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

92%

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

85%

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 a clear sequenced workflow, robust polling/validation, and clean one-level-deep reference to a real helper script. The only meaningful weakness is redundancy: the manual workflow, helper API, and worked example repeat near-identical tmux commands.

Suggestions

Collapse the duplication between the manual workflow (steps 1–5) and the helper-script section — since scripts/tmux-real-user-log.sh already encapsulates start/snapshot/send/wait-for/finish, present the manual commands only as a brief 'what the script does' note rather than a parallel full workflow.

Trim or merge the 'Short example' into the helper-script section so the canonical end-to-end flow appears once, cross-referenced from 'Designing a test scenario'.

Move the per-flag rationale (e.g. why -S grows per section, why send-keys is split from Enter) into the Common pitfalls section to shorten the inline code commentary.

Dimension	Reasoning	Score
Conciseness	There is no padding of concepts Claude already knows (no 'what is tmux/TUI' exposition) and the pipe-pane caveat is a justified non-obvious tip, but the same tmux workflow is presented three times — the full manual steps 1–5, the helper-script API, and the worked example — so it could be tightened, fitting the score-2 anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Fully executable, copy-paste-ready bash with specific flags (e.g. -x 200 -y 50, capture-pane -p -S -240, send-keys split from Enter) plus a real helper script with complete usage, matching the executable-and-specific anchor rather than the pseudocode/incomplete score-2 anchor.	3 / 3
Workflow Clarity	A clear 5-step sequence (start → snapshot → send keys → poll → finish) with explicit validation checkpoints (poll-for-ready, poll-for-completion) and a timeout feedback behavior that dumps the current pane, plus final-capture-before-kill; this is a capture workflow where polling validation is the appropriate level, so it meets the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The body is an overview pointing to one real, one-level-deep bundle file (scripts/tmux-real-user-log.sh, verified present) via a clearly signaled 'Recommended helper script' section with full usage and path, with no nested references, matching the well-signaled-one-level-deep anchor.	3 / 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 strong: third-person voice, explicit what-and-when, multiple natural trigger phrases in both Chinese and English, and a concrete, distinctive mechanism. It follows the good-example pattern with a clear 'should be used when' clause.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions/mechanisms — "real TUI usage," "step-by-step capture-pane snapshots," "complete readable logs," and a tmux-based E2E run — with no vague language, matching the multiple-specific-actions anchor rather than the score-2 'some actions, not comprehensive' anchor.	3 / 3
Completeness	Explicitly states what it does ("guides real TUI usage with step-by-step capture-pane snapshots rather than ANSI raw pipe logs") and when to use it via an explicit trigger clause, satisfying the both-what-and-when-with-explicit-triggers anchor; it is not capped at 2 because the 'Use when...' guidance is present.	3 / 3
Trigger Term Quality	Provides several natural phrasings a user would actually say (e.g. "用 tmux 做真实测试", "保存 tmux 日志", "像真实用户一样测试 Qwen", "测试 slash command 交互") plus an English fallback, giving good coverage of natural terms rather than jargon-only or partial coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and uniquely keyed (tmux real-user TUI testing with readable capture-pane logs and very specific Chinese/English triggers), making it unlikely to fire for unrelated skills, matching the clear-niche-distinct-triggers anchor.	3 / 3
	Total	12 / 12 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: 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.