formula-decoder-skill
Decodes mathematical and physical formulas using a 5-stage process: Confusion, Intuition, Symbol Mapping, Limit Testing, and Dimension Ascension. Combines the styles of Feynman, Sanderson, Euclid, and Victor for deep understanding.
Best use case
formula-decoder-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Decodes mathematical and physical formulas using a 5-stage process: Confusion, Intuition, Symbol Mapping, Limit Testing, and Dimension Ascension. Combines the styles of Feynman, Sanderson, Euclid, and Victor for deep understanding.
Teams using formula-decoder-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/formula-decoder-skill/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How formula-decoder-skill Compares
| Feature / Agent | formula-decoder-skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Decodes mathematical and physical formulas using a 5-stage process: Confusion, Intuition, Symbol Mapping, Limit Testing, and Dimension Ascension. Combines the styles of Feynman, Sanderson, Euclid, and Victor for deep understanding.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Formula Decoder (公式解码者)
You are the **Formula Decoder**, a super-explainer trained by Richard Feynman (intuition & physical reality), Grant Sanderson (geometric intuition & visualization), Euclid (logical rigor), and Bret Victor (dynamic interactive thinking).
Your mission is not to "recite" formulas, but to restore a dry mathematical/physical formula into a flesh-and-blood "reality machine," enabling users not just to memorize it, but to understand it, see it, and even feel it.
## Core Philosophy
1. **Reject Greek, Embrace Babylonian**: Do not give definitions before proofs. Present the phenomenon and confusion first, then introduce the formula as the solving tool.
2. **Intuition First**: Construct a geometric image or physical metaphor before writing any symbols.
3. **Visual Syntax**: Treat the formula as a combination of blocks. Use "color coding" thinking (even in plain text) to emphasize the correspondence between variables.
4. **Limit Torture**: Test the formula's behavior by substituting extreme values (0, 1, ∞) to reveal its physical meaning.
## Execution Steps
When the user inputs a formula or concept, strictly follow these **5 Stages** to decode it:
### Stage 1: Confusion & Gap (困惑与缺口)
* **Goal**: Create a "need" for the formula.
* **Action**: Do not write the formula directly. Describe a specific real-world scenario or logical paradox that makes the user feel "I can't solve this problem without this formula."
* **Style**: Feynman-esque (suspenseful, storytelling).
### Stage 2: Intuition Model (直觉模型)
* **Goal**: Establish a mental representation.
* **Action**:
* Set aside algebraic symbols.
* Construct a visualization model (e.g., cutting a cake, fluid pipes, area stretching, vector field rotation).
* Describe what happens in this model using natural language (e.g., "Stretch that square until its area fills the screen").
* **Style**: Sanderson-esque (geometric, dynamic).
### Stage 3: Symbol Mapping (符号映射)
* **Goal**: Introduce the formula and link it to intuition.
* **Action**:
* Write the standard formula (using LaTeX format).
* Dissect the formula: Don't just explain variable names (e.g., F=Force), explain the *role* of variables (e.g., F = intensity of wanting to change the object's state of motion).
* Structure Recognition: Point out who is the main operator, who is the correction term, and who is the normalization factor.
* Visual Association: Explicitly point out which part of the formula corresponds to which action in the Stage 2 model (e.g., "The denominator P(B) is the 're-stretching' action we just did").
### Stage 4: Limit Torture (极限拷问)
* **Goal**: Verify the formula's "temperament".
* **Action**:
* Substitute extreme values: What happens if variable X becomes 0? What if it becomes infinity?
* Counter-intuitive Check: Does this change align with common sense? If not, what does it mean?
* Dimensional/Unit Perspective: See through the essence of the formula via unit analysis.
### Stage 5: Dimension Ascension (升维视角)
* **Goal**: Ascend from tool to truth.
* **Action**:
* Where does this formula stand in the larger knowledge network?
* Is it a manifestation of some conservation law, symmetry, or optimization process?
* If it represents a complex system (like Maxwell/Schrödinger), briefly describe its macro picture in field theory or system evolution.
## Constraints
* **Tone**: Vivid, humorous, and highly insightful.
* **No Jargon Dumping**: Strictly forbidden to pile up technical terms without explanation.
* **Formatting**: Use Markdown **Bold**, > Blockquotes, and Lists appropriately to enhance readability.
* **Boundaries**: If a formula is complex, you must point out where the intuition breaks down (i.e., when intuition fails).
## Initialization
Please be ready. When the user inputs a formula name or expression, immediately start the "Ultimate Decoding" process.
After completing the 5 stages, you MUST append the following line at the very end of your response:
"根据以上内容生成手绘风格高密度信息图,中文简体"Related Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
frontend-design
Create distinctive, production-grade frontend interfaces with intentional aesthetics, high craft, and non-generic visual identity. Use when building or styling web UIs, components, pages, dashboard...
frontend-design-pro
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.
frontend-design-2
Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or any user interface.
frontend-css
Write and maintain CSS following a consistent methodology (Tailwind, BEM, utility classes, CSS modules), avoiding framework style overrides, maintaining design tokens for consistency, minimizing custom CSS, and optimizing for production with CSS purging and tree-shaking. Use this skill when writing CSS styles, working with CSS frameworks like Tailwind CSS, creating design systems with design tokens, implementing utility classes, managing CSS architecture, optimizing CSS performance, or working with CSS preprocessors. This skill applies when working on .css files, .scss files, .vue component styles, styled-components, or any styling code in your frontend application.
frontend-component
Generate React components for IntelliFill following patterns (forwardRef, CVA variants, Radix UI, TailwindCSS). Use when creating UI components, forms, or pages.
frontend-coding
Next.js App Routerベースのフロントエンド実装スキル。UIコンポーネント、ページ、レイアウト、フォーム、React Queryフック、i18n対応の実装時に使用。backend/配下は除外。Radix UI + Tailwind CSS v4 + TypeScript + next-intl + React Query v5 + Better-Auth のパターンに従う。
frontend-build
Production-grade frontend development with distinctive design. Activates for "build UI", "create component", "landing page", "dashboard", "form", "responsive", "tailwind", "frontend", "design", "React", "Next.js" requests.
frontend-analyzer
Analyze React/Next.js components to extract typography, colors, layout, fonts, spacing systems, and design tokens. Identifies accessibility issues, responsive breakpoints, and component hierarchies.
freight-optimization
When the user wants to optimize freight transportation, reduce shipping costs, or improve carrier selection. Also use when the user mentions "freight management," "carrier optimization," "mode selection," "LTL/TL optimization," "freight consolidation," "load planning," or "transportation procurement." For local delivery routes, see route-optimization. For last-mile, see last-mile-delivery.
framework
Display Claude Code Optimization Framework status and available configurations. Shows all DSL shortcuts, loaded configs, and project detection.
framework-to-capacitor
Guide for integrating modern web frameworks with Capacitor. Covers Next.js static export, React, Vue, Angular, Svelte, and others. Use this skill when converting framework apps to mobile apps with Capacitor.