ask
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 a critical conversation, challenge their own assumptions, or simply does not know where to start. The quality of your questions determines the quality of your thinking. This skill upgrades both.
Best use case
ask is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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 a critical conversation, challenge their own assumptions, or simply does not know where to start. The quality of your questions determines the quality of your thinking. This skill upgrades both.
Teams using ask should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ask/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ask Compares
| Feature / Agent | ask | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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 a critical conversation, challenge their own assumptions, or simply does not know where to start. The quality of your questions determines the quality of your thinking. This skill upgrades both.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# 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 stepRelated Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述