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".
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 solid skill description with excellent trigger terms and completeness. The explicit 'Use when' clause with natural user phrases is a strong point. The main weakness is that the 'what' portion could be more specific about the range of deployment-related actions supported beyond just 'deploy'.
Suggestions
Expand the capability list with more specific actions, e.g., 'Deploy applications and websites to Vercel, manage preview and production deployments, configure project settings, and check deployment status.'
| 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 like configuring environment variables, managing domains, checking deployment status, or rolling back deployments. | 2 / 3 |
Completeness | Clearly answers both 'what' (deploy applications and websites to Vercel) and 'when' (explicit 'Use when' clause with multiple trigger phrases covering different user phrasings). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger phrases users would actually say: 'deploy my app', 'deploy and give me the link', 'push this live', 'create a preview deployment'. These cover both technical and casual language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Vercel specifically, which distinguishes it from generic deployment skills or other hosting platforms. The mention of 'Vercel' and specific deployment-related triggers make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable deployment skill with an excellent decision-tree workflow that covers multiple environments and fallback paths. The main weakness is its length — the document tries to cover every scenario (linked/unlinked, auth/no-auth, git/no-git, claude.ai/Codex/Claude Code) in a single file, leading to some repetition and a document that could benefit from splitting into sub-files. The concrete commands and explicit validation checkpoints are exemplary.
Suggestions
Consider splitting agent-specific fallback methods (claude.ai sandbox, Codex sandbox) into separate referenced files to reduce the main SKILL.md length and improve progressive disclosure.
Reduce repetition of team selection logic — it's explained in Step 1, then re-explained in the 'Not linked + CLI authenticated' and 'Not linked + CLI not authenticated' sections. A single reference back to Step 1 would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines) and includes some redundant explanations (e.g., re-explaining team selection logic multiple times across methods, explaining what .vercel/project.json vs .vercel/repo.json contain). However, most content is genuinely necessary given the complexity of the decision tree. Some tightening is possible but it's not egregiously verbose. | 2 / 3 |
Actionability | Every path includes concrete, executable bash commands with specific flags and arguments. The skill provides copy-paste ready commands for each scenario (git push, vercel deploy, vercel link, fallback scripts) with exact flag usage like `--no-wait`, `--scope`, `-y`, and `--format json`. | 3 / 3 |
Workflow Clarity | The skill has an excellent decision tree structure: gather state first (4 explicit checks), then branch based on conditions. Each branch has clear numbered steps with validation (e.g., `vercel inspect` to check status, asking user before pushing). The feedback loop for team selection and the explicit 'ask before pushing' checkpoint demonstrate strong workflow design. Troubleshooting section covers error recovery paths. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic document that could benefit from splitting agent-specific notes or the detailed fallback methods into separate files. The references to external scripts (`deploy.sh`, `deploy-codex.sh`) are well-signaled, but the main file is quite long for a single SKILL.md. No bundle files were provided to verify referenced paths. | 2 / 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
- databricks/devhub
- Commit
6338825
- 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.