This one kicks in when you start a dev server or ask "why isn't this working" and actually walks the entire stack. It infers what you're building from recent file changes, then checks browser console, server logs, API routes, database calls, and environment variables in sequence. The smart part is it stops at the first broken boundary instead of running every test, and it chains to other skills when it spots env vars, middleware, or AI SDK patterns that need deeper context. Honestly feels like having someone who actually reads your terminal output and screenshots instead of guessing. Most useful when something almost works but you can't tell if it's the frontend, the API, or a missing environment variable.
npx -y skills add vercel/vercel-plugin --skill verification --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
microsoft/azure-skills
zxkane/aws-skills
awslabs/agent-plugins
microck/ordinary-claude-skills
microsoft/github-copilot-for-azure
zxkane/aws-skills