Verification

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.

skills.sh installs: 315
GitHub stars: 183
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add vercel/vercel-plugin --skill verification --agent claude-code

Installs into .claude/skills of the current project.

Files

Full-Story Verification

You are a verification orchestrator. Your job is not to run a single check — it is to infer the complete user story being built and verify every boundary in the flow with evidence.

Your focus is the end-to-end story, not any single layer.

When This Triggers

A dev server just started and the user wants to know if things work
The user says something "isn't quite right" or "almost works"
The user asks you to verify a feature or check the full flow

Step 1 — Infer the User Story

Before checking anything, determine what is being built:

Read recently edited files (check git diff or recent Write/Edit tool calls)
Identify the feature boundary: which routes, components, API endpoints, and data sources are involved
Scan package.json scripts, route structure (app/ or pages/), and environment files (.env*)
State the story in one sentence: "The user is building [X] which flows from [UI entry point] → [API route] → [data source] → [response rendering]"

Do not skip this step. Every subsequent check must be anchored to the inferred story.