Implementation Standards
SkillAI & modelsGives your agent reference coding standards covering defensive programming, error handling, and test patterns.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Implementation Standards skill
About this skill
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (`.github/agents/_developer.md`); not directly invokable.
What this skill tells your AI
The instructions your AI receives, as published by attilaszasz/sdd-pilot in .github/skills/implementation-standards/SKILL.md and read by ahel’s review.
Core Coding Principles
1. Defensive Coding
- Input Validation: Validate at entry point (Controller/API). Never trust user input.
- Fail Fast: Check preconditions immediately. Throw specific errors, not generic 500s.
- Null Safety: Avoid returning
null. UseOptiontypes or explicit "Not Found" errors.
2. Error Handling
- Structured Errors: Standard format (Code, Message, Details).
- Log Context: Log stack trace AND input parameters on catch.
- No Silent Failures: No empty
catchblocks.
3. Testing Mocks
- External Dependencies: Always mock 3rd party APIs in unit tests.
- Determinism: Tests must run without network access.
Common Patterns
Repository Pattern (Data Access)
interface UserRepository {
findById(id: string): Promise<User | null>
save(user: User): Promise<User>
}
Service Layer (Business Logic)
Contains all domain rules. Never access DB directly from Controller.
class UserService {
constructor(repo: UserRepository)
async register(email: string) {
if (await this.repo.findByEmail(email)) {
throw new DuplicateEmailError()
}
// ... logic
}
}
Context-Window Efficiency
When context budget is tight (late in long implementation runs):
- Targeted reads: re-read specific sections, not entire files.
- Defer optional docs: load
data-model.mdandcontracts/only when current task references them. - Summarize: reference earlier findings by key point, don't re-include full content.
Review Checklist for Agents
Before confirming task "Complete":
- Compiles/runs? (No syntax errors)
- Imports clean? (No unused imports)
- Types explicit? (No
anyorvarif avoidable) - Comments helpful? (Explain "Why", not "What")
Signals
- GitHub stars
- 97
- Forks
- 9
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
implementation-standards- Source
- github.com/attilaszasz/sdd-pilot
github.com/attilaszasz/sdd-pilot
More in AI & models
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsai-first-engineering
Skill · affaan-m
More in AI & models