vercel-deployment

Vercel deployment workflows, environment management, domain configuration, and build troubleshooting. Use when deploying, checking deployment status, reviewing build logs, or managing environments.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./src/orchestrator/plugins/vercel/SKILL.md

Quality

Content

82%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 concise, well-structured skill body that leans on tables and concrete MCP payloads rather than padding, with a real fix-verify-retry feedback loop in the troubleshooting workflow. The remaining gaps are execution details — an env-var tool that doesn't exist in the tool table, unresolved payload identifiers, and underdeveloped cron guidance.

Suggestions

Reconcile the environment-variable guidance with the tool inventory: either name the MCP tool that reads/sets env vars or state how to verify scopes via get_project / the Vercel dashboard.

Show how to obtain deployment_id and project_id (e.g., via list_deployments and get_project) before the payload examples that use them.

Either add a minimal vercel.json crons[] example or drop the cron section, since the current two-line stub is not actionable.

Dimension	Reasoning	Score
Conciseness	Lean throughout: tables for tool inventory, branch-to-environment mapping, and env var scopes; no explanation of concepts Claude already knows; project-specific detail is deferred to an external config file. The JSON payload examples add payload-structure information the tool table does not, so every section earns its place.	5 / 5
Actionability	Concrete MCP tool names, exact JSON payload templates, and a common-causes checklist make the guidance mostly executable. Not 5: "Verify required env vars exist in production and preview scopes" has no corresponding tool in the tool table, and there is no guidance on obtaining the deployment_id/project_id values the payload examples require.	4 / 5
Workflow Clarity	The troubleshooting workflow is a numbered sequence with a verification step ("Verify deployment status") and an explicit feedback loop ("After re-deploying, re-check get_deployment_build_logs and get_runtime_logs... Repeat until build succeeds"). Not 5: no mapping from observed log symptoms to the listed common causes, and the happy-path deployment workflow is thin.	4 / 5
Progressive Disclosure	A self-contained, well-sectioned body with one clearly signaled one-level-deep reference for project specifics. Not 5: the cron-jobs section is a two-line stub with no example vercel.json snippet, and the referenced external path cannot be verified or expanded upon from the skill itself.	4 / 5
	Total	17 / 20 Passed

Description

73%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 solid description with an explicit Use-when trigger clause, natural trigger phrases, and a clear Vercel niche. The main weakness is specificity — capabilities are named as generic activity categories rather than concrete actions, which keeps it just below the top anchor on completeness and specificity.

Suggestions

Replace generic category labels with concrete actions, e.g. "Trigger deployments, check deployment status, read build and runtime logs, configure domains and environments" instead of "deployment workflows, environment management".

Add missing natural trigger terms and synonyms such as "production", "preview deployments", "rollback", or "when the user mentions Vercel" to broaden and sharpen the when-clause.

Dimension	Reasoning	Score
Specificity	Names the Vercel domain and several capability areas ("deployment workflows, environment management, domain configuration, and build troubleshooting"), but these are activity categories expressed with generic gerunds rather than concrete operations like "trigger deployments" or "read build logs". Fits anchor 3 better than 4 because the actions themselves are not concretely stated.	3 / 5
Completeness	Explicitly answers both what ("Vercel deployment workflows, environment management, domain configuration, and build troubleshooting") and when ("Use when deploying, checking deployment status, reviewing build logs, or managing environments"). Not 5 because the 'what' relies on category labels and the 'when' could be more specific, e.g. naming the platform trigger ("when the user mentions Vercel").	4 / 5
Trigger Term Quality	"deploying, checking deployment status, reviewing build logs, or managing environments" are natural phrases users would say, giving good keyword coverage. Falls short of 5 because common synonyms and variations (e.g., "ship to production", "preview deployments", "rollback", "logs") are missing.	4 / 5
Distinctiveness Conflict Risk	"Vercel" is a strong niche marker with distinct, platform-specific triggers (deployment status, build logs, Vercel environments); minimal conflict risk with generic CI/CD or hosting skills.	5 / 5
	Total	16 / 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: monkilabs/opencastle
Path: src/orchestrator/plugins/vercel/SKILL.md
Commit: c0f4566

Reviewed: 1 day 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.