Deploy, manage, and develop projects on Vercel from the command line
68
60%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/vercel-cli/SKILL.mdQuality
Discovery
32%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 identifies the platform (Vercel) and general actions but lacks specificity in concrete capabilities and completely omits explicit trigger guidance ('Use when...'). It would benefit from listing specific Vercel operations and adding natural trigger terms users would use when needing Vercel-related help.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about deploying to Vercel, managing Vercel projects, checking deployment status, or configuring Vercel settings.'
List more specific concrete actions such as 'configure environment variables, set up custom domains, manage preview deployments, check deployment logs, link projects to Vercel'.
Include natural keyword variations users might say, such as 'Vercel CLI', 'vercel deploy', 'hosting', 'Next.js deployment', 'serverless functions', or 'production deployment'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Vercel) and lists some actions ('deploy, manage, and develop projects'), but these are fairly broad and not highly specific concrete actions like 'configure environment variables, set up custom domains, manage deployments'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also somewhat weak, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Vercel' and 'deploy' which are strong natural trigger terms, but misses common variations users might say like 'hosting', 'serverless', 'Next.js deployment', 'vercel CLI', 'production deployment', or 'preview deployment'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Vercel' is a distinct platform name that helps differentiate this from generic deployment skills, but 'deploy, manage, and develop projects' is broad enough that it could overlap with other deployment/hosting platform skills (e.g., Netlify, AWS). | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that serves as an effective routing document for Vercel CLI usage. It excels at conciseness and progressive disclosure, providing just enough context in the main file while pointing to detailed references. The main weakness is the lack of explicit validation/verification steps in the workflows, though for a routing-focused skill this is a minor gap.
Suggestions
Add a brief verification step after key commands in the Quick Start (e.g., 'Verify link: check `.vercel/project.json` exists' or 'Verify deploy: check the URL returned')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Vercel is or how CLIs work. Every section earns its place — the project linking section addresses a genuine pain point, the quick start is minimal, and the anti-patterns list contains non-obvious gotchas that Claude wouldn't inherently know. | 3 / 3 |
Actionability | The quick start provides copy-paste ready commands. The anti-patterns section gives specific, concrete guidance (e.g., use `--prebuilt` after `vercel build`, use `VERCEL_TOKEN` env var instead of `--token`). Diagnostic steps are concrete: check `.vercel/`, run `vercel whoami`. | 3 / 3 |
Workflow Clarity | The quick start provides a clear sequence for initial setup and deployment. However, there are no explicit validation checkpoints — for example, after `vercel link` or `vercel deploy`, there's no step to verify success or handle errors. The decision tree is helpful for routing but isn't a workflow with feedback loops. | 2 / 3 |
Progressive Disclosure | Excellent structure: concise overview with a well-organized decision tree pointing to 15+ reference files, all one level deep and clearly signaled. The SKILL.md serves as a proper routing document. However, no bundle files were provided to verify the referenced paths actually exist, so scoring based on the structure as presented. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
6338825
Table of Contents
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.