CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vercel-agent

Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.

59

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/vercel/skills/vercel-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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-organized, token-efficient overview of Vercel Agent with accurate concrete facts (pricing, gating, config location, triggers). It is weakest as an instructional document: no executable steps or validation checkpoints for using the capabilities it describes.

Suggestions

Add concrete invocation steps per capability, e.g. how to request an investigation on an anomaly alert, where review results appear, and how to verify the SDK-install PR.

Remove the redundant 'You are an expert in Vercel Agent' opener, which repeats the 'What It Is' section.

Include example commands or comment syntax (e.g. the exact '@vercel' PR comment form) so guidance is copy-paste actionable.

DimensionReasoningScore

Conciseness

A lean, bullet-driven ~46-line body that assumes Claude's competence and explains nothing it already knows; the only real padding is the 'You are an expert in Vercel Agent — AI-powered development tools built into the Vercel platform' opener, which duplicates the 'What It Is' section. Fits anchor 4 (efficient, minor trims possible) rather than 5.

4 / 5

Actionability

Contains concrete facts (config URL 'https://vercel.com/{team}/{project}/settings → AI section', '@vercel' mention trigger, '$0.30 per Code Review', 'Requires Observability Plus') but the guidance is descriptive rather than instructive — no commands or specific steps for triggering an investigation, reviewing output, or verifying an SDK-install PR. Anchor 3 (some concrete guidance but incomplete) fits; not 4 because most capability sections lack executable specifics.

3 / 5

Workflow Clarity

The 'When to Use' section gives clear usage triggers, but the body presents no sequenced process or checkpoints for any of the three capabilities — it is a product overview, not a workflow. Anchor 3 (sequence/structure present but checkpoints missing) is the best fit; it does not reach 4 because no capability shows an ordered procedure with validation.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files present and no content that needs external files; sections are well organized (What It Is, Capabilities, Pricing, Configuration, When to Use, References) with a single clearly signaled one-level reference link. Per the simple-skill exception, this matches the top anchor.

5 / 5

Total

15

/

20

Passed

Description

75%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 a clear third-person statement of capabilities and an explicit 'Use when...' clause. Its main weaknesses are a generic when-clause ('Vercel's AI development tools') and missing natural trigger variations that users would actually say.

Suggestions

Replace the generic when-clause with concrete triggers, e.g. 'Use when the user mentions Vercel Agent, @vercel in PR comments, anomaly alert investigation, or installing Web Analytics/Speed Insights SDKs'.

Distinguish the skill from Vercel's AI SDK product explicitly to reduce wrong-skill triggering.

Lead with what the skill itself provides (platform-level guidance) rather than the vague 'Vercel Agent guidance' opener.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'code review, incident investigation, and SDK installation', 'Automates PR analysis and anomaly debugging' — but the opening 'Vercel Agent guidance' is generic and the actions describe the product rather than what the skill enables, so it sits between anchors 4 and 5.

4 / 5

Completeness

Both an explicit 'what' ('AI-powered code review, incident investigation, and SDK installation... Automates PR analysis and anomaly debugging') and an explicit 'when' ('Use when configuring or understanding Vercel's AI development tools') are present, but the when-clause is generic rather than using concrete trigger phrases, fitting anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('code review', 'PR analysis', 'incident investigation', 'anomaly debugging', 'SDK installation', 'configuring', 'Vercel') but missing common user variations such as '@vercel', 'PR review', and 'anomaly alerts', matching the 'a few natural terms missing' anchor rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The 'Vercel Agent' niche is mostly distinct with clear product-specific triggers, but 'Vercel's AI development tools' overlaps with the separate Vercel AI SDK product line, creating minor conflict risk consistent with anchor 4 rather than the minimal-risk anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/vercel-agent/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.