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".
68
83%
Does it follow best practices?
Impact
—
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. The main weakness is that the 'what' portion could be more specific about the range of deployment-related actions supported (e.g., preview vs production deployments, environment configuration, deployment status checking).
Suggestions
Expand the capability list with more specific actions, e.g., 'Deploy applications and websites to Vercel, create preview deployments, manage production deployments, and configure project settings.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Vercel deployment) and a 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), meeting the criteria for a complete description. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'deploy my app', 'deploy and give me the link', 'push this live', 'create a preview deployment', plus 'Vercel' as a platform keyword. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Vercel deployments specifically, with distinct triggers like 'deploy', 'push this live', and 'preview deployment' that are unlikely to conflict with other skills unless there are competing deployment platform 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 high-quality, comprehensive deployment skill with excellent actionability and workflow clarity. The decision tree covering all environment/state combinations is well-designed with concrete commands at every step. The main weakness is length — the skill could be more concise by consolidating repeated patterns (team selection, deploy+inspect) and potentially splitting agent-specific sections into separate files.
Suggestions
Consolidate repeated patterns: team selection logic and the 'deploy then inspect' pattern appear in multiple methods — extract them into a shared reference section to reduce redundancy.
Consider splitting agent-specific notes (Claude Code, claude.ai sandbox, Codex) and troubleshooting into separate referenced files to reduce the main SKILL.md length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~200+ 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 complex decision tree. Some tightening is possible — the `.vercel/` directory explanation block and repeated deploy patterns could be consolidated. | 2 / 3 |
Actionability | Excellent actionability throughout — every method includes specific, executable bash commands with correct flags. The decision tree is concrete with exact commands for each branch (vercel deploy, vercel link --repo, git push, fallback scripts). Examples include real CLI flags like --no-wait, --scope, --format json, and specific file paths. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-structured: Step 1 gathers state with four specific checks, Step 2 branches into clearly labeled methods based on state combinations. Each method has numbered steps with validation (e.g., vercel inspect to check status, explicit 'ask before pushing' checkpoints). The decision tree covers all combinations of linked/unlinked × git/no-git × auth/no-auth with clear fallback paths. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's essentially a monolithic document. The agent-specific notes, troubleshooting, and detailed method descriptions could benefit from being split into separate files. References to external scripts (deploy.sh, deploy-codex.sh) are clear, but no bundle files were provided to verify their existence. The inline content is quite dense for a single SKILL.md. | 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
4ec6f84
- 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.