Experiment Design
lingzhi227/agent-research-skillsPlanning experiments for a research paper can be hard. This skill breaks the work into four clear stages. You start with a basic working implementation. Then you tune the settings to get better results. Next you explore creative new ideas. Finally you run ablation studies to test each part of your method.
Each stage builds on the last one. You use simple datasets first and add more later. The skill helps you choose baselines, datasets, and metrics. It also sets up hyperparameter sweeps. This keeps your experiments organized and saves time.
Anyone writing a research paper can use this plan. It works for machine learning and other scientific fields. The structured approach makes sure you do not skip important steps.
Add Experiment Design skill to your workflow
Global
mkdir -p ~/.claude/skills/experiment-designProject
mkdir -p .claude/skills/experiment-designSource Repository
More Research & Knowledge Management Claude Code Skills
Lark Baselarksuite/cli
Simplify your Lark Base data with tables, fields, records, and views
Lark Wikilarksuite/cli
Manage your Lark Wiki spaces, members, and documents with simple commands
Grillingmattpocock/skills
Test your plan thoroughly with clear step-by-step interview questions
Analyze Projectlllllllama/rigorpilot-skills
Safe read-only analysis of deep learning repos for understanding and risk detection
Ai Research Reproductionlllllllama/rigorpilot-skills
Faithful reproduction of deep learning research with auditable steps and minimal changes
Repo Intake And Planlllllllama/rigorpilot-skills
Scan a repo, find commands, and get a simple reproduction plan
Minimal Run And Auditlllllllama/rigorpilot-skills
Capture evidence from deep learning runs and create standardized audit reports
Obsidian Vaultmattpocock/skills
Search create and organize notes with wikilinks and index notes easily