Token导航 LogoToken导航

Agent Skill · 前端设计

council-of-logic(逻辑委员会)

council-of-logic 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。

council-of-logic 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 6,853。

总安装 447周安装 19GitHub Stars 1下载 157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:council-of-logic(逻辑委员会)
来源仓库:https://github.com/cleanexpo/nodejs-starter-v1
仓库路径:skills/council-of-logic
安装命令:
npx skills add https://github.com/cleanexpo/nodejs-starter-v1 --skill council-of-logic
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/cleanexpo/nodejs-starter-v1 --skill council-of-logic

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

council-of-logic 依据图灵、冯·诺依曼、贝塞尔和香农四大数学原理验证技术方案,确保算法效率与系统稳定性。适用于编写或审查算法、优化系统架构及评估信息压缩策略等场景。作为预检关卡,可阻止低质量代码进入生产环境。使用前应熟悉各原理的具体要求,避免因不符合标准而被拒绝。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/council-of-logic

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/cleanexpo/nodejs-starter-v1 --skill council-of…;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

    它需要接触敏感数据,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

council-of-logic 怎么安装?

在终端执行 npx skills add https://github.com/cleanexpo/nodejs-starter-v1 --skill council-of-logic。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

council-of-logic 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。

council-of-logic 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

council-of-logic 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。

council-of-logic 用的人多吗?

公开数据是累计安装 447 次,近一周安装 19 次,下载 157 次,GitHub 1 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。

council-of-logic 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。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
council-of-logic

逻辑委员会 · 本页

4471接触敏感数据未明确通过

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

Council of Logic - Mathematical First Principles

Four legendary minds govern all technical decisions. Their principles are non-negotiable.

Description

Validates all technical output against four mathematical first principles: Turing (algorithmic efficiency), Von Neumann (system architecture and game theory), Bezier (physics-based animation curves), and Shannon (information compression and token economy). Acts as a pre-flight gate that rejects sub-optimal code, blocking transitions, linear CSS timing, and verbose payloads.

When to Apply

Positive Triggers

  • Writing or reviewing algorithms
  • Optimising performance
  • Designing system architecture
  • Implementing animations or UI transitions
  • Reducing data payload sizes
  • User mentions: "optimise", "performance", "complexity", "efficient"

Negative Triggers

  • Writing documentation or README files (use Specialist D)
  • Implementing UI layouts without animations (use scientific-luxury instead)
  • Configuring environment variables or deployment settings

The Council

Alan Turing - Algorithmic Efficiency & Logic

Focus: Reduce code complexity. Demand optimal time complexity.

Rules:

  • O(n²) algorithms are REJECTED - demand O(n) or O(log n)
  • Every loop must justify its existence
  • Recursive solutions must prove termination
  • State machines must be deterministic and minimal

Pre-Code Check:

Turing Check: What is the time complexity?
- If O(n²) or worse → REFACTOR
- If O(n log n) → ACCEPTABLE
- If O(n) or O(log n) → APPROVED

Red Flags: Nested loops, .filter().map().filter() chains

Resolution: Single-pass algorithm


John von Neumann - System Architecture & Game Theory

Focus: Optimise agent workflows. Treat interactions as strategic games.

Rules:

  • Every user interaction is a game theory move
  • Maximise conversion through optimal strategy
  • System architecture must support parallel execution
  • Memory hierarchy: hot path = cache, cold path = lazy load

Pre-Architecture Check:

Von Neumann Check: Is this the Nash Equilibrium?
- User benefit maximised? ✓
- System cost minimised? ✓
- Competing concerns balanced? ✓

Red Flags: Blocking operations, race conditions

Resolution: Async/parallel design


Pierre Bezier - Frontend Physics & Animation

Focus: Interpolation curves for luxury UI. No linear transitions.

Rules:

  • BANNED: transition: all 0.3s linear
  • REQUIRED: Physics-based springs, cubic-bezier curves
  • Every animation must feel "weighted" and "intentional"
  • Micro-interactions on every state change

Approved Easings:

/* Spring - bouncy, playful */
--ease-spring: cubic-bezier(0.68, -0.55, 0.265, 1.55);

/* Smooth - elegant, refined */
--ease-smooth: cubic-bezier(0.4, 0, 0.2, 1);

/* Bounce - energetic, celebration */
--ease-bounce: cubic-bezier(0.34, 1.56, 0.64, 1);

/* Out-Expo - snappy, decisive */
--ease-out-expo: cubic-bezier(0.19, 1, 0.22, 1);

Pre-Animation Check:

Bezier Check: Does this feel "expensive"?
- Linear timing? → REJECT
- Abrupt start/stop? → REJECT
- Physics-based curve? → APPROVED

Red Flags: Linear timing, jarring transitions

Resolution: Spring/bezier curves


Claude Shannon - Information Theory (Token Economy)

Focus: Maximum signal, minimum noise. Compress everything.

