memory-leak-debugging
Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to analyze heapsnapshots or run memory leak detection tools like memlab.
77
78%
Does it follow best practices?
Impact
56%
0.85xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/memory-leak-debugging/SKILL.mdQuality
Discovery
100%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 an excellent skill description that clearly defines its scope (JavaScript/Node.js memory leak diagnosis and resolution), provides explicit trigger conditions covering both user-reported symptoms and specific tools, and uses natural language terms users would actually use. It follows third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'diagnoses and resolves memory leaks', 'analyze heapsnapshots', 'run memory leak detection tools like memlab'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Diagnoses and resolves memory leaks in JavaScript/Node.js applications') and when ('Use when a user reports high memory usage, OOM errors, or wants to analyze heapsnapshots or run memory leak detection tools like memlab'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'memory leaks', 'high memory usage', 'OOM errors', 'heapsnapshots', 'memlab', 'JavaScript', 'Node.js'. Good coverage of both symptoms and tools. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: memory leaks specifically in JavaScript/Node.js, with specific tools (memlab, heapsnapshots). Unlikely to conflict with general debugging or other language-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured skill that effectively uses progressive disclosure to keep the main file as an overview. Its main weaknesses are the lack of inline executable examples for the primary memlab workflow (relying entirely on a reference file) and the absence of validation/feedback loops in the workflows. Tightening the prose and adding a concrete memlab command example inline would significantly improve it.
Suggestions
Add at least one inline executable memlab command (e.g., `memlab find-leaks --baseline baseline.heapsnapshot --target target.heapsnapshot --final final.heapsnapshot`) so the primary workflow is actionable without reading the reference file.
Add explicit validation checkpoints: verify snapshot file sizes after capture, check memlab output for expected leak traces, and verify the fix by re-running the snapshot/analysis cycle.
Trim the opening sentence ('This skill provides expert guidance...') and other filler phrases to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation (e.g., 'This skill provides expert guidance and workflows for finding, diagnosing, and fixing memory leaks' is filler; the 'Note: Detached DOM nodes are sometimes intentional caches' aside adds marginal value). The core principles section has some padding but overall is reasonably tight. | 2 / 3 |
Actionability | Provides a concrete fallback command and clear workflow steps, but the primary workflow (memlab) delegates entirely to a reference file without showing any executable commands inline. The snapshot capture workflow describes actions conceptually rather than giving specific tool invocations or code. The mix of concrete (fallback script) and abstract (memlab, snapshot capture) lands at a 2. | 2 / 3 |
Workflow Clarity | The four workflows are clearly sequenced and logically ordered (capture → analyze → identify → fallback). However, there are no explicit validation checkpoints or feedback loops—e.g., no step to verify snapshots were captured correctly, no guidance on what to do if memlab finds no leaks, and no verification after applying a fix. For a destructive/diagnostic workflow this caps at 2. | 2 / 3 |
Progressive Disclosure | The skill is a well-structured overview that appropriately delegates detailed content to one-level-deep references (references/memlab.md, references/common-leaks.md, references/compare_snapshots.js). References are clearly signaled and the main file stays concise. Navigation is straightforward. | 3 / 3 |
Total | 9 / 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
- ChromeDevTools/chrome-devtools-mcp
- Commit
faac61d
- 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.