agent-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
35
0%
Does it follow best practices?
Impact
97%
19.39xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-performance-optimizer/SKILL.mdQuality
Discovery
0%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 description is critically deficient across all dimensions. It provides only an agent invocation command with no explanation of what the skill does, when to use it, or what domain it applies to. It is essentially a label with no actionable information for skill selection.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Profiles application code, identifies bottlenecks, optimizes database queries, and reduces memory usage.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions slow performance, latency issues, profiling, speed optimization, or bottleneck analysis.'
Specify the domain or technology scope (e.g., web apps, Python code, SQL queries) to make the skill clearly distinguishable from other optimization-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Performance-optimizer' is a vague label with no explanation of what it actually does—no specific capabilities like profiling, caching, reducing load times, etc. are mentioned. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no 'Use when...' clause and no meaningful explanation of functionality—only an invocation instruction. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'performance-optimizer,' which is a generic compound noun rather than natural language a user would use. No natural keywords like 'slow,' 'latency,' 'speed up,' 'profiling,' 'bottleneck,' etc. are present. | 1 / 3 |
Distinctiveness Conflict Risk | 'Performance-optimizer' is extremely generic and could overlap with any skill related to code optimization, database tuning, network performance, frontend rendering, etc. There is nothing to distinguish its specific niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%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, generic description of performance optimization concepts that reads more like a marketing document or course syllabus than actionable instructions. The code examples are non-functional skeletons with undefined helper methods, the workflows are abstract checklists without concrete steps, and the extensive bullet-point lists explain concepts Claude already knows. The skill fails on all dimensions by being simultaneously too long and too shallow.
Suggestions
Remove all generic concept explanations (what throughput is, what caching is, etc.) and focus exclusively on how to use the specific MCP tools listed — provide complete, executable examples with real input/output schemas for each tool.
Replace skeleton code with minimal, complete working examples showing actual MCP tool invocations with realistic parameters and expected response structures.
Add concrete validation steps to workflows — e.g., 'After running solve(), verify solution.residual < epsilon before proceeding' — instead of generic steps like 'Monitor optimization results'.
Cut the document by at least 70% by removing sections like 'Performance Metrics and KPIs', 'Integration Patterns', and 'Advanced Optimization Techniques' which are entirely generic bullet lists with no actionable content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Extensively explains concepts Claude already knows (what bottleneck identification is, what CPU/memory/network utilization means, what throughput and latency are). Massive bullet-point lists of generic concepts like 'Code Optimization: Optimize application code for performance' add zero value. The content could be reduced by 70%+ without losing actionable information. | 1 / 3 |
Actionability | Despite containing code blocks, the code is pseudocode/skeleton code with placeholder methods like `optimize_cpu_usage` that just print strings. Functions like `buildAllocationMatrix`, `extractAllocation`, `calculateEfficiency` are called but never defined. Nothing is copy-paste executable. The code creates an illusion of concreteness while being fundamentally abstract. | 1 / 3 |
Workflow Clarity | The 'Example Workflows' section lists generic high-level steps like '1. Baseline Assessment 2. Bottleneck Identification 3. Optimization Planning' with no concrete commands, validation checkpoints, or error recovery steps. Multi-step processes are described at a level so abstract they provide no operational guidance. No feedback loops or validation steps exist anywhere. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files. All content is inline regardless of depth or relevance. Sections like 'Performance Metrics and KPIs' with 15+ generic bullet points could be separate references. The document has many sections but poor information architecture — everything is at the same level of detail (which is uniformly shallow). | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
d29d87f
- 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.