deploy-to-vercel

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a strong, actionable runbook: concrete commands for every branch, an explicit decision tree, approval gating on the destructive push, and error-recovery guidance. Its only notable gaps are mild verbosity from duplicated environment-specific fallback sections and the absence of any split reference files for the longer peripheral material.

Suggestions

Consolidate the two near-identical no-auth fallback sections (claude.ai and Codex) into one parameterized section to reduce repetition and token cost.

Consider moving the Troubleshooting and Agent-Specific Notes into a separate reference file referenced from SKILL.md to improve progressive disclosure now that the body is long.

Tighten the repeated explanations of `vercel link` vs `vercel link --repo` so the rationale appears once rather than being restated across steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean commands and decision logic with no padding about concepts Claude already knows, though the two parallel no-auth fallback sections (claude.ai vs Codex) and some repeated linking explanations could be trimmed slightly.	4 / 5
Actionability	It provides copy-paste-ready, executable bash commands for every path (git remote check, `vercel deploy -y --no-wait`, `vercel inspect <url>`, `vercel link --repo --scope`) covering the common cases with concrete examples.	5 / 5
Workflow Clarity	The flow is clearly sequenced (gather state -> choose method by explicit conditions) with a validation checkpoint on the destructive git push ("Ask the user before pushing. Never push without explicit approval"), status verification via `vercel inspect`, and a troubleshooting section providing error-recovery feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist, so all content lives inline, but it is well-organized into clearly signaled sections (Step 1/2, Agent-Specific Notes, Output, Troubleshooting); the length and the inline troubleshooting/agent-notes material that could arguably be split keep it just below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed: it states a concrete capability, gives explicit 'Use when...' guidance with natural trigger phrases, and occupies a distinct Vercel-deployment niche. Its only weakness is that the action list is essentially a single deploy action with variants rather than multiple distinct capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain ("Deploy applications and websites to Vercel") with one concrete action and a preview variant, but does not list several distinct concrete actions, matching the '1-2 concrete actions' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	It explicitly answers both 'what' (deploy applications and websites to Vercel) and 'when' ("Use when the user requests deployment actions like...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural user phrases ("deploy my app", "deploy and give me the link", "push this live", "create a preview deployment") that users would actually say, giving good keyword coverage, though a few synonymous phrasings are absent so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Vercel-specific scope and deployment-only triggers carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vercel-labs/agent-skills
Path: skills/deploy-to-vercel/SKILL.md
Commit: b8caa26

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.