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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

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

A highly actionable, well-sequenced deployment workflow with strong validation checkpoints and error recovery. Its main weaknesses are repetition across agent-specific sections and a monolithic body that points to bundle scripts not included here.

Suggestions

Consolidate the repeated team-selection and no-auth fallback instructions into a single shared section referenced by each agent path to reduce length and duplication.

Either include the referenced deploy.sh / deploy-codex.sh in a scripts/ or references/ bundle, or remove the hardcoded script paths and keep the fallback guidance self-contained.

Move the per-agent path notes (claude.ai, Codex, Claude Code) into a concise matrix or a separate reference file so the main flow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient concrete commands with no concept-padding, but at ~310 lines it repeats the team-selection step and the no-auth fallback instructions/message across multiple agent sections, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash commands with flags and concrete fallback examples (current dir, specific project, tarball), rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	It sequences a clear state-gated decision flow with explicit validation checkpoints ("Run all four checks before deciding", vercel inspect, sleep 5 + vercel ls) and a troubleshooting section with error-recovery feedback loops (auth failure -> no-auth fallback).	3 / 3
Progressive Disclosure	The body is a single long inline document and references scripts (deploy.sh, deploy-codex.sh) that are not present in the bundle (no references/scripts/assets dirs), so content that could be split out is inline and references are not backed by actual bundle files.	2 / 3
	Total	10 / 12 Passed

Description

90%

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

A strong, third-person description with explicit "Use when" triggers and natural phrasing. The only weakness is that the capability statement lists a single action rather than several concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain and a single concrete action ("Deploy applications and websites to Vercel") but does not enumerate multiple distinct actions as the top anchor requires; it is more comprehensive than the vague anchor-1 examples yet not a full action list.	2 / 3
Completeness	It clearly answers both what (deploy apps/sites to Vercel) and when via an explicit "Use when the user requests deployment actions like..." clause, matching the anchor that requires explicit triggers.	3 / 3
Trigger Term Quality	The trigger phrases ("deploy my app", "deploy and give me the link", "push this live", "create a preview deployment") are natural variations a user would actually say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	It targets a clear Vercel-specific niche with distinct deployment triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: databricks/devhub
Commit: 131db95

Reviewed: 5 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.