agent-v3-performance-engineer

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

3.20x

Quality

Does it follow best practices?

Impact

96%

3.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-v3-performance-engineer/SKILL.md

Quality

Discovery

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 an extremely poor description that provides virtually no useful information for skill selection. It only contains an invocation command and a generic label, failing on every dimension of the rubric. Claude would have no basis to select this skill appropriately from a pool of available skills.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Profiles application performance, identifies bottlenecks, optimizes query execution, and analyzes resource utilization.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions performance optimization, slow queries, latency issues, benchmarking, profiling, or resource bottlenecks.'

Specify the domain or technology scope (e.g., 'v3 API performance', 'backend services', 'database queries') to make the skill clearly distinguishable from other performance-related skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only states it's an 'agent skill' with an invocation command, providing zero information about what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command with no functional or contextual information.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'performance-engineer' embedded in the agent name, but there are no natural keywords a user would say. No terms like 'optimize', 'benchmark', 'latency', 'profiling', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. 'Performance engineer' could overlap with many domains (web performance, database optimization, load testing, etc.) and there's nothing to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

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

This skill is essentially a project specification document masquerading as an actionable skill. It presents ambitious performance targets and extensive pseudo-TypeScript benchmark classes, but none of the code is executable, no concrete steps are provided, and Claude cannot actually use any of this to perform optimization work. The content is extremely verbose while providing almost zero actionable guidance.

Suggestions

Replace pseudo-TypeScript classes with actual executable benchmark commands or scripts that Claude can run (e.g., specific npm commands, real test files to create and execute)

Add a clear step-by-step workflow: what to do first, how to measure baseline, how to apply optimizations, how to validate results, with explicit validation checkpoints

Reduce content by 80%+ - remove ASCII box diagrams, collapse benchmark classes into concise specifications of what to measure and how, and eliminate the fictional API calls

Split into a concise SKILL.md overview with references to separate files for benchmark specifications, target metrics, and coordination protocols

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. The ASCII box diagrams are decorative and redundant with the text. The TypeScript benchmark classes are lengthy pseudo-implementations that Claude cannot actually execute - they reference non-existent APIs (this.sona.adapt, this.agentDBMemory.hnswSearch, etc.). The entire document could be condensed to a fraction of its size.	1 / 3
Actionability	Despite containing extensive TypeScript code, none of it is executable - it references fictional classes, methods, and APIs (MetricCollector, this.flashAttention, this.spawn15Agents, etc.). There are no real commands, no actual benchmark scripts to run, no concrete steps Claude can take. The checklists are aspirational targets, not actionable instructions.	1 / 3
Workflow Clarity	There is no clear workflow or sequence of steps to follow. The document presents benchmark classes and target metrics but never explains what to actually do first, second, or third. No validation checkpoints exist for the optimization process. The 'Success Validation Framework' is just a checklist of desired outcomes, not a process.	1 / 3
Progressive Disclosure	The entire document is a monolithic wall of TypeScript pseudo-code and ASCII art with no references to external files. All content is inline regardless of detail level. There's no separation between overview/quick-start and detailed reference material - everything is dumped at the same level.	1 / 3
	Total	4 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: 398f7c2

Reviewed: 3 days 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.