Name: benchmark-agents
Rating: 59.2 (1 reviews)
Author: vercel

benchmark-agents

Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow DevKit, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration. Designed to stress-test skill injection for complex, multi-system builds.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/benchmark-agents/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands and a clearly sequenced, validated eval workflow, but it is verbose and keeps everything in one large file with embedded version-history that should be split out. Splitting reference material into bundle files and trimming redundancy would improve conciseness and progressive disclosure.

Suggestions

Move the 'Common Issues Found in Evals' version-history table and the full 'Scenario Table' into separate reference files (e.g. references/SCENARIOS.md, references/ISSUES.md) and link to them from the body, restoring token efficiency and one-level-deep progressive disclosure.

Consolidate the 11-item 'DO NOT' list and the parallel 'Never use ...' rationale into a single concise prohibitions section to remove redundancy.

Relocate time-sensitive version numbers into an explicit 'Deprecated / historical fixes' section so they no longer penalize conciseness.

Dimension	Reasoning	Score
Conciseness	The body is concrete but very long (~310 lines) with redundancy across the DO NOT list, scenario table, and complexity tiers, and the 'Common Issues' table embeds time-sensitive version numbers (v0.9.5, v0.9.9) outside any deprecated/old-patterns section, which the guidelines penalize.	2 / 3
Actionability	It provides copy-paste-ready bash commands for setup, launch, monitoring, and verification, plus specific grep checks for generated code, so the guidance is fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The eval loop is explicitly sequenced (setup → launch → monitor → verify → fix → release → repeat) with numbered steps and concrete verification checkpoints, including a feedback loop for fixing skills and re-running evals.	3 / 3
Progressive Disclosure	The file is well-sectioned but monolithic at ~310 lines with no bundle files; content that could live in separate references (the scenario table, complexity tiers, and common-issues/version-history table) is inline, so navigation and content-splitting are only partial.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 is specific to a niche and lists concrete platform features, but it lacks an explicit 'Use when...' trigger clause and uses abstract actions and jargon instead of natural user-facing trigger terms. Adding a trigger clause and concrete action verbs would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when benchmarking Claude Code plugin skill injection across Vercel platform features, or when running eval loops to verify skill injection and PostToolUse validation.'

Replace abstract verbs ('push', 'stress-test') with concrete actions the skill performs, e.g. 'Launches interactive Claude Code sessions, verifies skill injection from claim dirs, and produces a coverage report.'

Soften product-name jargon with natural phrasings a user might actually say, such as 'agent evals', 'skill injection checks', and 'coverage reports'.

Dimension	Reasoning	Score
Specificity	The description names the domain and enumerates platform features ('Workflow DevKit, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox') but the actions are abstract ('push', 'stress-test') rather than concrete verbs describing what the skill does, and it omits the actual eval-loop actions found only in the body.	2 / 3
Completeness	It answers 'what' (benchmark scenarios that stress-test skill injection) but provides no 'Use when...' or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some relevant terms ('benchmark scenarios', 'stress-test skill injection') but leans on technical jargon and product names rather than phrases a user would naturally say; common natural-language variations are absent.	2 / 3
Distinctiveness Conflict Risk	The scope is a clear niche — Vercel plugin skill-injection benchmarking — with distinctive terms unlikely to overlap with or trigger unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vercel/vercel-plugin
Path: .claude/skills/benchmark-agents/SKILL.md
Commit: 19606ac

Reviewed: 1 day 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.