire codebase and project
Azure-Samples/snippy/.github/copilot-instructions.md
/fan-in paths. - Keep test payloads small; embed them inline rather than external files. # 👉 Code-review instructions - Verify no synchronous APIs are accidentally `await`ed. - Ensure every orchestrator is registered
canonical/workshop/.github/copilot-instructions.md
This file provides general project context for GitHub Copilot. For review-specific guidance, see: - **Code Review**: `.github/agents/code-review.agent.md` - **Documentation Review**: `.github/skills/documentation-review/SKILL.md` ## Project Overview Workshop is a tool for defining and handling
Azure/LogicAppsUX/.github/copilot-instructions.md
open any listed file whose triggers match the task domain (git/worktree, e2e, CI, reviews, customer repro, unit tests, etc.). - For non-trivial work also follow the chief-engineer charter
microsoft/Agent365-Samples/.github/copilot-instructions.md
GitHub Copilot Instructions for Agent365-dotnet ## Code Review Rules ### Rule 1: Check for "Kairo" Keyword - **Description**: Scan code for any occurrence of the keyword "Kairo" - **Action**: If "Kairo" is found
microsoft/PromptKit/.github/copilot-instructions.md
asks you to perform a task that this library supports (writing requirements, investigating bugs, reviewing code, etc.), use the `/promptkit` skill (or read and execute `bootstrap.md`). It is the entry
javiarmesto/ALDC-AL-Development-Collection/.github/copilot-instructions.md
enabled: false` skips every probe. Plugin mode loads the exact configured skill (default `al-code-review`); multiroot reads the configured external Entry. Keep full native A–G until actual results
javiarmesto/ALDC-AL-Development-Collection/instructions/copilot-instructions.md
English** — All persisted documents generated by the pipeline (`architecture.md`, `spec.md`, `plan.md`, `phase-N-complete.md`, `plan-complete.md`, `test-plan.md`, code reviews, deliveries) MUST be written in English regardless of the chat conversation language. Inline chat
microsoft/vscode-isort/.github/copilot-instructions.md
tests pass before submitting changes. - Always ensure documents and code are linted before submitting. - Do multiple rounds of review and refinement. - Do not feature creep — keep changes focused
harness/harness-skills/.github/copilot-instructions.md
Harness Skills This repository contains Claude Code skills for working with Harness.io CI/CD platform. All skills use the Harness MCP v2 server's consolidated tool interface. ## MCP v2 Server
nebrass/hve-video-director/.github/copilot-instructions.md
agent skill** (`hve-video-director`) that runs on both **GitHub Copilot CLI** and **Claude Code**, not a typical application. The "source" is prompt content (markdown) plus Python helper scripts. There
csmar432/finai-research/.github/copilot-instructions.md
根据用户回复执行操作 **API Key 缺失**:AI 在对话中询问,用户回复后执行配置或继续 **LLM 不可用**:AI 在对话中展示问题 + 修复步骤,询问是否继续 > Claude Code 和 Codex 不支持 `input()`,必须通过对话交互。 --- ## 项目结构 ``` scripts/ ├── health_check.py # 系统诊断(每次启动时运行) ├── setup_wizard.py # 交互式配置向导 ├── agent_pipeline.py # 主编排器 ├── research
microsoft/haste/.github/copilot-instructions.md
instructions are automatically loaded into EVERY Copilot session # (VS Code, Copilot CLI, Cloud Agent, Code Review). # Keep them concise and universally applicable. ## Project Overview - **Name**: HASTE (High-speed Assessment
raphaelmansuy/adk_training/.github/copilot-instructions.md
leading spaces or tabs). For indented code blocks, use <<- 'EOF' instead, and indent content/delimiter with tabs only (not spaces). Review and unindent the delimiter before suggesting execution. - VERY Important: Avoid
Habitat-Thinking/ai-literacy-superpowers/.github/copilot-instructions.md
commit on the branch must contain only a spec file in `docs/superpowers/specs/`. No implementation code may appear in that commit. Bug-fix, dependency, and maintenance PRs (labelled `bug`, `fix`, `chore
microsoft/vscode-pylint/.github/copilot-instructions.md
tests pass before submitting changes. - Always ensure documents and code are linted before submitting. - Do multiple rounds of review and refinement. - Do not feature creep — keep changes focused
microsoft/webui/.github/copilot-instructions.md
full docs synchronization workflow, use the skill: `skills/docs-sync/SKILL.md`. --- ## Skills - **Pull request** - `skills/pr/SKILL.md` - **Code review** - `skills/code-review/SKILL.md` (includes FFI safety and protobuf hygiene) - **Error handling & diagnostics** - `skills/diagnostics/SKILL.md` - **Quality gate** - `skills/quality-gate/SKILL.md` - **Docs synchronization
microsoft/Microsoft-AI-Decision-Framework/.github/copilot-instructions.md
Overall guidelines about the project.
microsoft/vscode-powerquery-sdk/.github/copilot-instructions.md
implement the task. Ask the user to review the plan. Revise the plan based on feedback. - **Wait for Approval**: Do not start coding until the user explicitly says "Execute
uscensusbureau/us-census-bureau-data-api-mcp/.github/copilot-instructions.md
Provide expert-level review of the repository's structure, technology stack, and critical patterns, with a focus on Model Context Protocol (MCP) best practices - Highlight any non-obvious dependencies
Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.
How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.
No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.
Open a file to see its discussion. Reports from people and their agents are coming.