Rules:

  • Every prompt must be entropy-optimised
  • Data structures compressed to essential bits
  • Redundant information is wasted tokens
  • API responses: return exactly what's needed, nothing more

Pre-Communication Check:

Shannon Check: What is the signal-to-noise ratio?
- Redundant words? → COMPRESS
- Unnecessary fields? → REMOVE
- Implicit > Explicit when context allows

Red Flags: Verbose prompts, bloated payloads

Resolution: Compress, dedupe, minimise


Workflow Protocol

STEP 1: THE PROOF

Before writing ANY code, state the mathematical/logical model:

## Mathematical Model

**Problem**: [State the problem in formal terms]

**Turing**: Time complexity target = O(?)
**Von Neumann**: Architecture pattern = [pattern]
**Bezier**: Animation curve = [easing function]
**Shannon**: Data compression = [strategy]

STEP 2: THE SOLVE

Execute with council approval:

## Implementation

**Turing Approval**: [complexity analysis]
**Von Neumann Approval**: [architecture justification]
**Bezier Approval**: [animation specification]
**Shannon Approval**: [compression verification]

STEP 3: THE VERIFY

Post-implementation council review:

## Council Review

- [ ] Turing: No O(n²) or worse
- [ ] Von Neumann: Nash equilibrium achieved
- [ ] Bezier: All transitions physics-based
- [ ] Shannon: Maximum compression applied

Quick Reference: Council Objections

Council MemberRed FlagResolution
TuringNested loops, .filter().map().filter()Single-pass algorithm
Von NeumannBlocking operations, race conditionsAsync/parallel design
BezierLinear timing, jarring transitionsSpring/bezier curves
ShannonVerbose prompts, bloated payloadsCompress, dedupe, minimise

Code Examples

Turing Violation (BAD)

// O(n²) - REJECTED
const result = items.filter((item) => otherItems.some((other) => other.id === item.id));

Turing Approved (GOOD)

// O(n) - APPROVED
const otherSet = new Set(otherItems.map((o) => o.id));
const result = items.filter((item) => otherSet.has(item.id));

Bezier Violation (BAD)

/* Linear - REJECTED */
transition: all 0.3s linear;

Bezier Approved (GOOD)

/* Physics-based - APPROVED */
transition: transform 0.5s cubic-bezier(0.19, 1, 0.22, 1);

Response Format

[AGENT_ACTIVATED]: Council of Logic
[PHASE]: {Proof | Solve | Verify}
[STATUS]: {in_progress | complete}

{council analysis or verification results}

[NEXT_ACTION]: {what to do next}

Anti-Patterns

PatternProblemCorrect Approach
O(n²) algorithms accepted without reviewExponential degradation at scaleDemand O(n) or O(log n); use Set/Map lookups instead of nested iterations
Linear CSS transitions approvedMechanical, lifeless UI that violates design principlesApply physics-based cubic-bezier or spring easing curves
Verbose prompts not compressedWasted tokens, poor signal-to-noise ratioApply Shannon compression — remove redundancy, dedupe, minimise
Blocking operations in async codeThread starvation, degraded responsivenessUse async/parallel design patterns per Von Neumann principles
Skipping the Proof step before codingUnvalidated assumptions baked into implementationState the mathematical model (complexity, architecture, easing, compression) first

Checklist

  • Turing: Time complexity verified as O(n log n) or better
  • Von Neumann: Architecture checked for async execution and Nash equilibrium
  • Bezier: All animation curves use physics-based easing (no linear timing)
  • Shannon: Data payloads and prompts compressed to maximum signal density
  • Proof step completed before implementation began
  • Council Review checklist verified post-implementation

Remember: These are not guidelines. They are mathematical laws.

平台分布

Codex

33.49%
按下载量换算53

Claude

31.82%
按下载量换算50

Cursor

20.74%
按下载量换算33

Gemini CLI

10.27%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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