Name: agent-benchmark-suite
Rating: 42.6 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-benchmark-suite

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

2.17x

Quality

15%

Does it follow best practices?

Impact

89%

2.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-benchmark-suite/SKILL.md

The canonical home for this skill is agent-benchmark-suite in ruvnet/claude-flow

Quality

Content

17%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 verbose code dump of architectural class definitions rather than lean, actionable skill guidance. It lacks a clear step-by-step workflow with validation checkpoints and keeps everything inlined with no progressive disclosure to supporting files.

Suggestions

Collapse the four large class code blocks into a concise quick-start with one small executable example, moving detailed architectures into reference files under ./references/.

Replace the class scaffolding with a numbered workflow with explicit validation checkpoints (e.g. run benchmark -> compare to baseline -> flag regressions -> report), since benchmarking is a batch operation that the rubric requires validation for.

Remove non-executable pseudocode references (undefined ThroughputBenchmark/mcp.* classes) and keep only runnable commands or copy-paste-ready snippets.

Dimension	Reasoning	Score
Conciseness	The body is ~660 lines dominated by large JavaScript class dumps (ComprehensiveBenchmarkSuite, RegressionDetector, etc.) that heavily pad the skill and do not assume Claude's competence, matching the 'severely verbose; heavily padded' anchor.	1 / 5
Actionability	Concrete bash commands (e.g. 'npx claude-flow benchmark-run --suite comprehensive') and metric configs exist, but the bulk is non-executable architectural class scaffolding referencing undefined classes (ThroughputBenchmark, mcp.*), fitting the 'minimal concrete executable guidance' anchor.	2 / 5
Workflow Clarity	There is no sequenced multi-step workflow guiding Claude through the task; validation logic is buried inside illustrative class methods rather than presented as explicit checkpoints, matching the 'rough sequence present but steps poorly defined' anchor.	2 / 5
Progressive Disclosure	No bundle files exist and the body is a monolithic inlined wall of code with section headers but no one-level-deep references, matching 'minimal structure; content that clearly belongs in separate files is inlined'.	2 / 5
	Total	7 / 20 Passed

Description

12%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 frontmatter description is a templated placeholder that names the domain but does not explain what the skill concretely does or when to invoke it. It reads as auto-generated boilerplate rather than a meaningful trigger description.

Suggestions

Replace the placeholder with concrete capability actions, e.g. 'Run performance benchmarks, detect regressions against baselines, and validate throughput/latency against SLAs'.

Add an explicit 'Use when...' trigger clause naming natural user phrases such as 'benchmark performance', 'performance regression', or 'validate SLA'.

Drop the internal invocation syntax ('$agent-benchmark-suite') from the user-facing description; keep third-person capability language only.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for benchmark-suite - invoke with $agent-benchmark-suite' names a domain but states no concrete capability actions, matching the 'entirely vague; no concrete actions' anchor (cf. 'Helps with documents').	1 / 5
Completeness	It gives a vague 'what' (an agent skill for benchmarking) but no 'when' / 'Use when...' trigger guidance, fitting the 'vague what and no when' anchor rather than score 1 only because a domain is at least named.	2 / 5
Trigger Term Quality	The only terms are 'benchmark-suite' and the invocation syntax '$agent-benchmark-suite', which are technical/internal jargon rather than natural phrases a user would say, matching the 'no natural keywords; only technical jargon' anchor.	1 / 5
Distinctiveness Conflict Risk	'benchmark-suite' provides a slight niche, but the boilerplate 'Agent skill for ... - invoke with ...' template is generic and overlaps with any other templated agent skill, fitting the 'very broad; high overlap risk' anchor.	2 / 5
	Total	6 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (670 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-benchmark-suite/SKILL.md
Commit: fa13ee4

Reviewed: about 8 hours 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.