stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck <PID> to focus on a specific process.

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 highly actionable with executable commands and a well-sequenced, validated diagnostic workflow, though it is somewhat verbose and monolithic with no external reference split. Strong on actionability and workflow clarity, room to tighten prose and factor out detail.

Suggestions

Trim explanatory prose around commands to the essential non-obvious gotchas; the flag-by-flag commentary inflates the token budget.

Consider moving the long platform-specific command reference (lsof/ss/stack-dump variants and RUNTIME_DIR resolution) into a references/ file linked from SKILL.md to improve progressive disclosure.

Collapse repeated credential-redaction notes into a single stated rule rather than restating it across the fast path, step 2, and step 3.

Dimension	Reasoning	Score
Conciseness	Most tokens earn their place (BSD grep \b quirks, ps rss-in-KB units, ptrace scope), but the body is lengthy and several prose passages could be tightened without losing clarity, fitting the mostly-efficient anchor.	2 / 3
Actionability	It provides concrete, copy-paste-ready shell commands (ps, pgrep, lsof, ss, node sidecar scan) with exact flags and thresholds, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The investigation is clearly sequenced (resolve RUNTIME_DIR → fast path → enumerate sidecars → ps enrichment → deep-dive → report) with explicit validation guards (kill -0, command grep) and fallback paths.	3 / 3
Progressive Disclosure	It is well-organized into labeled sections, but everything is inline in a single ~115-line file with no bundle files; some of the detailed command/flag reference could be split out for cleaner discovery.	2 / 3
	Total	10 / 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 specific, uses natural trigger terms, answers both what and when with an explicit "Use /stuck" clause, and occupies a clear non-conflicting niche. It is concise with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	"Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs" lists multiple concrete diagnostic actions rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	It states what it does (diagnose frozen/stuck/slow Qwen Code sessions via process/CPU/memory/log scans) and when to use it ("Use /stuck or /stuck <PID>"), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	"frozen, stuck, or slow" are exactly the natural terms a user would say, and "Use /stuck or /stuck <PID>" surfaces the invocation keywords, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to diagnosing frozen Qwen Code sessions on the local machine, with 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: QwenLM/qwen-code
Path: packages/core/src/skills/bundled/stuck/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.