cs-research-methodology
CS Research Methodology
Framework for investigating problems by identifying assumptions and proposing alternatives.
Core Concept: The Bit Flip
Every research contribution follows this pattern:
- The Bit: What does everyone assume?
- The Flip: What's the alternative?
- The Proof: Why does the alternative work better?
Investigation Process
Step 1: Identify the Bit
What do existing approaches take for granted?
- What do all solutions have in common?
- What's implicit in how the problem is framed?
More from sundial-org/skills
icml-reviewer
|
82training-data-curation
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
58ai-co-scientist
Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".
54tinker
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.
53project-referee
Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identify weaknesses, check claim-evidence gaps, or find missing citations.
51commit-splitter
Split large sets of uncommitted changes into logical, well-organized commits. Use when the user has many uncommitted changes and wants structured commits, or proactively suggest when detecting a large diff that would benefit from splitting.
49