detecting-memory-leaks
Detect potential memory leaks and analyze memory usage patterns in code. Use when troubleshooting performance issues related to memory growth or identifying leak sources. Trigger with phrases like "detect memory leaks", "analyze memory usage", or "find memory issues".
54
44%
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/memory-leak-detector/skills/detecting-memory-leaks/SKILL.mdQuality
Discovery
89%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 well-structured skill description that clearly communicates its purpose and provides explicit trigger guidance. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., what kind of analysis, what outputs). Overall it is a strong description that would perform well in skill selection.
Suggestions
Add more specific concrete actions beyond 'detect' and 'analyze', such as 'identify unclosed resources, track object retention paths, flag circular references, and suggest fixes for common leak patterns'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (memory leaks, memory usage) and some actions (detect, analyze), but doesn't list multiple concrete specific actions beyond detecting and analyzing. It lacks detail on what specific techniques or outputs are provided (e.g., heap analysis, reference counting, object lifecycle tracking). | 2 / 3 |
Completeness | Clearly answers both 'what' (detect potential memory leaks and analyze memory usage patterns in code) and 'when' (troubleshooting performance issues related to memory growth, identifying leak sources) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'detect memory leaks', 'analyze memory usage', 'find memory issues', 'performance issues', 'memory growth', 'leak sources'. These are phrases users would naturally say when encountering memory-related problems. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to memory leak detection and memory usage analysis, which is a distinct niche. The specific trigger terms around memory leaks and memory growth make it unlikely to conflict with general code analysis or other performance-related skills. | 3 / 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 descriptive rather than instructive. It explains what memory leak detection is and when to use it, but never provides concrete patterns to search for, specific commands to run, executable code examples, or actual detection logic. The content reads like a product description rather than an actionable skill for Claude.
Suggestions
Replace the abstract 'Instructions' list with concrete, language-specific code patterns to detect (e.g., regex patterns for unremoved event listeners in Node.js, common closure leak patterns in Python, specific heap analysis commands for JVM).
Add executable code examples showing actual memory leak detection - e.g., a Python script using tracemalloc, Node.js heap snapshot analysis commands, or JVM jmap/jstat usage with specific flags and output interpretation.
Remove the 'Overview', 'How It Works', 'When to Use This Skill', 'Integration', and 'Best Practices' sections entirely - they explain concepts Claude already knows and consume tokens without adding actionable value.
Add a concrete workflow with validation steps: e.g., '1. Run `node --inspect app.js`, 2. Take heap snapshot with `heapdump.writeSnapshot()`, 3. Compare snapshots to identify growing objects, 4. Cross-reference with code patterns below'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with sections that explain things Claude already knows ('How It Works', 'When to Use This Skill', 'Overview', 'Integration', 'Best Practices'). The 'Examples' section describes what the skill will do rather than showing how to do it. Multiple sections restate the same information. Most of this content is padding that doesn't add actionable value. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples anywhere. The 'Instructions' section is a vague checklist ('Analyze code for common memory leak patterns') without specifying what patterns to look for, what tools to run, or what code to write. The examples describe outcomes rather than providing actual detection logic or commands. | 1 / 3 |
Workflow Clarity | The 'Instructions' section lists 6 steps but they are abstract directives with no specifics on how to execute them, no validation checkpoints, and no feedback loops. There's no concrete sequence showing how to actually run profiling tools, interpret output, or verify fixes. For a skill involving diagnostic analysis, this lacks any meaningful workflow structure. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files to support it. The 'Resources' section lists generic categories ('Memory profiling tool documentation') without actual links or file references. Content is poorly organized with redundant sections that could be consolidated or eliminated. | 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.