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 essentially an invocation instruction with no substantive content. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, provides no 'when to use' guidance, and is too generic to be distinguished from other potential performance-related skills. It would be nearly useless for skill selection among a set of available skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Profiles application code, identifies bottlenecks, optimizes database queries, reduces memory usage, and improves response times.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions slow performance, latency issues, load times, memory leaks, CPU usage, or asks to speed up or optimize code.'
Clarify the scope/domain to reduce conflict risk, e.g., specify whether this is for backend, frontend, database, or general application performance optimization.
| 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 explanation of functionality—only an invocation instruction. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'performance-optimizer,' which is a tool name rather than a natural keyword a user would say. No natural trigger terms like 'slow,' 'latency,' 'speed up,' 'optimize,' 'bottleneck,' or 'profiling' are included. | 1 / 3 |
Distinctiveness Conflict Risk | 'Performance-optimizer' is extremely generic and could overlap with database optimization, frontend performance, network optimization, code profiling, or any number of other performance-related skills. There is nothing to distinguish its 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 file is an extremely verbose, largely non-actionable document that reads more like a marketing overview or textbook outline than a practical skill. It explains concepts Claude already knows, provides non-executable pseudocode with undefined helper functions, and lacks any concrete validation steps or feedback loops. The content would need to be reduced by 80%+ and replaced with actual executable examples and specific instructions.
Suggestions
Remove all bullet-point lists that merely name concepts Claude already knows (e.g., 'Throughput: Measure system throughput') and replace with only project-specific or non-obvious guidance.
Make code examples executable by defining all referenced helper functions or replacing pseudocode with real, runnable implementations that demonstrate actual MCP tool usage.
Add explicit validation checkpoints and error recovery steps to workflows, e.g., 'Run benchmark X, verify metric Y is below threshold Z, if not then adjust parameter W.'
Split the monolithic content into a concise SKILL.md overview (under 80 lines) with references to separate files for detailed examples, integration patterns, and metrics definitions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive bullet-point lists that describe concepts Claude already knows (what throughput is, what latency is, what caching is). The document is padded with generic descriptions of optimization concepts, metrics, and strategies that add no actionable value. Much of the content reads like a textbook table of contents rather than a skill file. | 1 / 3 |
Actionability | Despite containing code blocks, the code is pseudocode-level with placeholder methods like `optimize_cpu_usage` that just print strings. Functions like `buildAllocationMatrix`, `extractLoadDistribution`, and `calculateBalanceScore` are called but never defined. The code is not executable or copy-paste ready—it's illustrative scaffolding with no real implementation. | 1 / 3 |
Workflow Clarity | The 'Example Workflows' section lists high-level steps like 'Assess current infrastructure performance' and 'Identify performance bottlenecks' without any concrete commands, validation checkpoints, or error recovery steps. Multi-step processes are vague descriptions rather than actionable sequences. No feedback loops or validation steps are present despite dealing with system-level operations. | 1 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text exceeding 300 lines with no references to external files. Content that could be split into separate reference documents (metrics definitions, integration patterns, advanced techniques) is all inlined. There is no clear hierarchy or navigation structure—just an endless sequence of sections at the same level of detail. | 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
f547cec
- 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.