This markdown is meant to be given to an AI agent (Claude, Copilot, Junie, etc.) so it can generate all supporting repository markdown files needed for effective agent-assisted development.
The agent should read this document and then create the following files in the repository:
- README.md
- CONTRIBUTING.md
- ARCHITECTURE.md (or docs/architecture.md)
- AGENTS.md
- WORKFLOWS.md
- SPEC.md
- STYLEGUIDE.md
- SECURITY.md
- CODE_OF_CONDUCT.md (optional)
- Any tool-specific instruction files (e.g., .github/copilot-instructions.md)
Create high-quality, practical, concise markdown files that enable AI agents, developers, and collaborators to understand, use, refactor, and extend the repository.
Focus on clarity, structure, modularity, and actionable details.
Provide:
- Purpose of the project
- Tech stack
- Features
- Folder structure
- Setup instructions
- Development commands
- Testing commands
- Deployment instructions
Include:
- Branch naming rules
- PR rules
- Commit conventions
- Testing expectations
- Code quality expectations
- How to run linting, formatting, type-checking
- How agents should interact with PRs
Document:
- High-level system overview
- Modules and responsibilities
- Data flow or request flow
- Diagrams (mermaid preferred)
- If multiple services exist: boundaries and contracts
Describe:
- Agent roles and boundaries
- How they should collaborate
- What context they must read before acting
- What files they must update
- Guardrails (what not to touch)
- Definitions of done
Explain:
- CI/CD steps
- Testing pipeline
- Release process
- Branching strategy
- Any automation
Define:
- APIs
- Models
- Business rules
- Domain vocabulary
- Acceptance criteria
- UX flows if relevant
Specify:
- Coding standards
- Naming conventions
- Folder structure rules
- Linting rules
- Example good patterns
- Example bad patterns
Include:
- How to report vulnerabilities
- Dependency update strategy
- Secrets handling guidelines
- Security expectations for PRs
Generic template suitable for open-source or internal use.
If applicable, agent should generate:
.github/copilot-instructions.md.copilot/config.json(if needed).claude/config.mdorCLAUDE.mdfor Claude environments
Each should define:
- Style preferences
- Context requirements
- Include/exclude file patterns
- Operating mode of the agent
When generating the files, the agent should output each file in its own fenced markdown block, example:
# FILE: README.md
<content># FILE: CONTRIBUTING.md
<content>- Professional
- Highly practical
- No unnecessary prose
- No philosophical explanations
- No motivational text
- Direct instructions only
The agent should now generate all required markdown files.