# Codema

> The publisher for AI, tech and finance-tech. English and French.

- [Home](https://codema.ai/)
- [Accueil](https://codema.ai/fr/)
- [AI](https://codema.ai/ai.html)
- [Tech](https://codema.ai/tech.html)
- [Finance](https://codema.ai/finance.html)
- [Resources](https://codema.ai/resources/)
- [Ressources](https://codema.ai/fr/resources/)
- [Search](https://codema.ai/search.html?q={search_term_string})

## English

- [10 copy-paste AI coding prompts to ship a web app](https://codema.ai/articles/10-copy-paste-prompts-ship-web-app-with-ai.html): Ten copy-paste AI coding prompts that take a web app from idea to production in Cursor, Claude Code or Codex: plan, schema, auth, tests, security, launch. (Skills & Prompts)
- [How to build a bilingual app for Quebec with AI: French rules and Law 25](https://codema.ai/articles/building-with-ai-in-french-quebec.html): How to build a bilingual app for Quebec with AI: OQLF French-language rules, Law 25 privacy duties, Next.js i18n patterns and resources. (Build Guides)
- [What is MCP? The Model Context Protocol explained for vibe coders](https://codema.ai/articles/mcp-explained-for-vibe-coders.html): What is MCP? The Model Context Protocol lets your coding agent use real tools like your database. How it works, how to connect a server, and how to stay safe. (Build Guides)
- [Own your code and data: why it matters when you build with AI](https://codema.ai/articles/own-your-code-and-data-building-with-ai.html): AI makes software cheap to build, so ownership matters more. Why to own your code and data, how to avoid vendor lock-in, and a checklist to get there. (Opinion)
- [Cursor vs Claude Code vs Codex: how to pick an AI coding agent](https://codema.ai/articles/picking-a-coding-agent-cursor-claude-code-codex.html): Cursor vs Claude Code vs Codex vs GitHub Copilot: how these AI coding agents differ in where they run, and how to choose one without lock-in. (Tools)
- [Predictive creative testing: how to test AI ad creatives before you spend](https://codema.ai/articles/predictive-creative-testing-ai-ad-creatives.html): Predictive creative testing uses AI to generate and pre-score ad creatives, then confirms the winners with real Google Ads or Meta experiments. (Build Guides)
- [How to review AI-generated code before production: a checklist](https://codema.ai/articles/review-ai-written-code-before-production.html): A practical routine to review AI-generated code before production: access control first, then secrets, dependencies, errors, and agents reviewing agents. (Build Guides)
- [How to vibe code a SaaS with Supabase and Vercel in a weekend](https://codema.ai/articles/vibe-code-saas-supabase-vercel-weekend.html): A two-day plan to vibe code a SaaS with an AI agent, Next.js, Supabase and Vercel, including the Row Level Security steps most weekend builds skip. (Build Guides)
- [What are agent skills? How to write your first SKILL.md](https://codema.ai/articles/what-are-agent-skills-write-your-first-skill.html): Agent skills are SKILL.md folders your AI agent loads on demand. Learn the format and write your first skill for Claude Code, Cursor and Codex. (Skills & Prompts)
- [How to add an MCP server to Cursor, Claude Code and Codex](https://codema.ai/articles/add-mcp-server-cursor-claude-code-codex.html): Step-by-step: how to add an MCP server to Cursor, Claude Code and Codex, with copy-paste config for the Supabase and GitHub MCP servers. (Build Guides)
- [Universal AGENTS.md starter + bridge files for every coding agent](https://codema.ai/resources/agents-md-starter-template.html): One AGENTS.md that Codex, Cursor, Copilot, Claude Code and Gemini CLI all read, with bridge files, a loading-rules cheat sheet and a handoff template. (Starter template)
- [How to back up a Supabase database and export your data](https://codema.ai/articles/back-up-supabase-database.html): How to back up a Supabase database: what each plan backs up, how to export with supabase db dump, how to restore, and what backups leave out. (Build Guides)
- [Claude Code hooks starter: block risky commands and protect files](https://codema.ai/resources/claude-code-hooks-starter.html): Three copy-paste Claude Code hooks: block edits to .env and lockfiles, block git push and rm -rf, and auto-format with Prettier. Tested. (Starter template)
- [Claude Code safe settings.json: deny .env reads and git push](https://codema.ai/resources/claude-code-safe-settings.html): A ready settings.json for Claude Code: allow lint and tests, ask before commits, deny reading .env files, git push and rm -rf. Schema-validated. (Starter template)
