CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-performance-optimizer

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

61

19.39x
Quality

Does it follow best practices?

Impact

97%

19.39x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

35%

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, heavily padded catalog of generic performance-optimization bullet lists interleaved with partially-executable code examples that contain undefined helpers and missing imports. Workflows are listed but lack validation checkpoints, and everything is crammed into a single monolithic file with no reference splitting. The strongest dimension is actionability (concrete tool calls exist) and the weakest is conciseness.

Suggestions

Cut the generic capability/KPI bullet sections (Performance Metrics, Optimization Strategies, Integration Patterns) that restate knowledge Claude already has, keeping only non-obvious guidance to improve conciseness.

Make code examples fully executable — define or stub the helper functions and add missing imports (e.g., `import os`) — or explicitly justify the placeholder portions.

Add explicit validation/verification checkpoints to the example workflows (e.g., "Verify optimization improved the metric before applying") and move detailed reference material into separate files referenced one level deep.

DimensionReasoningScore

Conciseness

The ~370-line body is verbose and padded with generic bullet sections that restate concepts Claude already knows (e.g., "Throughput: Measure system throughput and processing capacity", "Latency: Monitor response times", "Caching Strategies: Implement optimal caching strategies"), plus long placeholder-filled code blocks, matching the score-1 anchor.

1 / 3

Actionability

It provides structured code calling MCP tools with specific parameters (method, epsilon, maxIterations), but the examples are not fully executable: they reference undefined helpers (this.buildAllocationMatrix, createLoadBalancingMatrix), rely on uncertain MCP tools, and the Python block uses os.environ without importing os, matching the score-2 "incomplete/missing key details" anchor.

2 / 3

Workflow Clarity

The "Example Workflows" section lists numbered sequences (Baseline Assessment → ... → Monitoring), but the steps are abstract with no commands and no validation/verification checkpoints or feedback loops; per the guidelines, missing validation for optimization/deployment-style operations caps workflow clarity at 2.

2 / 3

Progressive Disclosure

The file is well-sectioned but monolithic: all capability catalogs, code examples, and reference-style material live inline in one ~370-line file with no bundle files and no one-level-deep references, matching the score-2 anchor where content that should be separate is inline.

2 / 3

Total

7

/

12

Passed

Description

50%

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 description is competent and third-person, covering what the agent does with several named capabilities, but it stays at an abstract/buzzword level and omits any explicit "Use when" trigger guidance, capping completeness and trigger quality. The SKILL.md is also malformed: it contains two conflicting YAML frontmatter blocks (the first a boilerplate stub "Agent skill for performance-optimizer - invoke with $agent-performance-optimizer").

Suggestions

Add an explicit "Use when ..." clause naming natural trigger phrases (e.g., "Use when the user asks to speed up a system, find or fix bottlenecks, balance load, or optimize CPU/memory/resource allocation") to raise completeness and trigger_term_quality.

Replace abstract fluff ("efficiency maximization", "sublinear algorithms") with concrete, user-facing actions to move specificity from abstract verbs to granular capabilities.

Fix the duplicate/malformed YAML frontmatter — keep a single frontmatter block with one `name` and one `description`, removing the boilerplate stub block.

DimensionReasoningScore

Specificity

It names the domain and several actions ("identifies bottlenecks", "optimizes resource allocation", "computational performance analysis", "system optimization", "resource management", "efficiency maximization"), but these are high-level/abstract verbs rather than concrete granular actions like the score-3 anchor, and several read as buzzword fluff ("efficiency maximization", "sublinear algorithms").

2 / 3

Completeness

It answers "what does this do" clearly, but it never explicitly states "when" Claude should use it; per the judging guidelines a missing "Use when..." or equivalent explicit trigger caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some natural keywords a user might say ("performance optimization", "bottlenecks", "resource allocation", "distributed systems"), but coverage of common variations is thin and there is no explicit "Use when..." trigger phrase to surface them.

2 / 3

Distinctiveness Conflict Risk

"System performance optimization ... across distributed systems and cloud infrastructure" narrows the niche somewhat, but the framing is still broad enough to overlap with general devops, SRE, or resource-management skills, matching the score-2 anchor.

2 / 3

Total

8

/

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.

Validation16 / 16 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.