Token导航 LogoToken导航

Agent Skill · 运维和基础设施

let-fate-decide(让命运决定)

let-fate-decide 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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 是运维和基础设施类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在运维和基础设施类的 2,449 个 Skill 里排第 82。

总安装 33,264周安装 1,382GitHub Stars 4,888下载 11,648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
unknown

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/trailofbits/skills
仓库路径:skills/let-fate-decide
安装命令:
npx skills add https://github.com/trailofbits/skills --skill 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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/trailofbits/skills --skill let-fate-decide

这个 Skill 是做什么的

运维和基础设施类 Skill 处理部署、监控、日志和云资源,多数需要较高的执行权限。

当提示模糊或不明确时,使用加密熵绘制 4 张塔罗牌来指导决策。

触发显式调用(“让命运决定”、“感觉幸运”)、漫不经心的委托、游戏王引用或真正模棱两可的提示,其中多种方法同样有效 使用标准的 78 张牌,采用 Fisher-Yates 洗牌,每张牌有 50% 的逆转机会;从 Markdown 文件中输出带有卡片含义的 JSON 解释 4 个位置的分布(背景、挑战、指导、结果),将抽象的卡片含义综合为具体的技术决策 明确避免安全关键决策、覆盖用户需求或在脚本失败时模拟绘制;每个决策点仅抽奖一次

来源仓库内路径:skills/let-fate-decide

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/trailofbits/skills --skill 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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

let-fate-decide 怎么安装?

在终端执行 npx skills add https://github.com/trailofbits/skills --skill 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 Codex、Claude、Cursor、Gemini CLI。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?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

let-fate-decide 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

let-fate-decide 用的人多吗?

公开数据是累计安装 33,264 次,近一周安装 1,382 次,下载 11,648 次,GitHub 4,888 星。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

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 来源仓库有 4,888 星,维护活跃度相对可查。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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 Codex,想直接扩展它能力的人。
  • 需要处理运维和基础设施类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

运维和基础设施类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
brainstorming

头脑风暴 · Codex、Claude

3,148,776173,131操作浏览器MIT通过
copywriting

文案写作 · Codex、Claude

1,996,72425,583需要联网MIT通过
openclaw-secure-linux-cloud

OpenClaw secure linux cloud 命令行 · Codex、Claude

1,853,08840接触敏感数据未明确未通过
xget

xget 命令行 · Codex、Claude

1,799,28040执行命令未明确未通过
requesting-code-review

代码审查请求 · Codex、Claude

1,590,144173,103权限未标注MIT通过
let-fate-decide

让命运决定 · 本页

33,2644,888只读未明确通过

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

Let Fate Decide

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

Quick Start

  1. Run the drawing script: uv run --no-config {baseDir}/scripts/draw_cards.py
  2. The script outputs JSON with 4 drawn cards, each with a file path relative to {baseDir}/
  3. Read each card's meaning file to understand the draw
  4. Interpret the spread using the guide at {baseDir}/references/INTERPRETATION_GUIDE.md
  5. Apply the interpretation to the task at hand

When to Use

  • Vague prompts: The user's request is ambiguous and multiple reasonable approaches exist
  • Explicit invocations: "I'm feeling lucky", "let fate decide", "dealer's choice", "surprise me", "whatever you think", "YOLO"
  • Casual delegation: "whatever", "up to you", "your call", "idk", "just do something", "wing it", "I trust you", "doesn't matter", "do what you want", "I don't care", "any approach works", "you pick"
  • 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"
  • Shrug-like brevity: Very short prompts that fully delegate the decision without expressing a preference
  • Redraw requests: "Try again" or "draw again" when no actual system changes occurred (this means draw new cards, not re-run the same approach)
  • Tie-breaking: When you are about to arbitrarily pick between 2+ valid approaches, draw cards instead of silently choosing one

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 you NOT to use Tarot
  • The user's tone is precision-seeking rather than casual -- use ask-questions-if-underspecified instead to gather actual requirements

How It Works

The Draw

The script uses secrets for cryptographic randomness:

  1. Builds a standard 78-card Tarot deck (22 Major Arcana + 56 Minor Arcana)
  2. Performs a Fisher-Yates shuffle via secrets.randbelow() (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:

PositionRepresentsQuestion It Answers
1The ContextWhat is the situation really about?
2The ChallengeWhat obstacle or tension exists?
3The GuidanceWhat approach should be taken?
4The OutcomeWhere does this path lead?

Card Files

Each card's meaning is in its own markdown file under {baseDir}/cards/:

  • cards/major/ - 22 Major Arcana (archetypal forces)
  • cards/wands/ - 14 Wands (creativity, action, will)
  • cards/cups/ - 14 Cups (emotion, intuition, relationships)
  • cards/swords/ - 14 Swords (intellect, conflict, truth)
  • cards/pentacles/ - 14 Pentacles (material, practical, craft)

Interpretation

After drawing, read each card's 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
  • Never output interpretation as a text-only turn. Include the interpretation alongside your next tool call (the action that implements the chosen option). Read all 4 cards in parallel if possible.

Example Session

User: "I dunno, just make it work somehow"

[Draw cards]
1. The Magician (upright) - Context: All tools are available
2. Five of Swords (reversed) - Challenge: Let go of a combative approach
3. The Star (upright) - Guidance: Follow the aspirational path
4. Ten of Pentacles (upright) - Outcome: Long-term stability

Interpretation: The cards suggest you have everything you need (Magician).
The challenge is avoiding overengineering or adversarial thinking about edge
cases (Five of Swords reversed). Follow the clean, hopeful approach (Star)
and build for lasting maintainability (Ten of Pentacles).

Approach: Implement the simplest correct solution with clear structure,
prioritizing long-term readability over clever optimizations.

Error Handling

If the drawing script fails:

  • Script crashes with traceback: Report the error to the user and skip the reading. Do not invent cards or simulate a draw — the whole point is real entropy.
  • Card file not found: Note the missing file, interpret the card from its name and suit alone, and continue with the reading.
  • Never fake entropy: If the script cannot run, do not simulate a draw using your own "randomness." Tell the user the draw failed.

Rationalizations to Reject

RationalizationWhy Wrong
"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
"The reversed card means do nothing"Reversed means a different angle, not inaction
"Major Arcana overrides user requirements"User requirements always take priority over card readings
"I'll keep drawing until I get what I want"One draw per decision point; accept the reading

平台分布

Codex

37.9%
按下载量换算4,415

Claude

30.24%
按下载量换算3,522

Cursor

19.18%
按下载量换算2,234

Gemini CLI

8.77%
按下载量换算1,022

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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