- [Lean CLAUDE.md template (under 200 lines)](https://codema.ai/resources/claude-md-starter-template.html): A short CLAUDE.md starter that follows Anthropic's guidance: commands, workflow, project rules and security, well under the 200-line target. (Starter template)
- [AI code review skill (SKILL.md) for Claude Code, Codex and Cursor](https://codema.ai/resources/code-review-skill.html): An agent skill that reviews a branch the way our checklist does: access control first, then secrets, dependencies and errors, with file and line. (Agent skills (SKILL.md))
- [GA4 predictive audiences: how they work and how to use them in Google Ads](https://codema.ai/articles/ga4-predictive-audiences-google-ads.html): GA4 predictive audiences target users likely to buy or churn. The requirements, how to create one, and how to use it in Google Ads, from Google docs. (Build Guides)
- [Git and GitHub basics for vibe coders: never lose AI-written code](https://codema.ai/articles/git-github-basics-for-vibe-coders.html): Git and GitHub basics for vibe coders: the commands you need, a branch-per-task workflow for coding agents, .gitignore for secrets, and push protection. (Build Guides)
- [MCP config starter for Cursor, Claude Code and Codex + safety checklist](https://codema.ai/resources/mcp-config-starter.html): Copy-paste MCP configs for Supabase and GitHub in Cursor, Claude Code and Codex, plus a checklist to vet any MCP server before you connect it. (MCP servers)
- [MCP security best practices: how to use MCP servers without leaking data](https://codema.ai/articles/mcp-security-best-practices.html): MCP security best practices for vibe coders: prompt injection risks, what the MCP spec requires, and a checklist to use MCP servers without leaking data. (Build Guides)
- [PRD template for AI coding agents](https://codema.ai/resources/prd-template-for-ai-agents.html): A one-page PRD template built for AI agents: users and permissions, core flows, data and access rules, scope limits and testable acceptance criteria. (Starter template)
- [Pre-deploy check skill: is it ready to ship?](https://codema.ai/resources/pre-deploy-check-skill.html): An agent skill that runs build, tests and lint, checks secrets, env vars and database access, then answers READY, READY WITH WARNINGS or BLOCKED. (Agent skills (SKILL.md))
- [How to run coding agents safely: permissions, sandboxes and secrets](https://codema.ai/articles/run-coding-agents-safely-permissions-sandboxes.html): How to run coding agents safely with Claude Code permission modes, Codex sandbox and approval settings, deny rules, and habits that keep secrets out of reach. (Build Guides)
- [Vibe coding prompt pack: 10 copy-paste prompts to ship a web app](https://codema.ai/resources/ship-a-web-app-prompt-pack.html): Ten copy-paste AI coding prompts from project brief to launch: AGENTS.md, schema with RLS, auth, tests, debugging and a security review. (Prompt packs & templates)
- [Starter skills pack: 5 tested SKILL.md agent skills](https://codema.ai/resources/starter-skills-pack.html): Five validated agent skills (code review, pre-deploy check, Supabase RLS audit, PR description, SEO brief) plus a directory of official skill repos. (Agent skills (SKILL.md))
- [Supabase RLS audit skill for coding agents](https://codema.ai/resources/supabase-rls-audit-skill.html): An agent skill that checks every Supabase table for Row Level Security and per-operation policies, then reports gaps without changing anything. (Agent skills (SKILL.md))
- [UTM tracking setup: a UTM naming guide for AI-built sites](https://codema.ai/articles/utm-tracking-setup-guide.html): A UTM tracking setup for GA4: what each UTM parameter does, a lowercase naming convention to copy, auto-tagging rules, and launch checks for AI-built sites. (Build Guides)
- [Vibe coding security checklist: a 30-minute pre-launch pass](https://codema.ai/resources/vibe-coding-security-checklist.html): A vibe coding security checklist for AI-built apps: secrets, access control, dependencies, errors and agent settings, plus a Next.js and Supabase .gitignore. (Starter template)
- [What is AGENTS.md? How to write one your coding agents follow](https://codema.ai/articles/what-is-agents-md-how-to-write-one.html): AGENTS.md is a Markdown file that tells AI coding agents how to work on your repo. What it is, which tools read it, and how to write one that works. (Build Guides)

## Français