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
Critical
Do not install 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 'Use when' clause with natural user phrases is well-crafted and covers multiple ways users might request deployments. The main weakness is that the capability description could be more specific about the range of Vercel-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 deployments, configure environment variables, 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 ways users might request deployment). | 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 common variations of deployment requests. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Vercel specifically, which distinguishes it from generic deployment skills or other platform-specific deployment skills. The trigger terms are deployment-focused and Vercel-specific, making conflicts unlikely. | 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 high-quality, highly actionable deployment skill with an excellent decision tree covering multiple environments and states. Its main weakness is length — the comprehensive coverage of every scenario (linked/unlinked, auth/no-auth, git/no-git, claude.ai/Codex/Claude Code) makes it verbose, and some content like agent-specific notes and troubleshooting could be split into separate files. The workflow clarity is exemplary with explicit state-gathering, branching logic, and verification steps.
Suggestions
Move agent-specific notes (Claude Code, claude.ai sandbox, Codex) and troubleshooting into separate referenced files to reduce the main skill's token footprint.
Reduce repetition of team selection instructions — define the pattern once and reference it from each method instead of restating it in every branch.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough but verbose in places — the explanation of `.vercel/project.json` vs `.vercel/repo.json`, the repeated team selection instructions across multiple methods, and some conversational phrasing ('This is the opportunity to get the user into the best state') add tokens without proportional value. However, most content is necessary given the complexity of the decision tree. | 2 / 3 |
Actionability | Every path includes specific, executable bash commands with concrete flags and arguments. The decision tree is fully specified with copy-paste-ready commands for each scenario (git push, vercel deploy, vercel link, fallback scripts). Examples include exact paths, flags like `--no-wait`, `--scope`, and `--repo`. | 3 / 3 |
Workflow Clarity | The skill has an excellent multi-step workflow: gather state (4 explicit checks) → choose method based on state → deploy → verify output. Each method has clear sequencing with validation steps (e.g., `vercel inspect` after deploy, sleep + `vercel ls` after git push). The decision tree is well-structured with explicit branching conditions, and there are feedback loops for error recovery in the troubleshooting section. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a long monolithic document (~200+ lines) that could benefit from splitting agent-specific notes, troubleshooting, and fallback methods into separate referenced files. All content is inline rather than appropriately distributed across files. | 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
- vercel-labs/agent-skills
- Commit
5a4b5e1
- 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.