CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

71%

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.

The content is a clean, well-structured overview of Vercel Agent's capabilities and pricing, but it is largely descriptive rather than instructional — missing the concrete, executable configuration steps the description's trigger promises. Progressive disclosure and conciseness are strong; actionability and workflow clarity lag.

Suggestions

Add a concrete, step-by-step configuration workflow (e.g., navigate to the settings AI section, enable specific toggles, verify via a test PR) so the "configuring" trigger is actionable.

Replace descriptive capability bullets with explicit invocation guidance — how to trigger a review (`@vercel` in a PR comment vs. push), what inputs Vercel Agent needs, and how to read its output.

Add a validation checkpoint to the installation workflow (e.g., confirm the SDK is imported and events appear in the dashboard before merging the PR).

DimensionReasoningScore

Conciseness

The body is well-sectioned and mostly lean, with only minor padding such as "You are an expert in Vercel Agent" and the restated definition in "What It Is" that could be trimmed.

4 / 5

Actionability

It gives some concrete pointers (config URL `https://vercel.com/{team}/{project}/settings` → AI section, `@vercel` trigger syntax) but provides no executable steps, commands, or code for configuring or invoking the tool, leaving guidance incomplete.

3 / 5

Workflow Clarity

Capability lists (e.g., Installation: "Analyzes repo structure, installs dependencies, writes integration code, Creates PRs") give a rough sequence, but there are no explicit validation checkpoints or ordered steps for Claude to follow.

3 / 5

Progressive Disclosure

At under 50 lines with clearly organized sections and a single one-level external docs reference, the body matches the simple-skill exception where well-organized sections alone warrant a top score.

5 / 5

Total

15

/

20

Passed

Description

78%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.

The description clearly states the skill's domain and concrete capabilities with an explicit "Use when" trigger and a distinctive Vercel-scoped niche. It is slightly below top marks only because the trigger clause and synonym coverage could be more comprehensive.

DimensionReasoningScore

Specificity

Names several concrete actions — "AI-powered code review, incident investigation, and SDK installation" and "Automates PR analysis and anomaly debugging" — with only minor coverage gaps, fitting the "lists several specific actions" anchor rather than the comprehensive 5.

4 / 5

Completeness

Both "what" (review, investigation, installation) and "when" ("Use when configuring or understanding Vercel's AI development tools") are present, but the trigger clause is narrower than the multi-phrase concrete example that defines a 5.

4 / 5

Trigger Term Quality

Includes natural user-facing terms like "code review", "incident investigation", "SDK installation", and "configuring or understanding Vercel's AI development tools", with good but not exhaustive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

Scoped to a named platform feature ("Vercel Agent", "Vercel's AI development tools") with distinct, low-overlap triggers and no generic phrasing that would misfire against unrelated skills.

5 / 5

Total

17

/

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.

Validation14 / 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
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.