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

Critical

Do not install without reviewing

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-engineered overview skill: lean operational guidance with exact commands, an explicit pre-mutation validation workflow with stop conditions, and a clean decision-tree routing to 27 real one-level-deep reference files. The only notable improvement is consolidating the duplicated linking guidance between the Project Linking section and the Anti-Patterns list.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — stdout/stderr parsing rules, non-interactive JSON error protocol, linking semantics — with zero explanation of concepts Claude already knows. However, the "Critical: Project Linking" section and the "Anti-Patterns" section repeat the same points (wrong link type in monorepos, commands auto-linking, `whoami` not verifying the linked project), which is a minor trim opportunity. Anchor 4 ("efficient; minor instances ... that could be trimmed") fits better than 5 because of that deliberate but real duplication.

4 / 5

Actionability

Every directive is paired with an exact, executable command or flag: `vercel project inspect --non-interactive`, `vercel whoami --format json`, `vercel link --repo`, `npm i -g vercel`, `vercel deploy --force` without `--with-cache`, `vercel curl`, `VERCEL_TOKEN`. The Quick Start is copy-paste ready and each anti-pattern names its corrective command, covering the common cases as in the anchor-5 example. Not 4 — there are no missing steps or gaps in the guidance the body chooses to give.

5 / 5

Workflow Clarity

The Quick Start is a clear install → login → link → pull → dev → deploy sequence, and the body mandates an explicit pre-mutation validation checkpoint ("run `vercel project inspect --non-interactive` ... and confirm the reported owner and project") with stop conditions ("stop on `link_required` or a target mismatch") and error-recovery guidance via the JSON `status`/`reason`/`hint`/`next` protocol with safety constraints on follow-up commands. This matches anchor 5's explicit validation steps plus feedback loops; the destructive/batch cap does not apply because validation before consequential operations is explicitly required.

5 / 5

Progressive Disclosure

The body is a true overview: a small amount of critical operating guidance, a Quick Start, and a well-signaled Decision Tree routing each topic to a verified, one-level-deep `references/*.md` file (all 27 referenced files exist in the bundle, and reference files only cross-link to siblings at the same level, never nesting 2+ levels). Content is appropriately split with easy navigation, matching anchor 5; anchor 4's "minor organization gaps" does not apply.

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.

An exemplary description: concrete actions, an explicit 'Use for' trigger clause, and comprehensive, well-organized coverage of the CLI's feature surface including natural and tool-specific trigger terms. The only weakness is a handful of unqualified generic trigger terms (build failures, logs, metrics) that slightly raise overlap risk with adjacent skills.

DimensionReasoningScore

Specificity

Opens with multiple concrete actions ("Deploy, manage, inspect, and troubleshoot Vercel projects from the command line") and enumerates 25+ specific capability areas (Vercel Toolbar comments, Speed Insights, Core Web Vitals, Edge Config, Container Registry (VCR), cron jobs, deploy hooks, Blob storage), giving comprehensive coverage of the CLI surface. Anchor 4's "minor gaps in coverage" does not apply — the topic enumeration is near-exhaustive of the CLI's feature areas.

5 / 5

Completeness

Explicitly answers what ("Deploy, manage, inspect, and troubleshoot Vercel projects from the command line") and when ("Use for Vercel deployments, ... or `vercel api` fallback") with concrete trigger phrases. The structure mirrors the anchor-5 example (concrete action list followed by an explicit Use-when clause), so the anchor-4 caveat about a less-explicit 'when' does not apply.

5 / 5

Trigger Term Quality

Covers natural user phrasings ("build failures", "environment variables", "domains and DNS", "logs", "local development", "preview access") alongside tool-specific synonyms ("Vercel Toolbar comments", "`vercel flags`", "`vercel api` fallback"). This includes both colloquial terms and CLI-specific variants, matching anchor 5's comprehensive synonym coverage rather than anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The Vercel niche is clear and most triggers are Vercel-anchored, but several listed triggers are bare generic terms ("build failures", "logs", "metrics", "activity", "usage") that are not Vercel-qualified and could fire in non-Vercel contexts (other deploy platforms, general CI/debugging skills). This is anchor 4's "mostly distinct; minor overlap risk with closely related skills" — not 5, because those unqualified generic terms leave residual conflict risk; not 3, because the dominant framing is unmistakably Vercel-specific.

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.