A portable skill for AI coding agents (Codex, Claude Code, OpenCode) that provides discipline rules for code generation, testing, security, and validation across 22 languages: Bash, C, C#, C++, CSS, Dart, Go, HTML, Java, JavaScript, Kotlin, Lua, PHP, Python, R, Ruby, Rust, Shopify Liquid, SQL, Swift, TypeScript, and Zig.
Includes human-readable decision guides for each language, a local validation script, and adapters for specific coding environments. Core principles preserve existing repository conventions, default operational scripts to Python unless the project has a better native runner, and treat unsupported checks as explicit N/A items with evidence.
Current validation score: 100/100. Licensed under Apache License 2.0 (Apache-2.0), permitting commercial and non-commercial use. Installation available via one-line command for each supported agent or custom locations.
Ask the AI about this article →
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Visual Studio Code 1.135 now includes an experimental 'Rubber Duck' feature that lets developers request a sec…
Anthropic is making a permanent 25% increase to the usage limits in Claude Code, effective after September 14
OpenClaw creator Peter Steinberger and co-developers announced OpenClaw 2.0 over the weekend, describing it as…
AI coding has moved through three stages—prompt engineering, context engineering, and now harness engineering—…
Workday is integrating its AI agents with Google Cloud's Gemini Enterprise, letting employees start tasks like…
Over the last two years, writing code syntax has become much easier, with tools like Cursor, Claude Code, and…
