CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vercel-cli

Deploy, manage, inspect, and troubleshoot Vercel projects from the command line. Use for Vercel deployments, Vercel Toolbar comments, build failures, projects and teams, environment variables, domains and DNS, logs, metrics, Speed Insights, Core Web Vitals, request traces, usage, activity, alerts, firewall rules, cache, cron jobs, deploy hooks, Edge Config, feature flags (`vercel flags`), integrations, connectors, Blob storage, Container Registry (VCR), microfrontends, rolling releases, custom environments, Sandbox, agent/MCP setup, preview access, local development, or `vercel api` fallback.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is vercel-cli in vercel/vercel-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured hub skill: lean operational body with concrete, executable commands, explicit pre-mutation target validation with failure handling, and a verified one-level-deep reference tree covering the full CLI surface. The only trimmable content is mild repetition of the project-inspect verification guidance.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious CLI behavior (stdout/stderr split, exit-2 help reads, JSON error objects with status/reason/hint/next) and teaches no concepts Claude already knows, fitting "efficient; minor instances that could be trimmed". Not 5 because project-target verification guidance repeats across the Critical section, the "Being inside an app directory is not proof" paragraph, and the Anti-Patterns bullets.

4 / 5

Actionability

Guidance is copy-paste executable throughout: a runnable Quick Start block and specific commands like "vercel project inspect --non-interactive", "vercel whoami --format json", "vercel deploy --force", "vercel curl", and "VERCEL_TOKEN" instead of "--token". Matches the fully-executable anchor with specific examples covering the common cases; not 4 because there are no pseudocode or vague-direction gaps.

5 / 5

Workflow Clarity

Sequenced setup (login → link → pull → dev → deploy) plus explicit validation before consequential actions ("run `vercel project inspect --non-interactive` ... and confirm the reported owner and project", "stop on link_required or a target mismatch") and error-recovery feedback (treat printed usage as a successful help read; prefer a suggested `next` command only after confirming intent). The destructive/batch validation cap does not apply since verification steps are present; not 4 because checkpoints and failure handling are explicit rather than implicit.

5 / 5

Progressive Disclosure

The Decision Tree cleanly routes ~25 topic areas to references/*.md, and all referenced files exist as siblings one level deep (the few cross-links between references, e.g. deployment.md → project-infra.md, stay at the same level rather than nesting). The overview itself stays concise, matching the clear-overview anchor; not 4 because there are no buried references or misplaced inline content.

5 / 5

Total

19

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what-and-when structure with a comprehensive, natural-language trigger list and a clearly anchored Vercel niche. The only weakness is a handful of generic, unsuffixed trigger terms that create minor overlap risk with adjacent dev-ops skills.

DimensionReasoningScore

Specificity

"Deploy, manage, inspect, and troubleshoot Vercel projects from the command line" names four concrete actions, and the trigger enumeration covers the platform surface comprehensively ("Vercel Toolbar comments", "Edge Config", "Container Registry (VCR)", "feature flags (`vercel flags`)"). Matches the anchor for multiple specific concrete actions with comprehensive coverage; not 4 because no capability area of the CLI is left uncovered.

5 / 5

Completeness

Explicitly answers both questions: "what" via "Deploy, manage, inspect, and troubleshoot Vercel projects from the command line" and "when" via the explicit "Use for Vercel deployments, ... build failures, ... local development, or `vercel api` fallback" clause. Matches the anchor for clearly and explicitly answering both with concrete trigger phrases; not 4 because the when-clause is fully explicit rather than improvable.

5 / 5

Trigger Term Quality

Natural terms users would say are comprehensively covered, including synonyms and tool-specific forms: "deploy", "build failures", "environment variables", "domains and DNS", "logs, metrics", "cron jobs", "local development", plus command-form triggers like "`vercel flags`" and "`vercel api` fallback". Not 4 because common phrasings and variations (Speed Insights, Core Web Vitals, Blob storage, microfrontends) are all present.

5 / 5

Distinctiveness Conflict Risk

"Vercel" anchors the niche and most triggers are platform-distinct ("Vercel Toolbar comments", "Edge Config", "VCR", "`vercel flags`"), but several unsuffixed generic terms ("build failures", "logs, metrics", "usage, activity", "cache") could overlap with other deploy/CI/monitoring skills. Fits "mostly distinct; minor overlap risk" better than the 5 anchor, whose example carries minimal conflict risk because every trigger is domain-suffixed.

4 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

vercel/vercel-plugin

Path

skills/vercel-cli/upstream/SKILL.md

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.