memory-leak-debug

Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is tight, executable, and clearly sequenced with validation and verification steps. The main gap is a dangling reference to an examples file that is not present in the bundle.

Suggestions

Either add the examples/ directory with react-reconciler-performance-measure-leak.md or remove/soften the broken reference in the Worked Example section.

Consider marking the Node.js 22+ and chrome-devtools version requirements as prerequisites-only to avoid any time-sensitivity read on conciseness.

The external tmux-real-user-testing skill reference is fine, but a one-line note on what it provides would reduce the navigation hop for readers without it.

Dimension	Reasoning	Score
Conciseness	Lean and command-driven with no padding or explanation of concepts Claude already knows; prose notes are minimal and tied to actionable gotchas.	3 / 3
Actionability	Provides fully executable commands (helper eval, kill -USR2, chrome-devtools subcommands) with explicit placeholders, and the referenced find-leaf-node.sh script exists and is runnable.	3 / 3
Workflow Clarity	A clear 6-step sequence with a multi-snapshot comparison feedback loop and an explicit Step 6 'Verify Fix' checkpoint confirming stabilization.	3 / 3
Progressive Disclosure	Well-organized sections and a real bundle script, but the worked-example reference points to examples/react-reconciler-performance-measure-leak.md which does not exist in the bundle.	2 / 3
	Total	11 / 12 Passed

Description

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.

The description is concise, specific, and complete with both a clear capability statement and an explicit 'Use when' trigger. It is highly distinct and unlikely to be selected for unrelated tasks.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Diagnose memory leaks', 'using heap snapshots and the chrome-devtools CLI' — rather than vague language.	3 / 3
Completeness	Explicitly states what it does and when to use it via the 'Use when investigating...' clause, answering both what and when.	3 / 3
Trigger Term Quality	Covers natural user phrasings like 'high memory usage', 'unbounded growth', and 'object retention' alongside 'memory leaks'.	3 / 3
Distinctiveness Conflict Risk	Scoped to memory-leak debugging of the Qwen Code CLI with specific tooling and distinct triggers, unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: QwenLM/qwen-code
Path: .qwen/skills/memory-leak-debug/SKILL.md
Commit: 8878264

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.