agent-performance-monitor
Agent skill for performance-monitor - invoke with $agent-performance-monitor
35
0%
Does it follow best practices?
Impact
100%
2.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-performance-monitor/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 functions as little more than an invocation label, providing no information about what the skill does, what actions it performs, or when it should be selected. It would be nearly impossible for Claude to correctly choose this skill from a pool of available skills.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Monitors CPU usage, memory consumption, disk I/O, and network throughput for running processes and services.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about system performance, resource usage, slow processes, CPU load, memory leaks, or monitoring metrics.'
Remove the invocation instruction ('invoke with $agent-performance-monitor') from the description field, as this is operational metadata rather than descriptive content useful for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for performance-monitor' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an agent skill and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'performance-monitor', which is a technical/internal label rather than a natural term a user would say. No natural language trigger terms like 'CPU usage', 'memory', 'latency', 'metrics', etc. are included. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'performance-monitor' is too generic and could overlap with many types of monitoring (application, system, network, database). There are no distinguishing details to differentiate it from other potential monitoring or performance-related skills. | 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 an extensive but non-actionable collection of illustrative JavaScript pseudocode and fictional API calls. It reads more like a design document or architecture proposal than an executable skill. The code cannot be run, there are no real workflows or validation steps, and the massive length wastes token budget on concepts Claude already understands (statistical anomaly detection, percentile calculations, etc.).
Suggestions
Replace illustrative pseudocode with actual executable commands or real code snippets that Claude can use—focus on the CLI commands in the 'Operational Commands' section and make those the core of the skill.
Add a clear step-by-step workflow: e.g., 1) Start monitoring, 2) Check specific metrics, 3) Analyze bottlenecks, 4) Validate findings, 5) Take action—with explicit validation checkpoints.
Reduce content by 80%+ by removing class definitions that serve as architecture illustrations rather than actionable instructions; assume Claude understands concepts like percentiles, anomaly detection, and resource tracking.
Split detailed reference material (KPI definitions, anomaly detection models, dashboard schemas) into separate referenced files, keeping SKILL.md as a concise overview with navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Most code is non-executable pseudocode with placeholder methods (e.g., `this.getCPUUsage()`, `this.loadTimeSeriesModel()`) that explain concepts Claude already understands. Classes like StatisticalAnomalyDetector, MLAnomalyDetector are referenced but never defined. The entire file could be reduced to the operational commands section plus a brief architecture overview. | 1 / 3 |
Actionability | Almost none of the code is executable—it's all illustrative pseudocode with undefined methods, unimported dependencies, and fictional MCP calls (e.g., `mcp.agent_list`, `mcp.bottleneck_analyze`). The bash commands at the end reference `npx claude-flow` subcommands that may or may not exist, with no verification steps. Nothing is copy-paste ready. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps for performing performance monitoring. The content is organized as a collection of class definitions and code snippets with no ordering, no validation checkpoints, and no guidance on when or how to use each component. A user/agent would not know where to start or what sequence to follow. | 1 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of code blocks with no references to external files and no layered structure. Hundreds of lines of illustrative code are inlined that could be separated into reference documents. There's no quick-start section that gets to the point before diving into details. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (677 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
0d9f9b1
- 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.