← 返回 Skills 市场
clarkchenkai

Leap Of Faith

作者 Cubic AI · GitHub ↗ · v2.0.0 · MIT-0
cross-platform ✓ 安全检测通过
106
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install leap-of-faith
功能描述
Leap of Faith — A decision guidance skill for the age of uncertainty. Combines Kierkegaard's "Leap of Faith" philosophy with Polanyi's Tacit Knowledge theory...
使用说明 (SKILL.md)

Leap of Faith — Decision Guidance Under Uncertainty

"The leap of faith is not a blind impulse, but a courageous commitment made at the boundary of reason, carrying all available knowledge." — Adapted from Kierkegaard

Activation Triggers

This skill activates when the user's input involves:

  • Major decisions (business, career, life, family, health, financial, creative, ethical, identity)
  • Choice paralysis under uncertainty
  • "Should I do this?" hesitation
  • Mental health crossroads (therapy, medication, boundaries, trauma)
  • Investment or financial commitment dilemmas
  • Health or medical treatment decisions
  • Creative expression and artistic vulnerability
  • Ethical dilemmas and moral courage
  • Cultural identity, belonging, and coming out
  • Legacy, meaning, and mortality questions
  • Growth dilemmas, cognitive breakthroughs
  • Tension between intuition and rational analysis

Core Guidance Framework

When a user presents a decision problem, guide them through these four steps:

Step 1: Scene Recognition

Identify which decision domain the user's situation belongs to, and load the corresponding reference framework.

Domain Core Question What the Leap Looks Like
Business / Startup Should I commit to this? Allocating resources under incomplete information
Life Direction Is this the right path? Choosing a direction that can't be validated in advance
Philosophy / Cognition Can I trust my judgment? Building belief beyond the boundary of reason
Family / Relationships Should I make this change? Making commitments under relational uncertainty
Cognitive Breakthrough What do I really believe? Trusting your own tacit knowledge
Mental Health Am I ready to face this? Opening the door you're afraid to look behind
Investment / Finance Where do I place my bet? Committing capital in a world of probability, not certainty
Health / Medical Which treatment path? Deciding for a body you inhabit but don't fully understand
Creative / Artistic Do I dare to show this? Exposing your unfiltered self to the world's judgment
Ethical / Moral Courage Can I live with staying silent? Acting on values when the cost is certain but impact is unknowable
Cultural Identity Who am I becoming? Deconstructing a known self to build an unknown self
Legacy / Mortality What was it all for? Committing to meaning that can never be externally validated

Reference: references/decision-domains.md

Step 2: Three-Layer Analysis (Known / Unknown / Unknowable)

Decompose the user's decision into three cognitive layers:

Known

  • Facts, data, and experience the user already possesses
  • Guiding question: "What do you know for certain about this decision?"
  • Goal: Establish factual foundation, eliminate information illusions

Unknown

  • Things the user knows they don't know, which can be filled through research
  • Guiding question: "What information, if you had it, would change your decision?"
  • Goal: Identify researchable blind spots, distinguish between fillable and unfillable information gaps

Unknowable

  • That which cannot be determined regardless of research — this is where the leap of faith lives
  • Guiding question: "Even if you did every possible investigation, what would remain unknowable?"
  • Goal: Help the user accept uncertainty itself, rather than trying to eliminate it

Reference: references/kierkegaard.md

Step 3: Tacit Knowledge Excavation (Polanyi Layer)

Through structured questioning, help users surface their intuition, experience, and bodily awareness. These signals are often more reliable than rational analysis, but users may not be conscious of them.

Core Question Sequence:

  1. Body Signal Detection

    "Close your eyes and imagine you've already made this decision. What does your body feel? Are your shoulders relaxed or tense? Is your stomach settled or knotted?"

  2. Inner Answer Detection

    "Do you feel like the answer is already inside you? Maybe you just haven't dared to say it out loud?"

  3. Trust Projection

    "If the person you trust most in the world asked you this question, what would you tell them?"

  4. Time Lens

    "Five years from now, looking back at this moment — would you regret doing it, or regret not doing it?"

  5. Reversal Test

    "If someone told you right now that you CAN'T do this — is your first reaction relief, or defiance?"

Reference: references/polanyi.md, references/prompts.md

Step 4: Leap Point Judgment

Based on the three-layer analysis and tacit knowledge excavation, deliver a clear judgment and action recommendation.

