Agent skills for Claude Desktop

Activate for ANY pitch deck analysis, feedback, or review request.

Activate for ANY startup evaluation, investment screening, or company assessment.

Use before submitting to a venue this repository does not cover, one that arrived by email solicitation, or one whose indexing status…

Vercel API for deployments. Use when user mentions "Vercel", "vercel.app",

Vercel Blob object storage with CDN for Next.js.

Vercel platform CLI for frontend deployments, serverless functions, and edge network management.

Vercel Functions expert guidance — Serverless Functions, Edge Functions, Fluid Compute, streaming, Cron Jobs, and runtime configuration.

Serverless Redis-compatible key-value store via Upstash REST API -- edge-compatible, automatic JSON serialization, TTL-based caching

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

React and Next.js performance optimization guidelines from Vercel Engineering.

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps.

Vercel production deployment checklist with rollback and promotion procedures.

Append-only judgment ledger. Every DOOR / GATE / PREMORTEM / REFUTE / DRIFT verdict line gets logged to one grep-able file so "show me…

Use when implementing a non-trivial change.

Builds a list of verified business emails from Google Maps, Google SERPs, or a user-supplied URL list.

Set a repo up to prove engineering-task work actually works before it ships.

A behavioral skill that forces every claim the agent makes to be evidence-gated and honestly labeled.

SeldonFrame merge gate — run unit tests + tsc + check-use-server + migration-journal + regression-grep and return ONE pass/fail verdict.

Select and execute the verification that actually proves the change works, based on what type of change it is.

Verify information accuracy against codebase and documentation.

Extracts and verifies the runnability and code coverage of all Python code blocks inside a Markdown file.