← 返回 Skills 市场
agimodel

Ask

作者 AGImodel · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
320
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install ask
功能描述
The thinking partner that helps you ask better questions. Trigger when someone needs to get to the root of a problem, make a difficult decision, prepare for...
使用说明 (SKILL.md)

Ask

The Question Behind the Question

Every problem has a surface question and a real question. The surface question is what you think you are asking. The real question is what you actually need to answer.

"Should I take this job offer?" is a surface question. The real question might be: "Am I running toward something or away from something?" Or: "What would I regret more — taking it or not taking it?" Or: "Do I trust this manager, and is everything else negotiable?"

The surface question has a yes or no answer. The real questions have answers that change your life.

This skill finds the real question.


How It Works

You bring any problem, decision, or situation. The skill does not answer it immediately. It asks back — the question that reframes the problem, reveals the assumption you have not examined, or surfaces the information that would actually resolve the uncertainty.

This is not therapy. It is thinking infrastructure. The goal is clarity, not comfort.


Question Types and When to Use Them

QUESTION_TAXONOMY = {
  "clarifying": {
    "purpose":  "Expose vague language that creates false certainty",
    "triggers": ["always", "never", "everyone", "nobody", "should", "can't"],
    "examples": ["What specifically do you mean by [vague term]",
                 "When you say [X], what does that look like in practice",
                 "What would have to be true for that to be false"]
  },

  "reframing": {
    "purpose":  "Shift perspective to reveal options that were invisible before",
    "examples": ["What would you tell a close friend in this exact situation",
                 "If you knew you could not fail, what would you do",
                 "What is the opposite of your current assumption",
                 "What would someone who disagreed with you say, and are they right"]
  },

  "assumption_surfacing": {
    "purpose":  "Make invisible constraints visible so they can be examined",
    "examples": ["What are you taking for granted here",
                 "What would have to change for your current approach to be wrong",
                 "What is the constraint you have accepted that might not be real"]
  },

  "decision_forcing": {
    "purpose":  "Collapse analysis paralysis into a specific choice",
    "examples": ["If you had to decide by noon today, what would you choose",
                 "What information, if you had it, would make this decision easy",
                 "Which option would you regret more in ten years"]
  },

  "root_cause": {
    "purpose":  "Get beneath symptoms to underlying causes",
    "method":   "Five Whys — ask why five times in sequence",
    "example":  """
      Problem: I keep missing deadlines
      Why 1: I underestimate how long tasks take
      Why 2: I do not break tasks into concrete steps before estimating
      Why 3: I am uncomfortable with uncertainty so I avoid detailed planning
      Why 4: Detailed plans reveal how much I do not know
      Why 5: I am afraid of looking incompetent

      Root cause: Fear of incompetence, not poor time management
      Solution: Completely different from what the surface problem suggested
    """
  }
}

Decision Framework

When the question is a decision, the skill structures it:

DECISION_FRAMEWORK = {
  "step_1_define":    "What exactly is being decided, and by when",
  "step_2_options":   "What are the real options — including the ones you are avoiding",
  "step_3_criteria":  "What does a good outcome look like — write it down before evaluating",
  "step_4_evaluate":  "Rate each option against each criterion — separately, not holistically",
  "step_5_test":      "Which option would you regret most. Which feels right when you stop thinking.",
  "step_6_decide":    "Make the decision. Most decisions are more reversible than they feel."
}

When to Stop Asking and Start Acting

Not every question needs to be answered before acting. Some questions are only answerable through action. The skill distinguishes between:

QUESTION_TYPES_BY_ANSWERABILITY = {
  "answerable_now":    "More information or clearer thinking will resolve this",
  "answerable_later":  "Only experience will answer this — act and learn",
  "unanswerable":      "No information will resolve this — decide on values, not analysis"
}

The most common mistake in thinking is treating type 2 and 3 questions as type 1 — gathering more data when the answer requires action or acceptance, not analysis.


Quality Check

  • Surface question identified
  • Real question surfaced through follow-up
  • Key assumption examined
  • Decision structured if applicable
  • Action or acceptance identified as the right next step
安全使用建议
This skill is instruction-only and appears coherent with its stated purpose. It does not request credentials or install code. Consider that using the skill will involve you sharing whatever context or personal information you provide in prompts — avoid disclosing secrets (passwords, private keys, or highly sensitive personal data). If you plan to enable autonomous invocation for agents that may use this skill, be aware the agent could prompt users with follow-ups derived from your data; lock down autonomous behavior if that is a concern.
功能分析
Type: OpenClaw Skill Name: ask Version: 1.0.0 The 'ask' skill bundle is a purely instructional framework designed to guide an AI agent in helping users refine their questioning and decision-making processes. It contains no executable code, network requests, or sensitive data access, and its instructions in skill.md are entirely aligned with its stated purpose as a cognitive tool.
能力评估
Purpose & Capability
Name and description match the contents: SKILL.md provides question taxonomies, decision frameworks, and prompts for reframing. There are no unexpected requirements (no env vars, no binaries, no external integrations).
Instruction Scope
Instructions are limited to asking clarifying/reframing/decision questions and guidance on when to act. They do not instruct the agent to read system files, call external endpoints, or collect unrelated data.
Install Mechanism
No install spec and no code files. Because it's instruction-only, nothing is written to disk or fetched during install.
Credentials
The skill declares no environment variables, credentials, or config paths and the runtime instructions do not reference any. Requested access is proportional to the stated purpose (none required).
Persistence & Privilege
always is false and defaults apply. The skill does not request persistent or elevated privileges, nor does it modify other skills or system configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install ask
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ask 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug ask
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Ask 是什么?

The thinking partner that helps you ask better questions. Trigger when someone needs to get to the root of a problem, make a difficult decision, prepare for... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 320 次。

如何安装 Ask?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ask」即可一键安装,无需额外配置。

Ask 是免费的吗?

是的,Ask 完全免费(开源免费),可自由下载、安装和使用。

Ask 支持哪些平台?

Ask 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Ask?

由 AGImodel(@agimodel)开发并维护,当前版本 v1.0.0。

💬 留言讨论