agentleFS
Sign inStart free
vlad-ryzhkovvlad-ryzhkov/ai-context-engineering-for-frontend/.github/copilot-instructions.md

ai-context-engineering-for-frontend

Copilot instructions2 starsChanged 8 months agoUnlicenseView on GitHub

ALWAYS prioritize the context defined in CLAUDE.md and .claude/frontend_agent.md. Tech Stack, Core Principles, Safety Protocols: see CLAUDE.md at root (SSOT) GitHub Copilot reads context from open files. To execute a skill: Full project context: CLAUDE.md Skill catalog: .claude/frontend_agent.md

  • Reads credentials

The file

We split this copilot-instructions.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    ALWAYS prioritize the context defined in CLAUDE.md and .claude/frontend_agent.md.

    line 5

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
copilot-instructions.md

AI Context Engineering for Frontend — Copilot Instructions

INSTRUCTIONS FOR GITHUB COPILOT

ALWAYS prioritize the context defined in CLAUDE.md and .claude/frontend_agent.md.

Context

  • Project: AI Context Engineering Template for Vue 3 / React 18
  • Role: Frontend Lead
  • Frameworks: React 18 (TSX) and Vue 3 (SFC with <script setup lang="ts">)
  • Documentation: in English

Tech Stack, Core Principles, Safety Protocols: see CLAUDE.md at root (SSOT)

Anti-Patterns (BANNED)

ProblemWhat to do instead
: any in TypeScriptExplicit interface or unknown
Missing loading stateAll 4 states: loading / error / empty / success
div onClick no role<button type="button">
Hardcoded API URLsimport.meta.env.VITE_API_BASE_URL
v-for without :key:key="item.id" always
useEffect no depsExplicit dependency array [] or [dep]
Options API in Vue 3<script setup lang="ts"> with Composition API

Skills (How to Use)

GitHub Copilot reads context from open files. To execute a skill:

  1. Open the SKILL.md file in the editor
  2. Open the target source file
  3. Type your request in chat
TaskOpen in editor
Generate SPA component (React/Vue).claude/skills/component-gen/SKILL.md
Generate Next.js component.claude/skills/component-gen-next/SKILL.md
Write tests + a11y audit.claude/skills/component-tests/SKILL.md
Bind API.claude/skills/api-bind/SKILL.md
Generate API mocks (MSW).claude/skills/api-mocks/SKILL.md
E2E tests.claude/skills/e2e-tests/SKILL.md
Explore repo.claude/skills/fe-repo-scout/SKILL.md
Browser check (verify running UI).claude/skills/browser-check/SKILL.md
Explore backend repo.claude/skills/be-repo-scout/SKILL.md
Process visual annotations.claude/skills/ui-tweak/SKILL.md
Refactor / migrate code.claude/skills/refactor/SKILL.md
Generate project CLAUDE.md.claude/skills/init-project/SKILL.md
Create PR.claude/skills/pr/SKILL.md

Project Structure

CLAUDE.md                        # Full project context (SSOT)
.claude/frontend_agent.md        # Orchestrator: mindset, routing, protocols
.claude/agents/                  # Engineer + Auditor agent definitions
.claude/skills/                  # Detailed instructions per skill
.claude/fe-antipatterns/         # Anti-pattern reference files
.claude/protocols/gardener.md    # Continuous improvement protocol
examples/                        # React + Vue code examples

Full project context: CLAUDE.md Skill catalog: .claude/frontend_agent.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free