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

100%

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

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.

The body is a textbook progressive-disclosure skill: lean and dense with platform-specific gotchas, exact executable commands, an explicit pre-mutation validation workflow with error-recovery handling, and a complete routing table whose targets all exist. No dimension shows a real weakness.

DimensionReasoningScore

Conciseness

The ~85-line body contains no concept explanations Claude already knows (no "what is Vercel" filler) and every paragraph carries non-obvious operational facts (stdout vs stderr parsing, help commands exiting 2, the `next`-command error JSON, project.json vs repo.json resolution rules). Matches the 5 anchor ("lean and efficient; every token earns its place"); the only near-duplication (the --help advice in the intro) states a distinct rule and does not rise to the 4 anchor's "minor instances of over-explanation".

5 / 5

Actionability

Commands are copy-paste ready with exact flags throughout: `vercel project inspect --non-interactive`, `vercel whoami --format json`, `vercel deploy --force` without `--with-cache`, `vercel curl`, `VERCEL_TOKEN` instead of `--token`, and a runnable Quick Start block. The common cases are covered concretely and vaguer directions are paired with the exact corrective command (e.g. the anti-patterns each name the fix), matching the 5 anchor.

5 / 5

Workflow Clarity

The Quick Start gives a clear sequence (install → login → link → pull → dev → deploy), and the Critical Project Linking section provides an explicit pre-mutation validation gate ("run `vercel project inspect --non-interactive` ... and confirm the reported owner and project", "stop on `link_required` or a target mismatch") with error-recovery guidance for the JSON `status`/`reason`/`hint`/`next` error objects and cautions against auto-running follow-ups. Consequential mutations are explicitly gated by validation, satisfying the 5 anchor including its feedback loops and checklist (the Decision Tree acts as one).

5 / 5

Progressive Disclosure

The body is a clean router: a Decision Tree maps every symptom to one of 26 real reference files (all verified to exist), one level deep, with no inlined bulk detail that belongs in a reference. This matches the 5 anchor ("clear overview with well-signaled one-level-deep references"); the few cross-links between reference files (e.g. deployment.md → project-infra.md) are sibling see-also navigation, not deferred content chains, so the 1-anchor nesting penalty does not apply.

5 / 5

Total

20

/

20

Passed

Description

100%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 model description: third-person voice, an explicit what-statement followed by an explicit "Use for..." when-clause, comprehensive natural-language triggers including command names, and an unambiguous Vercel-only niche. No fluff or over-claims; the length is spent entirely on trigger coverage, not padding.

DimensionReasoningScore

Specificity

Opens with four concrete action verbs ("Deploy, manage, inspect, and troubleshoot") and then enumerates the concrete capability surface — "Vercel Toolbar comments", "Container Registry (VCR)", "Blob storage", "feature flags (`vercel flags`)" — covering essentially the whole CLI. This matches the 5 anchor ("Lists multiple specific concrete actions; comprehensive coverage") rather than 4, since there are no meaningful coverage gaps.

5 / 5

Completeness

Explicitly answers both questions: what ("Deploy, manage, inspect, and troubleshoot Vercel projects from the command line") and when ("Use for Vercel deployments, Vercel Toolbar comments, build failures, ..."). The explicit "Use for..." clause with concrete trigger phrases is exactly the 5 anchor; 4 would require the when-clause to be weaker or less specific.

5 / 5

Trigger Term Quality

Natural user phrasings are covered comprehensively with synonyms and exact command names: "build failures", "domains and DNS", "logs", "cron jobs", "preview access", "local development", plus command forms like "`vercel flags`" and "`vercel api` fallback". This is the 5 anchor ("comprehensive coverage of natural terms including synonyms"), not 4 ("a few natural terms missing") — no commonly-said trigger for this domain is absent.

5 / 5

Distinctiveness Conflict Risk

A clear niche (the Vercel platform CLI) with brand-anchored triggers ("Vercel deployments", "`vercel flags`", "Container Registry (VCR)"), so it is unlikely to fire for a non-Vercel skill. This is the 5 anchor ("clear niche with distinct triggers; minimal conflict risk"); 4 would involve residual overlap with closely related skills, which is not the case.

5 / 5

Total

20

/

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

openclaw/clawhub

Path

.agents/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.