#best-practices

Roblox Luau AI Agent Standards and Static Checker Toolkit 2026

Safe, review-first team setup for Codex, Claude Code and Cursor. Portable instructions, backups, recovery and vetted public skill recommendations.

Pre-deploy checklists for AI coding agents. Catch security holes, broken auth, and payment bugs before they hit production.

Vue 3 best-practice agent skills for AI coding agents — Composition API, Router 5, Pinia 4, Vitest 4 — plus an MCP server and eval suite

A Claude Code skill that writes and reviews your README.

Markdown-only engineering baseline for AI agents: how to build Go + htmx + pure-CSS web applications, CLI tools, and libraries — production grade, simplicity first, secure by default. Servers and deployment live in baseline-ops. Adversarially reviewed until zero defects, against an executable reference implementation.

Professional Roblox and Luau standards for AI agents, and a zero-dependency Luau checker that runs without one.

Professional Roblox and Luau standards for AI agents, and a checker that runs without one.

Opinionated CLAUDE.md rules and templates for shipping real products with Claude Code — from the trenches of MedKompas and newforms.

2026OpenAI官方提示词最佳实践简体中文翻译

AI AgenticSafe - stop your AI agent from breaking production at 3 a.m. 8 battle-tested doctrines, 3 real post-mortems, zero dependencies. By Yacine Mahboub, Founder of WEVIA.

A curated, verified CLAUDE.md best-practices template for Claude Code — refreshed regularly. Copy it into your project.

Defense-in-depth security rules AI coding agents can follow, and verify. 25 rule chapters, checklists, drop-in CLAUDE.md, self-verification test patterns.

Technology-neutral playbook and templates for AI agents that publish, secure, document, release, and maintain open-source repositories.

Amir Hadifar's personal blog on AI, ML, agents, LLMs, and agentic software development.

Deep, self-verifying React Native & Expo engineering skills for AI coding agents — 79 skills with checkers that prove the work: architecture, Expo Router, Zustand, TanStack Query, testing, i18n/RTL, accessibility, EAS releases & more. Agent Skills open standard; works with Claude Code, Cursor, Codex & 70+ agents.

Copyable Claude Code + GitHub Copilot configuration: AGENTS.md operating manual, CLAUDE.md, copilot-instructions, rules, skills, subagents, hooks, and a gated 7-stage SDLC (spec review, self code review, PR-bot triage). Token-efficient agentic coding you vendor into your repo and adapt with /adopt.