CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vercel-cli-with-tokens

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

The canonical home for this skill is vercel-cli-with-tokens in vercel-labs/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-sequenced CLI skill with executable commands, validation checkpoints, feedback loops, and approval gates for destructive operations. The main cost is mild redundancy (duplicated token warning, repeated deploy commands, and an inline pricing/features list) that inflates the token budget.

Suggestions

Deduplicate the --token guidance: keep the Bad/Good example in Step 1 and drop the repeated 'Never pass VERCEL_TOKEN as a --token flag' bullet from Working Agreement (or vice versa).

Trim or move the 'What Pro gives you' pricing/feature list (fees, vCPU specs, seat allocations) into a short reference or a one-line link to https://vercel.com/docs/plans/pro-plan, keeping only the upgrade/downgrade commands inline.

Consolidate the identical 'vercel deploy --scope <team-slug> -y --no-wait' command shown in both Quick Deploy and Full Deploy Flow B into a single shared 'Deploy' step referenced from both paths.

DimensionReasoningScore

Conciseness

The body is mostly command-dense with no conceptual padding, but it is noticeably loose in places: the --token warning appears twice (the 'Important' note in Step 1 and again in Working Agreement), the same deploy command is repeated across Quick Deploy and Full Deploy Flow B, and 'What Pro gives you' spends lines on pricing/marketing detail ('$20/month platform fee', 'Turbo build machines (30 vCPUs, 60 GB memory)') beyond what acting on the instruction requires. This is 'mostly efficient but could be tightened', not merely minor trims.

3 / 5

Actionability

Fully executable copy-paste commands with concrete flags throughout — 'vercel deploy --scope <team-slug> -y --no-wait', 'echo "value" | vercel env add VAR_NAME production --scope <team-slug>', 'vercel link --repo --scope <team-slug> -y' — with scenario branches covering the common cases (token in env, .env, renamed var, missing).

5 / 5

Workflow Clarity

Clear ordered scenario tree ('Work through these scenarios in order' A–D with an ask-the-user fallback), explicit validation steps ('vercel --version', 'vercel whoami', 'vercel inspect <deployment-url>'), feedback loops in Troubleshooting (auth error → whoami → fresh token; build failure → --logs → causes), approval checkpoints for destructive ops ('Ask the user before pushing. Never push without explicit approval'), and a checklist-style Working Agreement. Not a 4 because validation and error-recovery loops are present at every risky step.

5 / 5

Progressive Disclosure

No bundle files exist; the ~345-line body is a single file with clear, logically ordered section headers and one external docs link, making navigation easy. It is not a 5 because the environment-variable, domain, and Stripe plan reference material is all inline in SKILL.md where a references/ file could carry the bulk, though nothing is severely misplaced.

4 / 5

Total

17

/

20

Passed

Description

82%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 in third-person voice with an explicit 'Use when...' clause and natural quoted trigger phrases. Its only weakness is that the what-statement covers just deploy/manage while the skill body also handles environment variables, domains, and logs.

DimensionReasoningScore

Specificity

The what-statement 'Deploy and manage projects on Vercel using token-based authentication' names the domain plus one concrete action ('Deploy') and one generic one ('manage projects'); broader capabilities (env vars, domains, deployments) never appear in the what-clause, matching the 'domain and 1-2 concrete actions' anchor rather than 'several specific actions'.

3 / 5

Completeness

It clearly states what ('Deploy and manage projects on Vercel using token-based authentication') and when, via an explicit 'Use when working with Vercel CLI using access tokens rather than interactive login' clause with concrete quoted trigger phrases — the anchor-5 pattern exactly. Not a 4 because the when-clause is fully explicit with example triggers.

5 / 5

Trigger Term Quality

Quoted phrases 'deploy to vercel', 'set up vercel', and 'add environment variables to vercel' are natural user utterances, plus 'access tokens' and 'interactive login'. A few common variations are missing (e.g. 'vercel login', 'production deploy', 'add a domain'), which fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

A clear Vercel-specific niche further disambiguated by 'using access tokens rather than interactive login', with distinct trigger phrases; minimal overlap risk with any other skill.

5 / 5

Total

17

/

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

boranfurkan/reproducer-hackathon

Path

skills/.agents/skills/vercel-cli-with-tokens/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.