ablation-planner

by wanshuiyin 15k MIT Updated Aug 18, 2026
ablation-planner skill by wanshuiyin
ablation-planner — Data skill by wanshuiyin

ablation-planner is an open-source data skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/ablation-planner`.

What ablation-planner does

Systematically design ablation studies that answer the questions reviewers will ask. Codex leads the design (reviewer perspective), CC reviews feasibility and implements.

Installation

Add ablation-planner to your agent with:

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/ablation-planner

Always review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.

What's inside

The SKILL.md for ablation-planner is organised into these sections:

  • Context: $ARGUMENTS
  • When to Use
  • Workflow
  • Step 1: Prepare Context
  • Step 2: Codex Designs Ablations
  • Step 3: Parse Ablation Plan
  • Step 4: CC Reviews Feasibility
  • Step 5: Implement and Run
  • Rules

When to use it

Reach for ablation-planner when you want data help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.

Strengths

  • Clear MIT license — safe to read and adapt
  • Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
  • Actively maintained (recent commits)

Topics

ai-researchai-toolsarisautonomous-agentclaudeclaude-codeclaude-code-skillscodexdeep-learninggptidea-generationllmmachine-learningmcpmcp-serverml-researchopenaipaper-reviewpaper-writingresearch-automation

Frequently asked questions

What does ablation-planner do?
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
How do I install ablation-planner?
Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/ablation-planner in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
Is ablation-planner free to use?
Yes. ablation-planner is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
Where does ablation-planner come from?
ablation-planner ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.

Related skills

More Data →

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.

15k wanshuiyin MIT

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

15k wanshuiyin MIT

Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.

15k wanshuiyin MIT

Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.

15k wanshuiyin MIT

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".

15k wanshuiyin MIT