CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-v3-performance-engineer

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

35

3.20x
Quality

0%

Does it follow best practices?

Impact

96%

3.20x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-v3-performance-engineer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

0%Scale 1-3

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

This skill is a verbose, aspirational document that describes hypothetical performance targets and benchmark classes without providing any executable or actionable guidance. The TypeScript code references non-existent APIs and cannot be run. It reads more like a product requirements document or marketing brief than an operational skill that Claude can follow to accomplish concrete tasks.

Suggestions

Replace hypothetical TypeScript classes with actual executable benchmark commands or scripts that can be run against real code (e.g., 'npm run benchmark:flash-attention' with expected output format).

Add a clear step-by-step workflow: what to measure first, how to run benchmarks, how to interpret results, and what to do when targets aren't met — with explicit validation checkpoints.

Reduce content by 80%+ — remove ASCII box diagrams, remove explanations of what the targets are (state them once in a table), and focus on concrete commands and decision trees.

Split benchmark implementations into separate referenced files and keep SKILL.md as a concise overview with navigation links to detailed benchmark guides.

DimensionReasoningScore

Conciseness

Extremely verbose at 300+ lines. The ASCII box diagrams are decorative and redundant with the text. The TypeScript benchmark classes are lengthy pseudocode that Claude cannot execute — they describe hypothetical APIs (this.sona.adapt, this.flashAttention, etc.) that don't exist. The coordination section and mission statement add fluff without actionable content.

1 / 3

Actionability

Despite containing extensive TypeScript code, none of it is executable — all methods reference undefined APIs (this.agentDBMemory.hnswSearch, this.standardAttention, this.flashAttention, etc.). There are no real commands, no actual benchmark scripts to run, no concrete steps to optimize anything. The code is aspirational pseudocode dressed up as TypeScript classes.

1 / 3

Workflow Clarity

There is no clear workflow or sequence of steps to follow. The skill presents benchmark classes and checklists but never explains how to actually perform optimization — no 'step 1, step 2' process, no validation checkpoints, no error recovery. The checklist at the end is a wish list, not a workflow.

1 / 3

Progressive Disclosure

Monolithic wall of text with no references to external files and no bundle files provided. All content is inline with no structure for progressive discovery. The content would benefit enormously from splitting benchmark code into separate files and keeping the SKILL.md as a concise overview.

1 / 3

Total

4

/

12

Passed

Description

0%Scale 1-3

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 weak description that provides virtually no useful information for skill selection. It only contains an invocation command and a generic label ('v3-performance-engineer') without describing any capabilities, actions, or trigger conditions. This would be nearly impossible for Claude to correctly select 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 times, and analyzes resource utilization.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about performance optimization, profiling, benchmarking, latency reduction, or load testing.'

Remove the invocation command from the description (it's operational metadata, not descriptive content) and replace with domain-specific details that distinguish this skill from other engineering-related skills.

DimensionReasoningScore

Specificity

The description contains no concrete actions whatsoever. It only states it's an 'agent skill' with an invocation command, providing no 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 explanation of purpose or trigger conditions.

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', or any domain-specific triggers are present.

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 the lack of specificity makes it impossible to differentiate from other skills.

1 / 3

Total

4

/

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
ruvnet/claude-flow
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.