vercel

Set up a Codex monitor for Vercel deployments and preview URLs. Use when the user invokes /vercel or $vercel, asks Codex to watch or monitor a Vercel deployment, waits for a Vercel preview or PR preview to become ready, or wants to be notified with both the deployment URL and preview URL once Vercel is READY.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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, prescriptive skill body: it pins every risky decision (immutable deployment IDs, machine-readable state, no alias-based readiness), provides executable commands and a self-contained monitor prompt, and includes explicit validation and failure-recovery steps. The only improvement available is trimming the triple-stated preview-alias rule outside the heartbeat template.

Dimension	Reasoning	Score
Conciseness	No padding and no explanations of concepts Claude already knows — every section is Vercel/Codex-specific operational instruction. It falls short of anchor 5 only because the alias/state rule is stated three times ("Never monitor a branch preview alias", "never use it for state checks", "Never curl the preview URL to determine readiness"), though the repetition inside the heartbeat template is justified by the stated self-containment requirement.	4 / 5
Actionability	Fully executable throughout: "python3 .agents/skills/vercel/scripts/check-deployment.py <deployment-id-or-url>", "vercel list remotion --scope remotion --format=json" with exact JSON matchers (".meta.githubCommitSha == <full commit SHA>"), a concrete URL transformation example, and a copy-paste heartbeat prompt template. The referenced script exists in the bundle and behaves as described.	5 / 5
Workflow Clarity	Clear sequence (resolve → read state → create monitor) with explicit checkpoints: an ordered 1-4 resolution source list, a terminal/in-progress/unknown state map, a pre-flight validation step ("Before creating a heartbeat, run the checker once. If the deployment is already terminal, report immediately"), and an error-recovery branch ("ask for the Vercel dashboard URL, PR number, or commit SHA"). This matches the anchor-5 pattern of explicit validation plus feedback loops.	5 / 5
Progressive Disclosure	The one bundle file (scripts/check-deployment.py) is well-signaled and referenced consistently, one level deep, and the checker's ~170 lines of validation/normalization logic are correctly delegated to it instead of inlined in SKILL.md. Sections are clearly headed and the body stays at overview-plus-orchestration altitude, matching the anchor-5 structure.	5 / 5
	Total	19 / 20 Passed

Description

95%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: it states one concrete capability in third person, then gives an unusually thorough "Use when" clause covering slash-command invocation, natural watch/monitor phrasings, and the readiness-notification outcome. Its only soft spot is that the "what" is a single capability expressed with roughly two concrete verbs, which is appropriate for the skill's narrow scope.

Dimension	Reasoning	Score
Specificity	Concrete actions are named — "Set up a Codex monitor" and "notified with both the deployment URL and preview URL" — and cover this skill's narrow scope completely. It sits above anchor 3 ("1-2 concrete actions, but not comprehensive") because coverage is complete for the single task, but below anchor 5, which expects multiple distinct listed actions rather than roughly two.	4 / 5
Completeness	Explicitly answers both questions: the "what" ("Set up a Codex monitor for Vercel deployments and preview URLs") and a full "Use when..." clause with concrete trigger phrases. This matches the anchor-5 example pattern exactly; anchor 4 would require the "when" to be less explicit or specific than it is here.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms: "watch or monitor a Vercel deployment", "waits for a Vercel preview or PR preview to become ready", and "invokes /vercel or $vercel". These are the exact phrasings a user would naturally say when needing this skill; no common variation is missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — "/vercel", "Vercel deployment", "preview URL once Vercel is READY" — that no generic deployment, CI, or URL skill would claim. Minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: remotion-dev/remotion
Path: .agents/skills/vercel/SKILL.md
Commit: 6f4e0d5

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.