tracking-resource-usage
Track and optimize resource usage across application stack including CPU, memory, disk, and network I/O. Use when identifying bottlenecks or optimizing costs. Trigger with phrases like "track resource usage", "monitor CPU and memory", or "optimize resource allocation".
55
46%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/performance/resource-usage-tracker/skills/tracking-resource-usage/SKILL.mdQuality
Discovery
92%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 is a strong skill description that clearly communicates what the skill does and when to use it, with explicit trigger phrases. The specificity of resource types (CPU, memory, disk, network I/O) and use cases (bottlenecks, cost optimization) is good. The only minor weakness is potential overlap with adjacent performance or cost optimization skills, though the resource-monitoring focus helps differentiate it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions ('track and optimize resource usage') across specific resource types ('CPU, memory, disk, and network I/O') and mentions specific use cases like 'identifying bottlenecks' and 'optimizing costs'. | 3 / 3 |
Completeness | Clearly answers both 'what' (track and optimize resource usage across CPU, memory, disk, network I/O) and 'when' (identifying bottlenecks, optimizing costs) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'track resource usage', 'monitor CPU and memory', 'optimize resource allocation'. Also includes natural keywords like 'bottlenecks', 'costs', 'CPU', 'memory', 'disk', 'network I/O'. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies resource monitoring and optimization, it could overlap with more general performance monitoring or cost optimization skills. The 'application stack' framing is somewhat broad and could conflict with infrastructure-specific or cloud-specific monitoring skills. | 2 / 3 |
Total | 11 / 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 almost entirely abstract description with no concrete, executable guidance. It explains what resource tracking is and when to use it—things Claude already knows—while failing to provide any actual commands, code snippets, or specific tool configurations. The content is heavily padded with redundant sections and would need a complete rewrite focused on actionable instructions.
Suggestions
Replace abstract descriptions with concrete, executable commands (e.g., actual `vmstat`, `iostat`, `top` command invocations with specific flags and output parsing examples)
Remove redundant sections (Overview, How It Works, When to Use) and consolidate into a lean quick-start with copy-paste ready code/commands
Add validation checkpoints to the workflow, such as verifying tool availability, checking output format, and comparing against baselines with specific threshold values
Either create bundle files for detailed reference material (metrics schemas, baseline templates, alert configurations) or remove references to non-existent paths like '${CLAUDE_SKILL_DIR}/metrics/resources/'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows. Sections like 'Overview', 'How It Works', 'When to Use This Skill', and 'Integration' are largely redundant filler. The 'How It Works' section describes a generic workflow at a high level that adds no actionable value. The entire file could be reduced to roughly 20% of its current size. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific tool invocations. Everything is described abstractly ('Activate the resource-usage-tracker plugin', 'Collect real-time metrics using system tools'). The examples describe what the skill 'will do' rather than showing how. References to tools like top, vmstat, iostat are mentioned but never shown with actual usage patterns or commands. | 1 / 3 |
Workflow Clarity | The 'Instructions' section lists 6 vague steps with no validation checkpoints, no concrete commands, and no feedback loops. Steps like 'Analyze data for bottlenecks and patterns' and 'Generate optimization recommendations' are abstract descriptions, not actionable workflow steps. No verification or error recovery is built into the workflow itself. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to reference. Content is poorly organized with redundant sections (Overview, How It Works, When to Use, Examples all overlap significantly). References to '${CLAUDE_SKILL_DIR}/metrics/resources/' and 'resource-usage-tracker plugin' exist but no supporting files are provided. The 'Resources' section lists vague topic areas with no actual links. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.