vercel-automation

Automate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search tools first for current schemas.

2.15x

Quality

63%

Does it follow best practices?

Impact

97%

2.15x

Average score across 2 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/vercel-automation/SKILL.md

Quality

Content

57%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-structured, actionable MCP orchestration guide with concrete tool sequences and useful pitfalls. Its weaknesses are duplicated pitfall content, missing validation steps for destructive operations, and an inlined reference table with no progressive disclosure into separate files.

Suggestions

Add verification steps around destructive operations, e.g., "List env vars before deleting to confirm the ID" and "Verify DNS record state with VERCEL_GET_DNS_RECORDS after update."

Deduplicate the "Known Pitfalls" section against per-workflow pitfalls, or move pitfalls into the workflows and drop the section.

Move the Quick Reference table into a references/ file (e.g., REFERENCES.md) and link it, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tool sequences, parameters, pitfalls), but the "Known Pitfalls" section duplicates workflow-level pitfalls nearly verbatim ("Secret type vars are write-only" vs "type: 'secret' variables cannot be read back"; "A redeployment is needed" vs "Changes require a new deployment"), and it includes knowledge Claude already has ("MX records require priority values", "Implement backoff on 429 responses"). It fits anchor 3 rather than 4 because the redundancy is more than minor.	3 / 5
Actionability	Each workflow gives concrete tool slugs, ordered sequences with Required/Optional labels, key parameters, and ID-resolution patterns — mostly executable guidance. Not a 5 because structures like "gitSource: Git repository source with ref/branch info" are never concretized into an example payload.	4 / 5
Workflow Clarity	Sequences are clearly ordered and labeled ("When to use", Required/Optional, connection validation to ACTIVE), but destructive operations (VERCEL_DELETE_ENVIRONMENT_VARIABLE, VERCEL_UPDATE_DNS_RECORD) have no verification steps (e.g., list-before-delete, confirm-after-change). Per the rubric, missing validation in destructive/batch workflows caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the body runs ~220 lines with a 20-row inlined Quick Reference table plus repeated pitfall content that belongs in a separate reference file. Structure and section headers are present (better than a 2), but content that should be split out is inline with no references at all — anchor 3.	3 / 5
	Total	13 / 20 Passed

Description

70%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 specific, well-scoped description with strong natural keywords and minimal conflict risk. Its main weakness is the absence of any "Use when..." trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to deploy, inspect, or roll back Vercel deployments, manage DNS records, or set Vercel environment variables."

Replace the repeated generic verb "manage" with distinct concrete actions (e.g., "list and inspect deployments, trigger builds, add DNS records, set env vars").

Include a few common synonyms such as "environment variables" and "preview/production" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists six concrete capability areas ("manage deployments, domains, DNS, env vars, projects, and teams"), giving broad coverage. It falls short of a 5 because it relies on the single generic verb "manage" rather than distinct concrete actions, and above a 3 because it enumerates far more than 1-2 items.	4 / 5
Completeness	The "what" is clear ("Automate Vercel tasks... manage deployments, domains, DNS, env vars, projects, and teams"), but there is no "Use when..." clause or equivalent explicit trigger guidance; "Always search tools first for current schemas" is behavioral instruction, not a when-to-use trigger. Per the rubric guideline, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural keywords users would say are present: "Vercel", "deployments", "domains", "DNS", "env vars", "projects", "teams". Not a 5 because common synonyms and variations (e.g., "environment variables", "rollback", "preview deployments", "website") are missing.	4 / 5
Distinctiveness Conflict Risk	"Vercel tasks via Rube MCP (Composio)" carves out a clear niche with distinct, brand-specific triggers; minimal risk of firing for the wrong skill. Not a 4 because the named platform and MCP integration make overlap with other skills unlikely.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/vercel-automation/SKILL.md
Commit: c9856ea

Reviewed: 6 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.