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

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands, a clear sequenced workflow, and clean one-level-deep reference structure. Its only weakness is moderate redundancy where the example heartbeat prompt restates criteria already in the Check Status section.

Suggestions

Trim the example heartbeat prompt so it references the ready/failure criteria from "Check Status" instead of re-listing them inline, cutting ~10 lines of duplication.

In "Resolve Links", reconcile the two script paths shown (the prose `scripts/extract-vercel-links.py` vs. the example `.agents/skills/vercel/scripts/extract-vercel-links.py`) or note that the latter is the deployed path, to avoid confusion.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the example heartbeat prompt (~20 lines) re-states the ready/failure criteria and commands already covered in "Check Status", so it could be tightened; not the score-3 "every token earns its place" level.	2 / 3
Actionability	Quotes executable commands `vercel inspect <deployment-or-preview-url>`, `curl -I -L --max-time 20 <preview-url>`, and `python3 .agents/skills/vercel/scripts/extract-vercel-links.py`, plus a copy-paste-ready heartbeat prompt template and concrete cadence (one-minute, 30 attempts) — fully actionable.	3 / 3
Workflow Clarity	A clear 4-step sequence (Resolve → Check → Create → Tell) with an explicit pre-check ("Check whether it is already ready") and enumerated terminal/monitorable states; the heartbeat acts as the validate→retry feedback loop, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Well-organized into sections (Overview, Project Selection, Workflow, Resolve Links, Check Status, Create The Monitor) with a single one-level-deep reference to the real `scripts/extract-vercel-links.py`; no monolithic wall or nested references.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, third-person, and explicitly triggered, covering both what the skill does and when to invoke it with natural user terms. It occupies a distinct niche unlikely to collide with other skills.

Dimension	Reasoning	Score
Specificity	Quotes "Set up a Codex monitor for Vercel deployments and preview URLs" and "wants to be notified with both the deployment URL and preview URL" — it lists multiple concrete actions (set up monitor, watch/monitor, wait for ready, notify with URLs), matching the score-3 anchor rather than the single-domain score-2 anchor.	3 / 3
Completeness	Clearly answers what ("Set up a Codex monitor for Vercel deployments and preview URLs") and when via an explicit "Use when the user invokes /vercel or $vercel..." clause, satisfying the score-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	Quotes "/vercel or $vercel", "watch or monitor a Vercel deployment", "waits for a Vercel preview or PR preview to become ready", and "notified" — strong coverage of natural terms users would say; above the score-2 anchor which misses common variations.	3 / 3
Distinctiveness Conflict Risk	A narrow niche (Codex monitoring of a specific Vercel deployment) with distinct triggers like "/vercel" and "$vercel" makes conflict with other skills unlikely; clearer than the score-2 "could still overlap" anchor.	3 / 3
	Total	12 / 12 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: 06f2fd7

Reviewed: 2 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.