命令行交互体验评估专家
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "cli-ux-tester":https://skillpi.com/zh/skills/deepskill-cb4059b746216348bc7b4c4628d82d8ef7b39b2e4f412ea3414bd3943c8d906e。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/testing/cli-ux-tester/skills/cli-ux-tester/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/testing/cli-ux-tester/skills/cli-ux-tester --skill cli-ux-tester来源与配置
查看 GitHub 源码jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目介绍 命令行交互体验评估专家 的公开用途。DeepSkill 当前公开目录说明:“CLI、终端工具和开发者 API 的专家级用户体验评估员。适用于审查命令可用性、错误消息、帮助系统或开发者体验时使用。” 适用场景包括测试与安全校验。本页根据公开目录资料和固定版本的上游仓库整理,建议使用前核对该版本的环境、工具、权限及数据处理要求。Skillπ 提供站方用途介绍与原站链接;原始 SKILL.md 和附件仅在对应许可允许时开放。
文件浏览
---
name: cli-ux-tester
description: Expert UX evaluator for CLIs, terminal tools, and developer APIs. Use when reviewing command usability, error messages, help systems, or developer experience.
version: 3.0.0
allowed-tools: Read, Bash, AskUserQuestion, Agent
---
# CLI UX Tester
This skill evaluates the usability of command-line interfaces and developer tools. It identifies the target CLI,
asks clarifying questions if needed, runs three evaluation agents in parallel, then passes the collected results
to a synthesizer agent to produce artifacts.
**Architecture:** The skill spawns all evaluation sub-agents directly (one Explore agent and two test agents in
parallel). This works around the platform constraint that sub-agents cannot spawn further sub-agents. The
`cli-ux-tester:cli-ux-tester` agent acts as a pure synthesizer — it receives the pre-collected test data and
produces the scored report and artifacts.
## Step 1: Detect target CLI
Try to identify the CLI to evaluate from the user's message and current directory context.
**From the user's message:**
- If the user names a specific command or tool (e.g., "review my-tool"), use that as the target.
**From the current directory:**
```bash
# Check for executable entry points
ls -la *.sh bin/ scripts/ 2>/dev/null | head -20
# Check for package.json with a bin field (Node.js CLI)
cat package.json 2>/dev/null | grep -A5 '"bin"'
# Check for Python CLI setup
cat setup.py pyproject.toml 2>/dev/null | grep -A5 'console_scripts\|entry_points' | head -20
# Check for Go main package
ls main.go cmd/ 2>/dev/null
# Check README for CLI name and usage
head -50 README.md 2>/dev/null
```
## Step 2: Ask clarifying questions if needed
Skip this step if the target CLI was already identified from the user's message in Step 1.
Otherwise, ask exactly one AskUserQuestion using the appropriate form below:
**Entry point(s) detected in current directory** → ask which to evaluate:
```text
Question: "Which CLI should I evaluate?"
Options:
- [Each detected entry point]
- A different installed command (provide the name)
- A different path (provide the path)
```
**No entry points detected** → ask the user to specify:
```text
Question: "Which CLI tool should I evaluate?"
Options:
- An installed command available in $PATH (provide the name)
- A path to an executable (provide the path)
```
Proceed directly to Step 3 with whatever the user provides.
## Step 3: Run evaluation agents in parallel
Locate the reference files first:
- Use Glob (`**/testing-checklist.md`) to find `testing-checklist.md`; note the path
- Use Glob (`**/test-scenarios.md`) to find `test-scenarios.md`; note the path
Then spawn these three agents simultaneously, substituting the actual `{cli_command}` and `{working_dir}`:
**Explore agent** — codebase mapping:
```text
subagent_type: Explore
prompt: "Map the {cli_command} CLI codebase in {working_dir}. Find: all commands and subcommands,
help text locations, error handling code, version output, README and docs files, entry point(s),
flag/argument parsing. Return a structured summary: command tree, key file locations, patterns
observed."
```
**Test agent A** — discovery and help:
```text
subagent_type: general-purpose
prompt: "Test {cli_command}'s help system and discoverability (run from {working_dir}).
Run: {cli_command} --help, {cli_command} -h, {cli_command} help, {cli_command} (no args),
{cli_command} --version, {cli_command} -v, {cli_command} version, {cli_command} invalid-subcommand,
{cli_command} --invalid-flag. For each subcommand found, also run: {cli_command} subcommand --help.
Capture exact output. Note: what works, what fails, what's missing."
```
**Test agent B** — error handling and consistency:
```text
subagent_type: general-purpose
prompt: "Test {cli_command}'s error handling and consistency (run from {working_dir}).
Run: commands with missing required args, invalid flag values, nonexistent files, wrong syntax.
Check whether flag names are consistent across subcommands (--verbose always means the same thing).
Check exit codes with echo $?. Capture exact outputs. Note every inconsistency."
```
Wait for all three agents to complete and collect their full outputs before proceeding.
## Step 4: Launch synthesizer agent
Once all evaluation results are collected, launch the `cli-ux-tester:cli-ux-tester` agent.
Pass:
- The working directory
- The CLI entry point (command name, script path, or executable)
- Any relevant context from the user's message (e.g., "focus on error messages")
- The full output from all three evaluation agents (Explore, Test A, Test B)
- Path to `testing-checklist.md`
- Path to `test-scenarios.md`
## Step 5: Report results
When the agent completes, inform the user:
```text
✅ Evaluation complete!
📁 Results saved to: {timestamped_directory}
📊 Overall score: {overall_score}/5
🔍 Top issues: {brief_summary}
Clean up with: rm -rf CLI_UX_EVALUATION_*/
```
## Error handling
- **CLI not found**: Ask the user to confirm the command name or path
- **Permission denied**: Note the issue and ask if they want to test a different entry point
- **No CLI in current directory**: Ask the user to specify which tool to evaluate
当前收录版本
3.0.0
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
提供 CLI 工具的专业用户体验评估能力,适用于开发者审查命令可用性、错误消息、帮助系统等场景
评分依据
description 清晰描述了适用场景(CLI、终端工具、开发者 API 的 UX 评估)
评分依据
结构完整,包含清晰的步骤划分(Step 1-5)和出口条件
评分依据
使用标准工具(Read、Bash、AskUserQuestion、Agent),参数正确
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
-
删除文件
先确认绝对路径及作用范围,保留可恢复备份;不要直接对重要目录运行示例命令。
主文档提及 · 第 138 行
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。