---
title: "Vercel Optimize: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/vercel-labs-vercel-optimize/
description: "Runs a metrics-first Vercel audit: collects usage signals before reading source, gates candidates deterministically, then produces ranked cost and performance recommendations."
---

# Vercel Optimize: review, setup & limitations · Undominated.ai

> Runs a metrics-first Vercel audit: collects usage signals before reading source, gates candidates deterministically, then produces ranked cost and performance recommendations.

[← Explore all skills](/skills/)

CLOUD OPERATIONS / Vercel

# Vercel Optimize

Runs a metrics-first Vercel audit: collects usage signals before reading source, gates candidates deterministically, then produces ranked cost and performance recommendations.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 8 linked sources
 Publisher Vercel
 Licence [MIT declared in README; no LICENSE file at 063bee94 ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md)
 Revision 063bee94c3f4
 [Read what was—and wasn’t—checked ↓](#review)

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

 [Vercel · upstream description ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Enforces an observability-first pipeline: no source file is inspected until signals.json exists and a deterministic gate names a route, file, or setting, which blocks speculative rewrites.
- Ships a full audit toolkit at the pinned revision: doctrine plus candidates, data-collection, recommendations and scanner-patterns references with lib/ helpers for budget summary and cost coverage.

### A good fit for

 - Cutting a Vercel bill or explaining which routes drive it
- Checking caching, ISR, middleware, and image choices against measured usage
- Auditing a Next.js, SvelteKit or Nuxt project on Vercel that has Observability Plus enabled

### Weigh up before choosing

 - Needs Vercel project access and usage metrics; without signals the workflow stops by design and produces nothing.
- Recommendations are estimates until re-measured after the change; Astro support is limited and findings need version-aware doc checks.
- Licence corrected 2026-10-13: MIT is declared only in the repository README. The SKILL.md frontmatter declares no licence and the git tree at 063bee94 holds no licence file, so redistribution is not established and this catalogue offers no download.
- Running the audit executes the skill's own 15 Node scripts and 75 lib/ modules against your Vercel account and repository; none was run in this review.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/vercel-optimize/SKILL.md
- skills/vercel-optimize/references/doctrine.md
- skills/vercel-optimize/references/data-collection.md
- README.md
- Repository git tree at 063bee94 (script count and licence-file check)

### Our findings

 - The pipeline refuses source inspection before metric collection and gates every candidate before deep-dives.
- References separate signal collection, candidate gating, and recommendation rendering with explicit verification and failure-copy sections.
- Prerequisites in the SKILL.md: Vercel CLI v53+ (vercel metrics, usage, contract and api), an authenticated vercel login session, a linked app directory, Node.js 20+, and Observability Plus for route-level recommendations.
- The gate step defaults to 6 code-scope candidates; --max-candidates 12 or all widens it. With three or more briefs the SKILL.md tells the host to spawn one sub-agent per brief.
- The SKILL.md forbids typing VERCEL_TOKEN=..., --token or Authorization: Bearer into commands that may be echoed in chat, and limits customer-facing cost claims to magnitude phrases, never a $ figure.
- Licence corrected 2026-10-13: this record earlier set redistribution to true on a README-only MIT declaration. No file named LICENSE or COPYING exists anywhere in the repository tree at 063bee94.

### Not established by this review

 - No Vercel project was audited and no usage API was called.
- Estimated savings and performance effects were not measured.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/README.md)

DOCUMENTED COMMAND

 npx skills add vercel-labs/agent-skills --skill vercel-optimize Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

 npx skills add https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize --skill vercel-optimize Copy reviewed-revision command ↗ - Install the complete skill directory with its references, lib, and scripts; a copied SKILL.md alone is incomplete.
- Choose your AI tools and project or global scope in the installer, then review its permissions before using the skill.

### Before you start

 - Node.js/npm for this installer
- An agent that supports the Agent Skills format
- Access to the Vercel project, team, and usage metrics under review

### Compatibility

Agent Skills-compatible coding agents · Next.js, SvelteKit, Nuxt, and limited Astro on Vercel

### Project files and Vercel usage data

 - Read project config, routes, and Vercel metrics
- Write report files when authorized
- Optimization edits apply only with explicit approval

### Cost model

MIT is declared in the README only; Vercel usage, metrics access and agent calls have their own costs.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Skill definition at reviewed revision ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/SKILL.md) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access
- [Reviewed reference: references/doctrine.md ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/references/doctrine.md) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/references/doctrine.md Supports: review, limitations
- [Reviewed reference: references/data-collection.md ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/references/data-collection.md) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/skills/vercel-optimize/references/data-collection.md Supports: review
- [Upstream license declaration ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md Supports: license
- [Publisher installation documentation ↗](https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md Supports: install, compatibility
- [Skills installer source formats and selective installation ↗](https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/README.md) Checked 2026-10-13 https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/README.md Supports: install
- [Installer implementation: full commit SHA fallback ↗](https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/src/git.ts) Checked 2026-10-13 https://github.com/vercel-labs/skills/blob/48dc9e8eb8aa19040e91cb90ba0b642c9cbad57e/src/git.ts Supports: install
- [Repository tree at the pin (no licence file) ↗](https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278) Checked 2026-10-13 https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278 Supports: license, limitations, review

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AKS Automatic Readiness ↗ Pins Microsoft's AKS Automatic readiness skill, which assesses a cluster or local manifests without changing the cluster and writes files only after an accepted diff.](/skills/microsoft-azure-kubernetes-automatic-readiness/)[### Azure Deploy ↗ Pins Microsoft's Azure deploy skill, which stops unless a separate validation skill has already marked the deployment plan validated.](/skills/microsoft-azure-deploy/)[### Azure Enterprise Infra Planner ↗ Pins Microsoft's enterprise Azure infrastructure skill, which holds IaC and deployment until the user approves the plan and acknowledges deploy risk.](/skills/microsoft-azure-enterprise-infra-planner/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
