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 essentially a label with an invocation command, providing no useful information about what the skill does, what actions it performs, or when it should be selected. It fails on every dimension of the rubric, offering neither concrete capabilities nor trigger guidance for skill selection.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Monitors CPU usage, memory consumption, disk I/O, and network throughput for running processes and system resources.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about system performance, CPU load, memory usage, slow processes, or resource bottlenecks.'
Remove the invocation instruction ('invoke with $agent-performance-monitor') from the description, as it wastes space that should be used for capability and trigger information.
| 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 tool name rather than a natural term a user would say. There are no natural language trigger terms like 'CPU usage', 'memory', 'latency', 'metrics', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Performance-monitor' is vague enough to overlap with many monitoring-related skills. Without specific capabilities or triggers, it's impossible to distinguish this from other performance or monitoring tools. | 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-functional architectural sketch masquerading as an agent skill. It consists almost entirely of illustrative JavaScript class definitions that cannot be executed, reference numerous undefined dependencies, and provide no concrete workflow for Claude to follow. The content would need to be fundamentally restructured around actual executable commands, real tool integrations, and clear step-by-step workflows.
Suggestions
Replace illustrative class definitions with actual executable commands or tool invocations that Claude can run — e.g., real CLI commands, actual MCP tool calls with documented parameters, or working code snippets.
Add a clear workflow section with numbered steps: what to monitor first, how to interpret results, when to escalate, and how to validate that monitoring is working correctly.
Reduce content by 80%+ — remove all pseudocode classes and focus on a concise quick-start section with the 3-5 most important monitoring commands and their expected outputs.
Split detailed reference material (anomaly detection algorithms, dashboard integration, analytics formulas) into separate referenced files if they are truly needed, keeping SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. The code is largely pseudocode/illustrative class definitions that Claude cannot execute. It explains general concepts like statistical anomaly detection (3-sigma rule), percentile calculations, and WebSocket patterns that Claude already knows. Almost every section could be reduced by 80%. | 1 / 3 |
Actionability | Despite the volume of code, none of it is executable — classes reference undefined dependencies (CircularBuffer, CPUBottleneckDetector, MLAnomalyDetector, etc.), undefined MCP methods, and non-existent modules. The bash commands at the end reference 'npx claude-flow' subcommands without verifying they exist. This is architectural pseudocode dressed as implementation, not actionable guidance. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps for performing performance monitoring. The content is organized as a catalog of class definitions without any guidance on when to use what, in what order, or how to validate results. No validation checkpoints or error recovery steps are provided. | 1 / 3 |
Progressive Disclosure | The entire content is a monolithic wall of code blocks with no references to external files, no layered structure, and no separation of overview from detail. Everything is dumped inline with no navigation aids. There are no bundle files to support progressive disclosure either. | 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
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.