CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/vercel-automation/SKILL.md

The canonical home for this skill is vercel-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

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 automation skill with concrete tool sequences and useful pitfalls. Its main weaknesses are duplicated pitfall content, a redundant summary table, no validation loops around destructive operations (env var deletion, DNS changes), and no use of reference files to keep SKILL.md lean.

Suggestions

Add validation checkpoints to destructive workflows: for env var deletion and DNS record create/update, include a verify step (e.g., re-list env vars or DNS records to confirm the change) and confirm-before-delete guidance.

De-duplicate content: the Known Pitfalls section repeats per-workflow pitfalls (write-only secrets, redeployment requirement) and the Quick Reference table restates workflow tool lists — consolidate each pitfall into one location and trim the redundant table or move it to a reference file.

Delete the vacuous closing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview') or replace it with concrete applicability guidance.

DimensionReasoningScore

Conciseness

The body is dense and operational, but pitfalls are stated twice ('Secret type vars are write-only; values cannot be retrieved after creation' appears in Workflow 3 and again in Known Pitfalls; 'Changes require a new deployment to take effect' also appears twice), the Quick Reference table largely restates the workflow tool lists, and the closing 'This skill is applicable to execute the workflow or actions described in the overview' adds nothing. Mostly efficient, but the duplication and filler could be tightened.

3 / 5

Actionability

Each workflow names concrete tool slugs (VERCEL_LIST_PROJECTS, VERCEL_CREATE_NEW_DEPLOYMENT) with numbered sequences annotated [Required]/[Optional]/[Prerequisite], plus key parameters like 'projectId', 'gitSource', 'type: A/AAAA/CNAME'. Falls short of 5 because no example values or call payloads are shown, leaving minor gaps.

4 / 5

Workflow Clarity

Sequences are clearly numbered with prerequisites and a setup validation checkpoint ('Confirm connection status shows ACTIVE before running any workflows'), but destructive operations lack verification steps — deleting an env var only warns 'requires both projectId and the env var id (not the key name)' with no confirm/verify loop, and DNS create/update has none either. Per the rubric, missing validation in destructive/batch workflows caps this at 3.

3 / 5

Progressive Disclosure

Sections are clearly organized (Prerequisites, Setup, six Core Workflows, Common Patterns, Quick Reference), but everything is inlined in one ~220-line file with no reference files; the 20-row Quick Reference table and per-domain parameter detail are content that could be split out. Good structure, but content that should be separate is inline.

3 / 5

Total

13

/

20

Passed

Description

66%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 trigger terms for Vercel platform operations. Its one material gap is the absence of any 'Use when...' trigger clause, which caps the heavily-weighted completeness dimension and leaves users without explicit guidance on when to invoke it.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user wants to manage Vercel deployments, domains, DNS records, environment variables, projects, or teams.'

Spell out 'environment variables' alongside 'env vars' and consider adding 'logs' and 'rollback' to broaden natural keyword coverage.

Move the behavioral instruction 'Always search tools first for current schemas' into the body, where it already exists in Prerequisites, to free description space for trigger guidance.

DimensionReasoningScore

Specificity

'manage deployments, domains, DNS, env vars, projects, and teams' names the domain and six concrete object areas with minor gaps in coverage. It falls short of 5 because the verbs are generic ('Automate', 'manage') rather than enumerated distinct actions, and above 3 because it covers far more than 1-2 actions.

4 / 5

Completeness

The 'what' is clear (automate Vercel platform operations across six areas), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the second sentence ('Always search tools first for current schemas') is behavioral instruction, not a trigger. Per the rubric guideline, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

'Vercel', 'deployments', 'domains', 'DNS', 'env vars', 'projects', and 'teams' are all natural terms a user would say, giving good keyword coverage. A few natural terms are missing (spelled-out 'environment variables', 'logs', 'rollback'), and 'Rube MCP (Composio)' is implementation jargon users would not say, so not 5.

4 / 5

Distinctiveness Conflict Risk

'Automate Vercel tasks via Rube MCP (Composio)' carves a clear niche with distinct triggers (Vercel, deployments, DNS), so conflict risk is low. Minor overlap remains with generic deployment/hosting or other Vercel-access skills, keeping it below 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/vercel-automation/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.