Coding
Published entries filed under “Coding” in Skills, newest first by publication date on this site.
9 entries
Modern Web Guidance: current platform advice for coding agents
Modern Web Guidance is a coding-agent skill that retrieves current browser and web-platform advice across 250 features, including compatibility-aware fallbacks.
azure-cloud-migrate: write the migration assessment before touching code
A Microsoft azure-skills skill that assesses which platform features an app depends on, then converts code and config for Azure into a separate folder.
supercmo-skills: a marketing production pipeline for AI agents
SuperCMO Skills is Apache-2.0: 23 marketing skills plus a local MCP server that turn a product photo and a brief into UGC or ad videos, with your own keys.
design-control-loop: run your codebase like a control system, and let an agent pay down tech debt daily
HumanLayer's skill interviews you, then builds a sensor-controller-actuator loop on scheduled CI — small reviewable PRs toward a target, in your repo.
typesafe-ai: the skill that teaches agents typed decisions with Jev
typesafe-ai is TypeSafe's official skill: it teaches agents to swap prompt-and-parse for Jev's typed judgments, starting from the live docs.
security-audit: make the agent prove a vulnerability before reporting it
Cloudflare's security-audit skill stops agents dressing up guesses as findings: six phases force source evidence and independent verification first.
golive: ship agent-built apps to your own cloud
golive is an Agent Skill that makes an agent plan, get approval, apply and verify before shipping your app to your own Vercel, Supabase or Neon accounts.
impeccable: 24 design commands and a 61-rule detector for AI-built UIs
Paul Bakaus's open-source design skill gives coding agents 24 named commands and a 61-rule detector that catches AI-slop UI tells without an LLM or API key.
frontend-design: make the agent decide who the page is for before it writes CSS
The front-end design skill from Anthropic's official skills repository. It has the agent ground the design in the product and its industry, commit to a small token system, then build and self-review from screenshots, so the result stops looking like every other AI-generated page.





