Token导航 LogoToken导航

Agent Skill · 研究检索

let-fate-decide(让命运决定)

let-fate-decide 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。

let-fate-decide 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 38,711。

总安装 1,521周安装 64GitHub Stars 公开资料未说明下载 532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
1.0.2

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:let-fate-decide(让命运决定)
来源仓库:https://github.com/kc0bfv/let-fate-decide
安装命令:
openclaw skills install let-fate-decide
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 let-fate-decide

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。

let-fate-decide 引入加密随机性抽取塔罗牌,辅助模糊意图下的决策引导。适用于战略规划、创意激发或不确定性较高的探索性任务。通过 clawhub 安装并使用 openclaw skills install let-fate-decide 命令部署。结果不具备预测性质,仅供启发思考而非替代专业判断。

每次调用生成四张牌布局,附带解释仅供参考。

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 let-fate-decide;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

let-fate-decide 怎么安装?

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

let-fate-decide 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。

let-fate-decide 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。

let-fate-decide 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。

let-fate-decide 用的人多吗?

公开数据是累计安装 1,521 次,近一周安装 64 次,下载 532 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。

let-fate-decide 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
let-fate-decide

让命运决定 · 本页

1,521—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
let-fate-decide
description
Draw Tarot cards using cryptographic randomness to inject entropy into planning when prompts are vague or underspecified. Interprets a 4-card spread to guide next steps. Use when the user is nonchalant, feeling lucky, says 'let fate decide', makes Yu-Gi-Oh references ('heart of the cards'), demonstrates indifference about approach ('whatever you think', 'surprise me', 'dealer's choice'), or says 'try again' / 'draw again' on a system with no changes. Also triggers on sufficiently ambiguous prompts where multiple approaches are equally valid.

Let Fate Decide

When the path forward is unclear, let the cards speak.

Based on the let-fate-decide plugin by theexpensiveexperience, licensed under CC BY-SA 4.0.

Quick Start

  1. Run the drawing script:
   python3 {baseDir}/scripts/draw_cards.py
  1. The script outputs JSON with 4 drawn cards, each with a suit and card_id
  1. Look up each card's meaning in the appropriate file under {baseDir}/cards/:

- cards/major.md — 22 Major Arcana - cards/wands.md — 14 Wands - cards/cups.md — 14 Cups - cards/swords.md — 14 Swords - cards/pentacles.md — 14 Pentacles

Each card is under a heading matching its name (e.g. "# The Fool", "# Ace of Cups").

  1. Interpret the spread using {baseDir}/references/INTERPRETATION_GUIDE.md
  1. Apply the interpretation to the task at hand

When to Use

  • Vague prompts: The user's request is ambiguous and multiple valid approaches exist
  • Explicit invocations: "I'm feeling lucky", "let fate decide", "dealer's choice", "surprise me", "whatever you think"
  • Yu-Gi-Oh energy: "Heart of the cards", "I believe in the heart of the cards", "you've activated my trap card", "it's time to duel"
  • Nonchalant delegation: The user expresses indifference about the approach
  • Redraw requests: "Try again" or "draw again" when no actual system changes occurred (draw new cards)
  • Tie-breaking: When you genuinely cannot decide between equally valid approaches

When NOT to Use

  • The user has given clear, specific instructions
  • The task has a single obvious correct approach
  • Safety-critical decisions (security, data integrity, production deployments)
  • The user explicitly asks NOT to use Tarot

How It Works

The Draw

The script uses os.urandom() for cryptographic randomness:

  1. Builds a standard 78-card Tarot deck (22 Major Arcana + 56 Minor Arcana)
  2. Performs a Fisher-Yates shuffle using rejection sampling (no modulo bias)
  3. Draws 4 cards from the top
  4. Each card independently has a 50% chance of being reversed

The Spread

The 4 card positions represent:

  • Position 1 — The Context: What is the situation really about?
  • Position 2 — The Challenge: What obstacle or tension exists?
  • Position 3 — The Guidance: What approach should be taken?
  • Position 4 — The Outcome: Where does this path lead?

Interpretation

After drawing, look up each card in its suit file and synthesize meaning. See {baseDir}/references/INTERPRETATION_GUIDE.md for the full interpretation workflow.

Key rules:

  • Reversed cards invert or complicate the upright meaning
  • Major Arcana cards carry more weight than Minor Arcana
  • The spread tells a story across all 4 positions; don't interpret cards in isolation
  • Map abstract meanings to concrete technical decisions

Error Handling

  • Script fails: Report the error to the user and skip the reading. Do not invent cards.
  • Card not found in file: Interpret the card from its name and suit alone; continue the reading.
  • Never fake entropy: If the script cannot run, do not simulate a draw. Tell the user the draw failed.

Rationalizations to Reject

  • "The cards said to, so I must" → Cards inform direction, they don't override safety or correctness
  • "This reading justifies my pre-existing preference" → Be honest if the reading challenges your instinct
  • "I'll keep drawing until I get what I want" → One draw per decision point; accept the reading

平台分布

OpenClaw

77.38%
按下载量换算412

安全审计

VirusTotal

通过

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