Agent skill
root-instructions
Generate a concise .github/copilot-instructions.md file for a repository by analyzing its codebase structure, tech stack, and conventions.
Install this agent skill to your Project
npx add-skill https://github.com/microsoft/agentrc/tree/main/plugin/skills/root-instructions
SKILL.md
You are an expert codebase analyst generating a .github/copilot-instructions.md file.
Exploration Strategy
Fan out multiple Explore subagents to map out the codebase in parallel:
- Check for existing instruction files: glob for
**/{.github/copilot-instructions.md,AGENTS.md,AGENT.md,CLAUDE.md,.cursorrules,README.md,.github/instructions/*.instructions.md} - Identify the tech stack: look at
package.json,tsconfig.json,pyproject.toml,Cargo.toml,go.mod,*.csproj,*.fsproj,*.sln,global.json,build.gradle,pom.xml, etc. - Understand the structure: list key directories
- Detect monorepo structures: check for workspace configs (npm/pnpm/yarn workspaces, Cargo.toml [workspace], go.work, .sln solution files, settings.gradle include directives, pom.xml modules)
Output Guidelines
Generate concise instructions (~20-50 lines) covering:
- Tech stack and architecture
- Build/test commands
- Project-specific conventions
- Key files/directories
- Monorepo structure and per-app layout (if this is a monorepo, describe the workspace organization, how apps relate to each other, and any shared libraries)
Output Contract
When you have the complete markdown content, call the emit_file_content tool with it. Do NOT output the file content directly in chat.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
area-instructions
Generate a concise .instructions.md file for a specific area of a codebase, scoped to files matching certain patterns.
nested-detail
Generate a deep-dive instruction file about a specific topic for a repository or area.
nested-hub
Generate a lean AGENTS.md hub file for a repository or area, including recommended topics for detail files.
auth
Activate when code touches token management, credential resolution, git auth flows, GITHUB_APM_PAT, ADO_APM_PAT, AuthResolver, HostInfo, AuthContext, or any remote host authentication — even if 'auth' isn't mentioned explicitly.
python-architecture
Activate when creating new modules, refactoring class hierarchies, introducing design patterns, or making changes spanning 3+ files in the APM CLI codebase.
cli-logging-ux
Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (_rich_success, _rich_warning, _rich_error, _rich_info, _rich_echo), DiagnosticCollector, STATUS_SYMBOLS, CommandLogger, or any user-facing terminal output — even if the user doesn't mention "logging" or "UX" explicitly.
Didn't find tool you were looking for?