Develops intuition for what makes research "good" versus "incremental." Use when asked about research taste, how to identify good research, what makes a paper impactful, how to develop research intuition, or how to pick important problems. Analyzes patterns in highly-cited work and what top researchers do differently.
/plugin marketplace add GhostScientist/skills/plugin install writing-skills@GhostScientist-skillsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Research taste is the ability to distinguish work that matters from work that doesn't - before the community tells you. This skill helps you develop that instinct.
It's the intuition that lets experienced researchers:
Taste isn't magic - it's pattern recognition from deep exposure. This skill accelerates that exposure.
Pick a specific subfield. We'll study what "good" looks like there.
Questions to investigate:
For each landmark paper, analyze:
Look for what the great papers have in common:
The Patterns of Impact:
Papers that introduce a building block others build on.
Papers that link two previously separate areas.
Papers showing that scale changes qualitative behavior.
Papers that formalize what was previously folklore.
Papers that solve a problem far more simply than expected.
Learn to recognize work that won't age well:
The Incremental Treadmill:
The Method Mashing:
The Benchmark Overfitter:
The Complexity Monster:
The Solution Without a Problem:
Exercise 1: Prediction Game Before reading a paper, predict based on title/abstract:
Exercise 2: Explain the Gap For any two papers in citation count:
Exercise 3: The Time Machine Pick a highly-cited paper. Go back to when it was published:
Exercise 4: Design a Hit Given current state of a field:
What top researchers seem to do differently:
Problem Selection:
Execution Taste:
Communication Taste:
Portfolio Taste:
# Research Taste Analysis: [Field/Subfield]
## Landmark Paper Analysis
### [Paper 1 Title] ([Year])
- **Pre-existing state:** [What was true before]
- **Core insight:** [One sentence]
- **Why it's cited:** [Specific reason]
- **Pattern type:** [New Primitive / Connection / etc.]
### [Paper 2 Title]
[Same structure]
## Pattern Distribution
In this subfield, highly-cited papers tend to be:
- [X]% New Primitives
- [Y]% Surprising Connections
- [Z]% Other
## Anti-Pattern Warnings
The following patterns are common but don't lead to impact:
1. [Anti-pattern common in this field]
2. [Another one]
## Taste Heuristics for [Field]
When evaluating a paper in this field, ask:
1. [Field-specific question that distinguishes good from meh]
2. [Another one]
3. [Another one]
## Current Opportunities
Based on this analysis, promising directions seem to be:
1. [Direction 1]: [Why it's ripe]
2. [Direction 2]: [Why it's ripe]
## Your Taste Development Exercises
1. [Specific exercise for this field]
2. [Another one]
You have good taste when:
This takes years. But deliberate practice - not just reading, but analyzing - accelerates it dramatically.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.