CtrlK
BlogDocsLog inGet started
Tessl Logo

vercel-optimize

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.

75

Quality

92%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a high-quality, complex skill that orchestrates a multi-step Vercel optimization audit pipeline with strong actionability and workflow clarity. Every pipeline step has executable commands, explicit validation gates, and clear error-handling paths. The progressive disclosure is well-structured with appropriate delegation to reference files. Minor conciseness improvements are possible—some scope-resolution guidance is repeated and a few prompt templates could be referenced rather than inlined—but overall the content density is justified by the complexity of the task.

DimensionReasoningScore

Conciseness

The skill is lengthy but most content earns its place—complex multi-step pipeline with specific blockers, error handling, and edge cases. However, some sections are repetitive (scope resolution is explained multiple times) and the unsupported framework prompt template could be referenced rather than inlined. It respects Claude's intelligence in most areas but could be tightened by ~20%.

2 / 3

Actionability

Excellent actionability throughout: every pipeline step has exact, copy-paste-ready bash commands with specific script names, flags, file paths, and output redirection. Error handling paths have concrete commands (e.g., `vercel link --yes --project <project-name-or-id> --team <team-slug>`). The blocker resolution table maps each error code to a specific action.

3 / 3

Workflow Clarity

The pipeline is clearly sequenced (Collect → Gate → Deep-dive → Verify → Render) with explicit validation checkpoints: JSON parse validation after collection, blocker checks before gating, reconciliation to disprove candidates before investigation, verification with regen loops for failed recommendations, and a final render step that controls customer-visible output. Feedback loops are present (regenPlan entries trigger re-investigation).

3 / 3

Progressive Disclosure

The skill serves as a clear orchestration overview and consistently delegates detailed content to well-signaled one-level-deep references: doctrine.md, data-collection.md, recommendations.md, verification.md, scanner-patterns.md, scoring.md, voice.md, observability-plus.md, candidates.md, and docs-library.json. Navigation is easy with inline links. No bundle files were provided to verify these exist, but the referencing pattern is exemplary.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong, well-crafted skill description that clearly defines its scope (Vercel cost and performance optimization), specifies concrete actions (collect metrics, investigate candidates, produce ranked recommendations), and provides an explicit trigger clause with extensive natural keywords. The description is concise yet comprehensive, covering the what, when, and how without unnecessary verbosity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: collect Vercel metrics, usage, project config, and code scan results; investigate metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware docs. Also names specific frameworks (Next.js, SvelteKit, Nuxt, Astro).

3 / 3

Completeness

Clearly answers both 'what' (collect metrics, investigate candidates, produce ranked recommendations) and 'when' with an explicit trigger clause listing specific scenarios like bill reduction, slow routes, caching opportunities, and various Vercel-specific metrics.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'Vercel bill reduction', 'slow or expensive routes', 'caching opportunities', 'Function Invocations', 'Build Minutes', 'Fast Data Transfer', 'Core Web Vitals', 'Bot Management', 'Fluid compute', 'cost breakdown'. These are terms a user dealing with Vercel cost/performance issues would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Vercel-specific cost and performance optimization. The combination of Vercel platform specificity, named metrics (Function Invocations, Build Minutes, Fast Data Transfer), and the optimization/cost-reduction focus makes it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
vercel-labs/agent-skills
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.