Implements the MAID methodology for systematic development and TDD workflow.
Install
mkdir -p .claude/skills/role-developer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15917" && unzip -o skill.zip -d .claude/skills/role-developer && rm skill.zipInstalls to .claude/skills/role-developer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Developer role in MAID methodology. Use for implementation, debugging, technical design, TDD workflow, code review.Key capabilities
- →Translate requirements to technical designs
- →Write clean, tested, maintainable code
- →Debug systematically
- →Identify risks and edge cases
- →Perform code reviews
How it works
The skill guides a developer through TDD workflow, systematic debugging, and defense-in-depth principles to produce clean, tested code.
Inputs & outputs
When to use role-developer
- →Implement new feature
- →Debug systematically
- →Follow TDD workflow
- →Perform code review
About this skill
Developer Role
Core Responsibilities
- Translate requirements to technical designs
- Write clean, tested, maintainable code
- Debug systematically - never guess
- Identify risks and edge cases early
Phase Focus
| Phase | Focus | Output |
|---|---|---|
| Discovery | Feasibility | Risk notes, complexity |
| PRD | Requirements clarity | Questions, edge cases |
| Tech Spec | Architecture | Spec, APIs, data models |
| Development | Implementation | Code, tests, docs |
| QA & Ship | Bug fixes | Fixes, deployment docs |
TDD Workflow
RED (Write failing test) -> GREEN (Minimal code) -> REFACTOR (Clean up) -> REPEAT
Systematic Debugging
NO FIXES WITHOUT ROOT CAUSE.
Four Phases
- Root Cause - Read errors, reproduce, gather evidence
- Pattern Analysis - Find working examples, compare
- Hypothesis - Single theory, test minimally
- Implementation - Failing test, single fix, verify
If 3+ fixes failed -> Stop, question architecture.
Defense-in-Depth
Validate at EVERY layer:
| Layer | Purpose |
|---|---|
| Entry Point | Reject invalid at boundary |
| Business Logic | Validate for operation |
| Environment Guards | Block dangerous ops |
| Debug Instrumentation | Log for forensics |
300-Line Rule
| Size | Action |
|---|---|
| < 200 | Ideal |
| 200-300 | Consider splitting |
| 300-400 | Split now |
| > 400 | Must refactor |
Module Structure
feature/
feature.controller.ts # HTTP (thin)
feature.service.ts # Business logic
feature.repository.ts # Data access
feature.types.ts # Types
feature.validation.ts # Validation
Code Quality
Must Have
- Single responsibility
- DRY code
- Priority: Keyboard shortcuts over mouse clicks (Efficiency/Human-like behavior)
- Type hints
- Meaningful names
- Error handling
- Files < 300 lines
Must Not Have
- any types
- TODO/FIXME
- Commented-out code
- Silent exceptions
- Business logic in controllers
- Arbitrary timeouts in tests
Async Testing
// Wrong
await sleep(100);
// Right
await waitFor(() => result !== undefined);
Anti-Patterns
| Anti-Pattern | Fix |
|---|---|
| No TDD | Tests first |
| if is_test in prod | No test logic |
| Happy path only | Test errors |
| Over-mocking | Real dependencies |
| Guessing at fixes | Systematic debug |
| Large files | Split modules |
Handoff Checklist
- All tests passing
- Code reviewed
- Error handling implemented
- Edge cases covered
- Files < 400 lines
- Multi-layer validation
When not to use it
- →When guessing at fixes without root cause analysis
- →When writing code with more than 400 lines in a single file
Limitations
- →Requires adherence to TDD workflow
- →Enforces a 300-line rule for file size
- →Prohibits guessing at fixes without root cause
How it compares
This skill provides a structured methodology for software development, emphasizing systematic debugging and TDD, unlike an unstructured approach.
Compared to similar skills
role-developer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| role-developer (this skill) | 0 | 4mo | No flags | Intermediate |
| qlty-check | 5 | 7mo | Review | Beginner |
| solid | 5 | 6mo | No flags | Advanced |
| code-refactor | 3 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by megori
View all by megori →You might also like
qlty-check
parcadei
Code quality checks, formatting, and metrics via qlty CLI
solid
ramziddin
Use this skill when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging. This skill transforms junior-level code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software design.
code-refactor
luongnv89
Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a phased approach with research, planning, and safe incremental implementation.
improvement
tddworks
Guide for making improvements to existing ClaudeBar functionality using TDD. Use this skill when: (1) Enhancing existing features (not adding new ones) (2) Improving UX, performance, or code quality (3) User asks "improve X", "make Y better", or "enhance Z" (4) Small enhancements that don't require full architecture design For NEW features, use implement-feature skill instead.
tdd-workflows-tdd-refactor
sickn33
Use when working with tdd workflows tdd refactor
moai-workflow-ddd
modu-ai
Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation