This one pushes you to think about security at every layer of development, not just tack it on later. It's organized around five pillars starting with authentication and authorization, covering the fundamentals of who gets in and what they can do once they're there. The core pitch is solid: fixing security bugs in production costs 10x more than catching them during development. If you're building anything that touches user data or needs access controls, this gives you a structured checklist to work through. It's opinionated about security being built in from day one, which honestly more projects need.

GitHub stars
33
last updated
Aug 21, 2026

Install

$ npx -y skills add daffy0208/ai-dev-standards --skill 'Security Engineer' --agent claude-code

Installs into .claude/skills of the current project.

Files

Security Engineer

Security is not optional - build it in from day one.

Core Principle

Security is built-in, not bolted-on.

Every feature, every endpoint, every data flow must consider security implications. Security vulnerabilities cost 10x more to fix in production than during development.

5 Security Pillars

Pillar 1: Authentication & Authorization 🔐

Authentication: Who are you? Authorization: What can you do?

Authentication Strategies

JWT (JSON Web Tokens):

  • When: Stateless APIs, mobile apps, microservices
  • How: Sign tokens with secret, store in httpOnly cookies or Authorization header
  • Security: Use RS256 (not HS256), short expiry (15min access, 7d refresh)
// Example: Next.js API with JWT
import { SignJWT, jwtVerify } from 'jose'

const secret = new TextEncoder().encode(process.env.JWT_SECRET!)

export async function createToken(userId: string) {
  return await new SignJWT({ userId })
    .setProtectedHeader({ alg: 'HS256' })
    .setExpirationTime('15m')
    .sign(secret)
}

export async function verifyToken(token: string) {
  const { payload } = await jwtVerify(token, secret)
  return payload
}

Sponsors

Details

Repository
github.com/daffy0208/ai-dev-standards
Categories
Backend & APIs, Security, DevOps & CI/CD, AI & Agent Building
First seen
Jun 3, 2026

More from daffy0208/ai-dev-standards

All 49
1davila7 avatarMCP Integrationdavila7/claude-code-templatesThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", 0skills.sh installs
2davila7 avatarSQL Injection Testingdavila7/claude-code-templatesThis skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "0skills.sh installs
3FISHers6 avatarsetupFISHers6/clawBro从零引导配置 clawbro-gateway,包括 API Key、默认 Agent、运行模式(Solo/Multi-agent/Team)、Channel(Lark/DingTalk)。无需 fork 或重新编译。0skills.sh installs
4github avatarmcp-implementation-security-reviewgithub/awesome-copilotReview the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions0skills.sh installs
5hoangsonww avatardebug-live-issuehoangsonww/claude-code-agent-monitorDebug production-like issues in this repository with disciplined evidence gathering. Use when fixing failing workflows, regressions, flaky behavior, or data inc0skills.sh installs
6hoodini avatarmeta-adshoodini/ai-agents-skillsPull, analyze, manage, and CREATE Meta ads (Facebook, Instagram, Messenger, Threads, Click-to-WhatsApp) via the Marketing API. Use when the user mentions Meta/F0skills.sh installs