agent-benchmark-suite

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

2.17x

Quality

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

Quality

Content

15%

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

The body is an oversized, monolithic dump of non-executable JavaScript scaffolding that describes capabilities rather than guiding Claude through a clear, validated workflow. It lacks any progressive disclosure structure and wastes the context budget on padding.

Suggestions

Replace the class scaffolding with a lean overview plus a concrete, sequenced workflow (run benchmarks -> compare to baseline -> detect regressions -> validate) with explicit validation checkpoints.

Provide executable examples (real commands with concrete inputs) instead of pseudocode classes referencing undefined 'mcp.*' and placeholder methods.

Move detailed benchmark definitions and class internals into reference files (e.g. references/benchmarks.md) and keep SKILL.md as a concise entry point with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The body is ~660 lines of sprawling JavaScript class scaffolding with placeholder constructors (e.g. 'new ThroughputBenchmark()') and redundant headings, far exceeding a token-efficient overview and explaining structure Claude already understands.	1 / 3
Actionability	It provides some concrete elements (bash commands like 'npx claude-flow benchmark-run --suite comprehensive --duration 300' and benchmark target tables), but the JavaScript is non-executable scaffolding referencing undefined classes and 'mcp.*' calls, so it is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The content is a catalog of class definitions rather than a sequenced workflow, and it lacks explicit validation checkpoints or feedback loops despite covering batch/regression monitoring operations where the rubric caps clarity at 2 absent such loops.	1 / 3
Progressive Disclosure	It is a monolithic wall of text with no references, scripts, or assets directory and no navigation signaling; all content sits inline in a single file, matching the 'monolithic' anchor.	1 / 3
	Total	5 / 12 Passed

Description

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 generic template string that names the skill but states no concrete capabilities and provides no usage triggers. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the description with concrete actions, e.g. 'Run performance benchmarks, detect regressions, and validate SLA/scalability targets against baselines'.

Add an explicit trigger clause such as 'Use when the user asks to benchmark performance, check for performance regressions, or validate throughput/latency SLAs'.

Drop the meta 'invoke with $agent-benchmark-suite' phrasing in favor of natural user-facing language.

Dimension	Reasoning	Score
Specificity	The description is 'Agent skill for benchmark-suite - invoke with $agent-benchmark-suite', which names no concrete actions, only a domain label and an invocation token, matching the 'vague or no actions' anchor.	1 / 3
Completeness	It states only a name-based 'what' and has no 'Use when...' or equivalent trigger guidance, so it misses both a clear what and the when, capping completeness at the lowest level.	1 / 3
Trigger Term Quality	The only term is 'benchmark-suite' plus the literal '$agent-benchmark-suite' token; there are no natural keywords a user would say (e.g. 'benchmark performance', 'detect regressions'), so it falls at the jargon/generic level.	1 / 3
Distinctiveness Conflict Risk	The templated wording is indistinguishable from any other agent skill and carries no distinctive triggers, so it would conflict broadly with similar skills.	1 / 3
	Total	4 / 12 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: 26c35b5

Reviewed: about 6 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.