CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vercel-cli

Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, debugging a deployed app on Vercel (errors, 5xx responses, timeouts, slow routes, or a single failing request), managing domains, managing feature flags with vercel flags, or interacting with the Vercel platform from the command line. Use the vercel-tracing skill instead for `vercel traces` span search, trace inspection, and sampling rules, or for OpenTelemetry setup.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary CLI skill body: it front-loads non-obvious operational semantics (linking resolution, output-stream parsing, non-interactive JSON errors), provides copy-paste commands with exact corrections for common mistakes, and defers all topic depth to a complete, verified set of one-level-deep references. No padding or over-explanation was found.

DimensionReasoningScore

Conciseness

The body is lean and every sentence carries non-obvious operational knowledge Claude would not know ("Parse only stdout for URLs and JSON", "Some help commands exit 2 after printing usage", the project.json vs repo.json resolution rules). It assumes CLI competence and contains no padded explanation of what Vercel or a CLI is, matching the anchor-5 example of every token earning its place.

5 / 5

Actionability

The Quick Start block is copy-paste ready ("npm i -g vercel", "vercel link --repo", "vercel deploy"), and anti-patterns give exact corrective commands such as "use `vercel deploy --force` without `--with-cache`" and "Use `VERCEL_TOKEN` env var instead of `--token`". Concrete verification commands like "vercel project inspect --non-interactive" and "vercel whoami --format json" cover the common cases.

5 / 5

Workflow Clarity

There is an explicit validation checkpoint before consequential actions ("run `vercel project inspect --non-interactive` from the intended directory and confirm the reported owner and project… stop on `link_required` or a target mismatch"), feedback loops for error recovery (check `vercel <command> --help` before guessing; handle JSON `next` follow-ups without auto-running mutations), and the Decision Tree acts as a routing checklist.

5 / 5

Progressive Disclosure

The body is a lean overview with a well-signaled Decision Tree routing each topic to one of 26 reference files (deployment.md, firewall.md, flags.md, etc.); all referenced files exist in references/ and are one level deep (at most a single cross-link, no nested chains). Content is appropriately split — no bulk reference material is inlined.

5 / 5

Total

20

/

20

Passed

Description

92%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 with explicit Use-when triggers, a comprehensive concrete action list, and an explicit boundary redirect to a sibling skill. Its only weakness is the absence of literal command/file-invocation triggers (e.g., "vercel deploy", "vercel.json", "vc") that users commonly type verbatim.

Suggestions

Add a few literal invocation triggers users type verbatim — e.g., "vercel deploy", "vercel env", "vercel.json" — to close the gap in trigger_term_quality.

Mention the `vc` alias in the description so prompts using the short command form match naturally.

DimensionReasoningScore

Specificity

The description lists many concrete actions — "deploying, managing environment variables, linking projects, viewing logs, querying metrics, debugging a deployed app on Vercel… managing domains, managing feature flags with vercel flags" — giving comprehensive coverage of the CLI surface. It is not the anchor-4 case because no meaningful capability area of the CLI is left uncovered.

5 / 5

Completeness

Both halves are explicit: the "what" is given by the concrete action list, and the "when" is an explicit "Use when deploying… or interacting with the Vercel platform from the command line" clause with concrete trigger phrases, matching the anchor-5 pattern.

5 / 5

Trigger Term Quality

Natural user phrasing is well covered ("deploying", "viewing logs", "errors, 5xx responses, timeouts, slow routes, or a single failing request", "OpenTelemetry setup"), but the description omits literal invocation triggers users would actually type — "vercel deploy", "vercel env", "vercel.json", or the "vc" alias. This sits between anchor 4 ("good keyword coverage; a few natural terms missing") and anchor 5 ("including synonyms and file extensions").

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous (Vercel CLI from the command line) and the description actively prevents mis-triggering by redirecting overlapping scope: "Use the vercel-tracing skill instead for `vercel traces` span search, trace inspection, and sampling rules, or for OpenTelemetry setup". This is a clear anchor-5 fit with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

vercel/vercel-plugin

Path

skills/vercel-cli/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.