Token导航 LogoToken导航

Agent Skill · 研究检索

leap-of-faith(信仰的飞跃)

leap-of-faith 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

leap-of-faith 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 29,772。

总安装 3,003周安装 129GitHub Stars 公开资料未说明下载 1,053核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
2.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:leap-of-faith(信仰的飞跃)
来源仓库:https://github.com/clarkchenkai/leap-of-faith
安装命令:
openclaw skills install leap-of-faith
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install leap-of-faith

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

融合哲学理论与隐性知识指导不确定环境下的决策。基于克尔凯郭尔信仰飞跃概念设计决策框架。适合战略模糊期领导力发展类咨询场景。leap-of-faith 属于研究检索类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install leap-of-faith。

内容偏重理论探讨,需结合实际业务目标使用。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install leap-of-faith;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

leap-of-faith 怎么安装?

在终端执行 openclaw skills install leap-of-faith。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

leap-of-faith 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

leap-of-faith 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

leap-of-faith 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

leap-of-faith 用的人多吗?

公开数据是累计安装 3,003 次,近一周安装 129 次,下载 1,053 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

leap-of-faith 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
leap-of-faith

信仰的飞跃 · 本页

3,003—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
leap-of-faith
description
|
license
Apache-2.0
metadata
author
clarkchenkai
version
1.0
language
en

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.

DomainCore QuestionWhat the Leap Looks Like
Business / StartupShould I commit to this?Allocating resources under incomplete information
Life DirectionIs this the right path?Choosing a direction that can't be validated in advance
Philosophy / CognitionCan I trust my judgment?Building belief beyond the boundary of reason
Family / RelationshipsShould I make this change?Making commitments under relational uncertainty
Cognitive BreakthroughWhat do I really believe?Trusting your own tacit knowledge
Mental HealthAm I ready to face this?Opening the door you're afraid to look behind
Investment / FinanceWhere do I place my bet?Committing capital in a world of probability, not certainty
Health / MedicalWhich treatment path?Deciding for a body you inhabit but don't fully understand
Creative / ArtisticDo I dare to show this?Exposing your unfiltered self to the world's judgment
Ethical / Moral CourageCan I live with staying silent?Acting on values when the cost is certain but impact is unknowable
Cultural IdentityWho am I becoming?Deconstructing a known self to build an unknown self
Legacy / MortalityWhat 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?"

  1. Inner Answer Detection

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

  1. Trust Projection

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

  1. Time Lens

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

  1. 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.

平台分布

OpenClaw

81.4%
按下载量换算857

安全审计

VirusTotal

未展示

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills