by luoling8192
A collection of Claude Code skills that enforce coding discipline and prevent common AI coding anti-patterns.
# Add to your Claude Code skills
git clone https://github.com/luoling8192/ai-coding-principlesGuides for using ai agents skills like ai-coding-principles.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:56:07.299Z",
"npmAuditRan": true,
"pipAuditRan": true
}ai-coding-principles is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by luoling8192. A collection of Claude Code skills that enforce coding discipline and prevent common AI coding anti-patterns. It has 166 GitHub stars.
Yes. ai-coding-principles passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/luoling8192/ai-coding-principles" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ai-coding-principles against similar tools.
No comments yet. Be the first to share your thoughts!
A collection of Claude Code skills for coding discipline and system design knowledge.
Mandatory rules loaded during all code writing tasks that prevent common AI coding anti-patterns.
| # | Rule | Summary |
|---|---|---|
| 1 | No Silent Fallbacks | Don't use ?? / ` |
| 2 | No Catch-All try/catch | Business logic lets errors propagate; catch only at API boundaries |
| 3 | Tests Must Fail When Code Breaks | Verify specific outcomes, not just existence |
| 4 | No Hardcoded Lookup Tables | Implement real logic, not test-case-fitting shims |
| 5 | Red-Green Testing (TDD) | Write failing test first, then fix |
| 6 | Don't Remove Debug Logs During Fix | Logs stay until human confirms the fix works |
Distilled reference guide based on Martin Kleppmann's Designing Data-Intensive Applications. Loaded when designing database schemas, choosing storage engines, implementing replication/partitioning, handling distributed transactions, or building batch/stream processing pipelines.
| Part | Topics |
|---|---|
| I: Foundations | Reliability, Scalability, Maintainability; Data Models & Query Languages; Storage & Retrieval (B-tree vs LSM-tree, OLTP vs OLAP); Encoding & Evolution |
| II: Distributed Data | Replication (single/multi-leader, leaderless); Partitioning (key-range, hash, compound); Transactions & Isolation Levels; Distributed System Challenges; Consistency & Consensus |
| III: Derived Data | Batch Processing (MapReduce, Spark, Flink); Stream Processing (Kafka, CDC, Event Sourcing); Data Integration Patterns |
npx skills add luoling8192/ai-coding-principles