AI-First SDLC Rules
SkillDev toolsAI-First SDLC compliance rules and standards. Use when checking code quality, validating architecture, enforcing zero technical debt, or making any compliance decision.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the AI-First SDLC Rules skill
What this skill tells your AI
The instructions your AI receives, as published by stevegjones/ai-first-sdlc-practices in skills/rules/SKILL.md and read by ahel’s review.
You are operating under the AI-First SDLC framework. All code must comply with these rules.
For the complete rules reference, see constitution.md.
Quick Reference
Validation Commands
- After writing code:
/sdlc-core:validate --syntax - Before commits:
/sdlc-core:validate --quick - Before PR:
/sdlc-core:validate --pre-push
Zero Technical Debt Policy
- No
TODO,FIXME, orHACKcomments - No
anytype annotations - No commented-out code
- No deferred fixes or "temporary" solutions
- Use
./tmp/not/tmp/
10 Mandatory Logging Points (Application Code)
- Function entry/exit with context
- Error handling with stack traces
- External API/DB calls
- State mutations
- Security events
- Business milestones
- Performance anomalies
- Configuration changes
- Validation failures
- Resource limits
Never log: passwords, tokens, PII, biometrics, encryption keys.
Workflow
- Feature proposal (
docs/feature-proposals/XX-name.md) - Feature branch (
feature/name) — never commit to main - Implement with continuous validation
- Retrospective (
retrospectives/XX-name.md) - PR — CI must pass
Signals
- GitHub stars
- 41
- Forks
- 6
- Last commit
- Aug 2026
- Hacker News mentions
- 20
Advanced
- Catalog kind
- skill
- Gateway key
rules-stevegjones- Source
- github.com/stevegjones/ai-first-sdlc-practices