Art Of Questioning
v1.1.0培养洞察力和深度提问能力的双模式 Skill。 实战模式：分析用户正在学习/听/读的内容，自适应匹配 15+ 跨学科提问方法论， 生成 5 个关键环节的深度问题清单，每个问题标注方法论和认知层次。 训练模式：构造仿真场景，分环节教学讲解最佳提问方式，支持定时任务自动触发。 当用户需要深度理解内容、准备提问、练习批...
⭐ 0· 62·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (training users to ask deeper questions) match the actual content: SKILL.md and methodology library define question frameworks and output templates. The skill requires no binaries, env vars, or installs — proportional for an instruction-only tutoring skill.
Instruction Scope
Runtime instructions operate purely on user-provided content (classify content, derive 5 key stages, produce questions, or construct training scenarios). They do not reference files, credentials, or external endpoints. Note: the doc mentions '定时任务自动触发' (timed/automatic triggers) and a scene library — this implies the agent may be expected to initiate periodic training sessions if the hosting platform supports scheduling, but the skill itself provides no mechanism, code, or external endpoints to perform scheduling or data exfiltration.
Install Mechanism
No install spec and no code files — lowest-risk delivery model (instruction-only). There are no downloads, no extracted archives, and nothing written to disk by the skill materials.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. All outputs are derived from user input and internal methodology text; no disproportionate access requested.
Persistence & Privilege
always:false and no special privileges requested. The skill can be invoked normally by the agent; there is no code that modifies other skills or system-wide settings. The only potential persistence-related item is the described 'timed task' behavior, but no implementation or credential access is included in the package.
Assessment
This skill appears internally consistent and low-risk: it is instruction-only, asks for nothing sensitive, and works on whatever text you provide. Before using it, avoid pasting secrets or proprietary internal documents (the skill will analyze whatever you give it). If your agent/platform supports scheduled/automatic runs, check how those triggers are managed (the SKILL.md mentions timed training but provides no code); ensure you control and understand any schedule the host platform might set up. Otherwise it is safe to install from a coherence perspective.Like a lobster shell, security has layers — review code before you run it.
latestvk972qer2zqqyckwc1ra8f6n35183m5dt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.