tmux-real-user-testing

This skill should be used when the user asks to "用 tmux 做真实测试", "保存 tmux 日志", "像真实用户一样测试 Qwen", "生成可复查的 TUI 测试报告", "测试 slash command 交互", or requests a tmux-based real user E2E run with complete readable logs. It guides real TUI usage with step-by-step capture-pane snapshots rather than ANSI raw pipe logs.

Quality

88%

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

81%Weight 40%Scale 1-5

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

The skill body is highly actionable with executable commands, a clean sequenced workflow, and explicit validation via polling. Its main weakness is mild verbosity from the pedagogical scenario-design section and overlap between the manual and helper-script workflows.

Suggestions

Trim the 'Designing a test scenario' section to the essential checklist rather than explaining entry point / branch point / waiting state concepts Claude already understands.

Reduce duplication between the 'Manual workflow' and 'Recommended helper script' sections, e.g. present the helper as primary and keep only the one-off snippets the script cannot express inline.

Move the macOS 'open <file>' and other environment-specific notes out of 'Common pitfalls' into a single short callout to tighten the tail of the document.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural bash, but 'Designing a test scenario' explains fairly basic concepts (entry point, branch points, waiting states) and the manual workflow partially duplicates the helper-script path, so it could be tightened; not a 4 because padding is more than minor.	3 / 5
Actionability	Fully executable, copy-paste-ready bash throughout (start, snapshot, send, poll, finish), backed by a complete referenced helper script whose usage is shown; common cases are covered with concrete examples.	5 / 5
Workflow Clarity	A clearly sequenced five-step manual workflow with explicit validation checkpoints (poll for startup string, poll for completion text, dump pane on timeout) and an error-recovery feedback path; the helper script mirrors the same structure.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a real one-level-deep bundle reference (scripts/tmux-real-user-log.sh, verified present) that is clearly signaled; not a 5 because the manual workflow duplicates much of what the helper script already encapsulates, leaving some inline content that could be slimmer.	4 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities, lists multiple natural trigger phrases, and explicitly covers both what and when. It is specific enough to be unlikely to fire for the wrong skill.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('step-by-step capture-pane snapshots', 'real TUI usage', 'tmux-based real user E2E run with complete readable logs'), with only minor coverage gaps; not a 5 because the action list is not fully comprehensive.	4 / 5
Completeness	Explicitly answers both what ('guides real TUI usage with step-by-step capture-pane snapshots rather than ANSI raw pipe logs') and when ('should be used when the user asks to ... or requests a tmux-based real user E2E run'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Direct quotes of natural user phrasings including synonyms ('用 tmux 做真实测试', '保存 tmux 日志', '像真实用户一样测试 Qwen', '生成可复查的 TUI 测试报告', '测试 slash command 交互') give comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (tmux-driven real-user TUI testing with readable capture-pane logs) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: QwenLM/qwen-code
Path: .qwen/skills/tmux-real-user-testing/SKILL.md
Commit: 054eabb

Reviewed: 1 day 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.