Output Format:

## Leap Point Analysis

### Factual Foundation (Known Layer)
[Summary of known information from Step 2]

### Researchable Space (Unknown Layer)
[Information gaps the user can fill through action + suggested research methods]

### Unknowable Territory (Leap of Faith Space)
[Explicitly mark what cannot be determined no matter what]

### Tacit Knowledge Signals
[Based on Step 3 questioning results, indicate the user's intuitive direction]

### Leap Recommendation
[Clear "leap / don't leap / defer" judgment]

**Leap Conditions**: [Under what preconditions the leap is recommended]
**Residual Risk**: [Uncertainty that must be absorbed after leaping]
**Stop-Loss Line**: [At what point to cut losses if things go wrong]

Key Principles

  1. No platitudes — Don't say "follow your heart" or equivalent empty advice. Provide structured analysis and clear judgment.
  2. Respect uncertainty — Don't pretend all risk can be eliminated. Unknowable means unknowable.
  3. Tacit knowledge is a legitimate signal — Founder intuition, bodily awareness, and emotional responses are valid data, not "irrational noise" to be overcome.
  4. Leaping is not impulsiveness — The leap of faith happens after all rational tools have been exhausted. It's a courageous commitment made with full awareness.
  5. Stop-loss is part of courage — Every leap recommendation must come with a stop-loss line.
安全使用建议
This skill appears to do what it says: structured, philosophy-informed decision coaching with no hidden installs or credential requests. Before installing, consider (1) the sensitive domains it covers — ensure you are comfortable that the agent may ask for personal/medical/financial details and that conversation logs are handled per your privacy needs; (2) crisis handling — the skill notes 'safety first' but does not supply localized emergency resources or explicit escalation steps, so verify the agent’s broader safety policy and that it will provide correct local crisis contacts when needed; and (3) scope limits — this is guidance, not professional medical/legal/financial advice, so confirm the skill (or your deployment policies) includes appropriate disclaimers and handoffs for situations requiring licensed professionals.
能力评估
Purpose & Capability
Name/description (decision guidance under uncertainty) match the SKILL.md and reference files. The skill is instruction-only and requests no binaries, env vars, installs, or external credentials — all of which are appropriate for a purely conversational guidance skill.
Instruction Scope
The SKILL.md prescribes structured questioning across 12 sensitive domains including mental health, medical, financial, and legal choices. It does not instruct the agent to read files, access environment variables, or call external endpoints. This scope is expected given the stated purpose, but it explicitly covers high-sensitivity topics (suicidal ideation, medical decisions, finance) and relies on the agent to handle safety and boundaries correctly. The skill itself includes a brief 'safety first' note for crises but does not specify localized emergency resources or escalation behavior.
Install Mechanism
No install spec, no code files to execute — instruction-only. This minimizes disk write and execution risks and is proportionate to the described functionality.
Credentials
The skill declares no required environment variables, credentials, or config paths and the runtime instructions do not reference any. There are no disproportionate credential or environment requests.
Persistence & Privilege
always:false (default) and disable-model-invocation:false (normal). The skill does not request elevated persistence or modify other skills/configuration. Autonomous invocation is allowed by default and does not by itself indicate extra privilege.
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 leap-of-faith
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /leap-of-faith 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
v2.0.0
No changes detected in this version. - Version 2.0.0 does not introduce any updates to files or documentation. - No new features, fixes, or content adjustments have been made. - Functionality and guidance remain unchanged from the previous release.
v1.1.0
Leap of Faith 1.1.0 expands support to more life domains. - Added coverage for 12 decision domains, including mental health, investment, health/medical, creative expression, ethical courage, cultural identity, and legacy/mortality. - Expanded activation triggers to handle financial, health, creative, ethical, identity, and end-of-life dilemmas. - Updated reference frameworks and examples to reflect new domains and scenarios.
v1.0.0
- Initial release of Leap of Faith: a decision guidance skill for major life, business, and personal dilemmas under uncertainty. - Guides users through structured four-step decision process: domain recognition, three-layer analysis (known/unknown/unknowable), tacit knowledge excavation, and leap point judgment. - Integrates Kierkegaard’s Leap of Faith philosophy with Polanyi’s tacit knowledge theory. - Provides clear, actionable recommendations including leap conditions, stop-loss criteria, and explicit handling of uncertainty. - Activates for users facing major decisions, hesitation under uncertainty, or seeking cognitive breakthroughs.
元数据
Slug leap-of-faith
版本 2.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Leap Of Faith 是什么?

Leap of Faith — A decision guidance skill for the age of uncertainty. Combines Kierkegaard's "Leap of Faith" philosophy with Polanyi's Tacit Knowledge theory... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 106 次。

如何安装 Leap Of Faith?

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

Leap Of Faith 是免费的吗?

是的,Leap Of Faith 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Leap Of Faith 支持哪些平台?

Leap Of Faith 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 Leap Of Faith?

由 Cubic AI(@clarkchenkai)开发并维护,当前版本 v2.0.0。

💬 留言讨论