How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
ashp15205Copilot instructionsashp15205/vibe-coding-essentials/templates/copilot-instructions.md
This project uses: **[set your stack]** Apply framework-specific best practices for these versions. ## Code Style Follow the existing patterns in the file being edited: - Match naming conventions already
Microsoft AzureCopilot instructionsAzure/setup-azd/.github/copilot-instructions.md
setup-azd — Instructions for Copilot Chat and Copilot code review For any work in this repository, especially release work and code reviews, you MUST read [AGENTS.md](../AGENTS.md) in its entirety
event4u-appCopilot instructionsevent4u-app/agent-config/.github/copilot-instructions.md
Copilot Chat to read those > files. The instructions below are self-contained for Copilot Code Review, > which cannot follow links. ## ✅ What this repo contains - **Bash** scripts under `src/scripts/install.sh` and `src/scripts/condense.sh
kurone-kitoCopilot instructionskurone-kito/idd-skill/.github/copilot-instructions.md
GitHub Copilot execution surfaces because it has `applyTo: "**"`, but it is excluded from Copilot code review with `excludeAgent: "code-review"` so reviewer-side context stays lighter. Open the routed phase
paulasilvatechCopilot instructionspaulasilvatech/awesome-harness-primitives/.github/copilot-instructions.md
primitive-architect` agent owns read-only classification, composition review, and responsibility-boundary advice. - The `create-copilot-primitive` prompt is a VS Code-only guided entry point. - Scripts
wuemaikblumeCopilot instructionswuemaikblume/dsgvo-skills/codex/copilot-instructions.md
east-1`) - **Variante B** — DSGVO-konform (EU-Region + Fail-closed-Whitelist) 3. **Über dem Code als Bullet-Liste** die DSGVO-Pflichten vor Production: - Rechtsgrundlage (Art. 6 / Art. 9) - DPF-Status
Aryanpanwar10005Copilot instructionsAryanpanwar10005/seo-geo-optimizer/.github/copilot-instructions.md
explicit written approval from the user before writing a single line of code, configuration, markup, or content. **LAW 5 — ZERO AUTONOMOUS CHANGES** Never make any change — not a "small
Microsoft AzureCopilot instructionsAzure/apim-policy-update/.github/copilot-instructions.md
relevant issues or discussions - Any additional context that may be helpful for reviewers ## Code Review Guidelines When performing a code review, please follow these guidelines: - If there are changes that
daveshefferCopilot instructionsdavesheffer/hunch/.github/copilot-instructions.md
Copilot instructions ## 🧠 Hunch (Engineering Memory) This repo has **Hunch**, a graph of *why* the code is the way it is. It holds **337 decisions, 2 bugs, 31 constraints, 22 components
fritzprixCopilot instructionsfritzprix/libr-agent/.github/copilot-instructions.md
refactoring work to ensure code quality and build integrity.** **Workflow Recommendation:** After making any code changes, always run: ```sh pnpm refactor:validate ``` **Execution rule:** Prefer repository `pnpm` scripts for validation
mantacronCopilot instructionsmantacron/manta/.github/copilot-instructions.md
Copilot Instructions — Manta This project uses Manta: an automated code review pipeline. Copilot is used for writing code; the agent pipeline runs automatically via git hooks (Claude Code). --- ## Principles
mattbaconzCopilot instructionsmattbaconz/signal/.github/copilot-instructions.md
when asked: **`signal-commit`**, **`signal-push`**, **`signal-pr`**, **`signal-review`**, **`signal-ckpt`**, **`signal-compress`** (scripts support `--dry` / `--draft`). - Never compress: code blocks, file paths, line numbers, quoted errors, technical terms
MicrosoftCopilot instructionsmicrosoft/slack-plus-teams/.github/copilot-instructions.md
Copilot Code Review Instructions ## Review philosophy **Approve by default.** This is a fast-moving project with example code and knowledge-base Markdown. Only flag issues that would cause runtime failures
autovantCopilot instructionsautovant/superpowers/.github/copilot-instructions.md
development**: skills/subagent-driven-development/SKILL.md - **test-driven-development**: skills/test-driven-development/SKILL.md - **systematic-debugging**: skills/systematic-debugging/SKILL.md - **verification-before-completion**: skills/verification-before-completion/SKILL.md - **requesting-code-review**: skills/requesting-code-review/SKILL.md - **receiving-code-review**: skills/receiving-code-review/SKILL.md - **using-git-worktrees**: skills/using-git-worktrees/SKILL.md - **finishing-a-development-branch**: skills/finishing-a-development-branch/SKILL.md
dgenioCopilot instructionsdgenio/contextweaver/.github/copilot-instructions.md
specific guidance. Do not treat this file as a standalone reference. ## Review-Critical Rules - **Review code and agent docs together.** When a PR changes behavior that agent-facing docs describe
LazyWorkshopCreateCopilot instructionsLazyWorkshopCreate/agent-based-workflow/.github/copilot-instructions.md
Review feedback to process?** → `Process Review Feedback` 22. **Ready for review handoff?** → `Request Code Review` --- ## Lifecycle Extension Points This delivery lifecycle covers the design-to-code-to-review cycle
magicpro97Copilot instructionsmagicpro97/vibeflow/.github/copilot-instructions.md
destructive/free-handed actions; `vf doctor` shows ON/OFF). **Working with vf — Confidence gate (MANDATORY):** After ANY code edit, and BEFORE you claim a task is done, YOU MUST run `vf verify
MicrosoftCopilot instructionsmicrosoft/purview-dlm-mcp/.github/copilot-instructions.md
learn` | "how do I create a retention policy", "what is eDiscovery" | | Asks to review commands run | `get_execution_log` | "show me what we ran", "summarize the investigation" | - **Default
NAJEMWEHBECopilot instructionsNAJEMWEHBE/unreal-ai-connection/.github/copilot-instructions.md
constraints below. These mirror the conventions already applied by the human + Codex + Gemini review loop; align with them rather than re-litigating settled patterns. ## What this repo
prasad-vennamCopilot instructionsprasad-vennam/Awesome-Android-AI-Agent-Skills/.github/copilot-instructions.md
data layer, domain models, or business logic for Android apps. - **File Path**: `skills/android-clean-architecture/SKILL.md` ## android-code-review-expert - **Scope**: Use when performing a code review for Android pull requests, focusing
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.
