Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.
Guides you through implementing research papers step-by-step from scratch with checkpoint questions.
/plugin marketplace add GhostScientist/skills/plugin install ghostscientist-documentation-skills@GhostScientist/skillsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
The best way to truly understand a paper is to implement it. This skill guides you through that process methodically.
Before writing any code:
Identify the core algorithm - Strip away ablations, extensions, bells and whistles. What's the minimal version?
List the components - Break into modules:
Find the tricky parts - What's non-obvious?
Gather reference numbers - What should we expect?
Build up the implementation in this order:
# Start with synthetic/toy data
# Verify shapes and types before touching real data
Checkpoint: Can you describe what each tensor represents and its expected shape?
# Build layer by layer
# Print shapes at each stage
# Verify parameter counts match paper
Checkpoint: If you randomly initialize and do a forward pass, do the output shapes match what the paper describes?
# Implement exactly as described
# Test with known inputs/outputs
# Check gradient flow
Checkpoint: Can you explain each term in the loss and why it's there?
# Minimal loop first (no logging, checkpointing, etc.)
# Verify loss decreases on tiny overfit test
# Then add bells and whistles
Checkpoint: Can you overfit a single batch? If not, something is broken.
# Implement paper's exact metrics
# Compare against reported numbers
Checkpoint: On the same data split, how close are you to paper's numbers?
When it doesn't work (and it won't at first):
The Overfit Test
The Gradient Check
The Initialization Check
The Learning Rate Sweep
The Ablation Debug
At each stage, you should be able to answer:
Understanding:
Implementation:
Debugging:
For each implementation session, provide:
## Today's Implementation Goal
[Specific component we're building]
## Prerequisites Check
- [ ] Previous components working
- [ ] Understand what we're building
- [ ] Know expected behavior
## Implementation
### Code
[Code blocks with extensive comments]
### Checkpoint Questions
1. [Question]
<details><summary>Answer</summary>[Answer]</details>
2. [Question]
<details><summary>Answer</summary>[Answer]</details>
### Verification Steps
- [ ] Test 1: [What to check]
- [ ] Test 2: [What to check]
### Common Bugs at This Stage
1. [Bug pattern]: [How to identify and fix]
## What's Next
[Preview of next component and how it connects]
You're done when:
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.