coding-guidelines-gen

Nymbo's avatarfrom Nymbo

Generate nested AGENTS.md coding guidelines per module (monorepo-aware), detect languages/tooling, ask architecture preferences, and set up missing formatters/linters (Spotless for JVM).

⭐1stars🔀0forks📁View on GitHub🕐Updated Dec 20, 2025
[Architecture Design]

When & Why to Use This Skill

This Claude skill automates the generation of module-level coding guidelines and architectural boundaries within complex monorepos. By creating nested AGENTS.md files, it establishes clear architecture preferences (such as Clean, Hexagonal, or Layered styles) and ensures codebase consistency. It also streamlines developer workflows by detecting project tooling and automatically configuring essential linters and formatters like Spotless for JVM environments.

Use Cases

  • Monorepo Standardization: Automatically scan and generate localized coding guidelines for multiple modules to maintain consistency across large-scale projects.
  • Architectural Boundary Enforcement: Define and document strict dependency rules (e.g., preventing domain layers from importing infrastructure) to preserve system integrity.
  • Automated Environment Setup: Detect missing development tools and automatically configure best-practice formatters and linters for Java and Kotlin modules.
  • AI-Agent Integration: Create machine-readable 'codex-guidelines' blocks that allow other AI agents to verify code quality using runnable commands.
namecoding-guidelines-gen
descriptionGenerate nested AGENTS.md coding guidelines per module (monorepo-aware), detect languages/tooling, ask architecture preferences, and set up missing formatters/linters (Spotless for JVM).

Coding guidelines generator

Goal

Create nested AGENTS.md files (not repo root) that define:

  • architecture preferences + boundaries (high level)
  • formatting/lint/testing commands (runnable)
  • a small verifiable config block the verifier skill can execute

Minimal questions to ask (don’t skip)

  • Where are the module roots? (Confirm the folders that should each get an AGENTS.md; avoid repo root unless explicitly requested.)
  • Architecture style: layered / hex / clean (pick one) and any hard boundaries (e.g., domain/ must not import infra/).
  • OK to add tooling when missing? (default: yes; Spotless for Java/Kotlin)
  • Default commands: format / lint / test for each module (changed-files-first where practical).

Workflow (monorepo-aware)

  1. Scan for candidate modules and languages.
    • Use scripts/scan_modules.py to produce a quick inventory.
  2. Propose the nested AGENTS.md placement(s) and get confirmation.
    • If the only detected module is repo root, suggest a subdir (e.g., src/, apps/<name>/, packages/<name>/) or ask the user where the code “starts”.
  3. For each confirmed module root:
    • Create/update <module>/AGENTS.md using references/agents-template.md.
    • Fill the codex-guidelines JSON block (schema: references/verifiable-block.md) with runnable commands.
  4. Ensure formatting + linting exist (prefer existing; otherwise add best-practice defaults).
    • JVM (Gradle/Maven): add/configure Spotless (see references/spotless.md).
    • Others: pick a minimal, common default and wire commands into AGENTS.md (see references/language-defaults.md).

Output

  • One AGENTS.md per module root (nested scope).
  • Minimal tool config changes only where tooling is missing (format/lint first).