vercel-deploy
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". Do NOT use for deploying to Netlify, Cloudflare, or Render (use their respective skills).
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger terms, clear completeness (both what and when), and outstanding distinctiveness through explicit exclusion of competing platforms. The main weakness is that the specificity of capabilities could be richer—listing more concrete actions beyond just 'deploy' (e.g., managing environment variables, linking projects, checking deployment status) would strengthen it further.
Suggestions
Add more specific concrete actions beyond 'deploy', such as 'create preview deployments, promote to production, configure environment variables, check deployment status' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Vercel deployment) and the general action (deploy applications and websites), but doesn't list multiple specific concrete actions beyond 'deploy'. Could mention specific capabilities like preview deployments, production deployments, environment configuration, or project linking. | 2 / 3 |
Completeness | Clearly answers both 'what' (deploy applications and websites to Vercel) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes a 'Do NOT use' clause that further clarifies boundaries, which is excellent for routing. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'deploy my app', 'deploy and give me the link', 'push this live', 'create a preview deployment'. Also includes the explicit platform name 'Vercel' and contrasts with competing platforms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit platform targeting (Vercel) and an explicit exclusion clause naming competing platforms (Netlify, Cloudflare, Render), making it very unlikely to conflict with similar deployment skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured deployment skill with clear actionable commands and good organization. Its main weaknesses are minor redundancy (escalated permissions mentioned twice) and the lack of explicit validation/verification steps in the workflow — particularly no structured feedback loop for checking deployment status or handling build failures beyond network issues.
Suggestions
Remove the duplicate escalated permissions guidance — keep it in one place (Troubleshooting) and reference it briefly from Prerequisites.
Add a validation step after deployment to check the returned JSON/output for success indicators before presenting the URL to the user, or explicitly document what a failed build output looks like and how to handle it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy — the sandbox/escalated permissions point is mentioned in both Prerequisites and Troubleshooting, and the timeout guidance is repeated. The 'Tell the user' instruction and some explanatory text could be tightened. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready commands for both primary and fallback deployment methods, with specific flags (-y, --prod) and clear paths. The fallback script usage with multiple invocation patterns is practical and executable. | 3 / 3 |
Workflow Clarity | The workflow follows a clear primary → fallback sequence, but lacks explicit validation checkpoints. There's no step to verify the build succeeded before presenting the URL, and the troubleshooting for network failures doesn't include a retry loop — it just says to rerun with escalated permissions without a structured feedback loop. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the content is well-organized into logical sections (Quick Start, Fallback, Production, Output, Troubleshooting) with clear headers. No unnecessary nesting or external references needed for this scope. | 3 / 3 |
Total | 10 / 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.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- Reviewed
Table of Contents
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.