Name: agent-performance-optimizer
Rating: 53.8 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-performance-optimizer

Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

19.39x

Quality

30%

Does it follow best practices?

Impact

97%

19.39x

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-performance-optimizer/SKILL.md

The canonical home for this skill is agent-performance-optimizer in ruvnet/claude-flow

Quality

Content

41%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 body is a long, repetitive capability catalog padded with abstract bullet lists and stub code that is not actually executable (undefined helper methods and print-only optimizer functions). It lacks any validation/feedback checkpoints in its workflows and has no bundle-file structure, so it fails to act as a lean overview pointing to deeper materials.

Suggestions

Collapse the four overlapping capability/metrics/strategy bullet sections into one concise list and remove filler sentences like "serves as the central hub for all performance optimization activities".

Make code examples executable: either implement the referenced helper methods (buildAllocationMatrix, identifyBottlenecks, etc.) inline or replace stubs with concrete, runnable logic so examples are copy-paste ready.

Add explicit validation checkpoints to the Example Workflows (e.g., a verify/baseline-compare step after implementation) and split the large embedded MCP/Flow-Nexus code into separate reference files linked one level deep.

Dimension	Reasoning	Score
Conciseness	The ~370-line body is noticeably verbose, repeating nearly identical capability bullet lists under "Core Capabilities", "Advanced Optimization Techniques", "Performance Metrics and KPIs", and "Optimization Strategies", and padding sections with abstract phrases like "serves as the central hub for all performance optimization activities"; it does not explain basic concepts Claude knows (so not score 1), but the repetition and list padding clearly overruns the token budget.	2 / 5
Actionability	It provides several concrete-looking code blocks invoking mcp__sublinear-time-solver__solve etc., but the classes call undefined helper methods (this.buildAllocationMatrix, this.identifyBottlenecks, createLoadBalancingMatrix) and the optimizer functions are stubs printing "Optimizing CPU usage...", so it is pseudocode masquerading as executable code — matching the score-3 anchor of some concrete guidance but incomplete / not truly executable.	3 / 5
Workflow Clarity	Numbered workflows appear under "Example Workflows" (Baseline → Bottleneck → Plan → Implement → Monitor), giving a rough sequence, but there are no validation checkpoints, no error-recovery feedback loops, and no verify step for what are batch/system-modifying operations; per the rubric this caps at 3, and the steps are high-level hints rather than runnable commands so it does not reach 4.	3 / 5
Progressive Disclosure	There is no SKILL.md-as-overview structure and no referenced bundle files exist (references/ scripts/ assets/ are all absent), yet ~370 lines of capability catalogs, MCP usage, and large embedded code blocks are inlined in one file — content that clearly belongs in separate reference files is inlined with minimal navigation, matching the score-2 anchor.	2 / 5
	Total	10 / 20 Passed

Description

18%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 real frontmatter description is a non-semantic placeholder ("Agent skill for performance-optimizer - invoke with $agent-performance-optimizer") that does not explain what the skill does or when to use it. Note: the SKILL.md body opens with a second, richer descriptive block, but that is not the frontmatter description field and is not what users see for skill routing.

Suggestions

Replace the placeholder frontmatter description with a concrete, third-person statement of actions (e.g., "Identifies performance bottlenecks and optimizes CPU, memory, and network resource allocation across distributed systems.").

Add an explicit "Use when..." trigger clause naming natural user phrases such as "optimize performance", "reduce latency", "find bottlenecks", or "right-size resources".

Include natural synonyms and concrete file/tool terms users would actually say, rather than the artificial "$agent-performance-optimizer" invocation token.

Dimension	Reasoning	Score
Specificity	The frontmatter description is the placeholder string "Agent skill for performance-optimizer - invoke with $agent-performance-optimizer" — it names the skill/domain but lists zero concrete actions, mirroring the score-2 anchor "Names the domain but actions are minimal or generic" rather than score 3 which requires actual named actions.	2 / 5
Completeness	It gives only a vague pointer to invocation (a weak, non-semantic "what") and entirely lacks a "when to use" trigger clause; the rubric's guideline caps completeness at 3 when "Use when..." is missing, and here even the "what" is too thin, so it sits at 2 between the missing-both and clear-what-only anchors.	2 / 5
Trigger Term Quality	It contains no natural user keywords at all, only the artificial invocation token "$agent-performance-optimizer" and the generic word "skill"; there is nothing a user would naturally say, matching the score-1 anchor of only technical jargon / generic language.	1 / 5
Distinctiveness Conflict Risk	The placeholder phrasing "Agent skill for performance-optimizer" is extremely broad and reads as a generic agent wrapper rather than a distinct niche, giving high overlap risk with other agent skills; not entirely generic (score 1) since it does name performance optimization, so it lands at 2.	2 / 5
	Total	7 / 20 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: ruvnet/ruflo
Path: .agents/skills/agent-performance-optimizer/SKILL.md
Commit: fa13ee4

Reviewed: about 4 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.