ablation-planner SKILL.md skillA

ablation-planner from wanshuiyin/auto-claude-code-research-in-sleep is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wanshuiyin/auto-claude-code-research-in-sleep/ablation-planner@git:20260906.0472e53

Pins git:20260906.0472e53 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wanshuiyin/auto-claude-code-research-in-sleep
Path
skills/skills-codex/ablation-planner/SKILL.md
Versions recorded
5
Latest version
git:20260906.0472e53, committed Sep 6, 2026
First version recorded
May 13, 2026
Size
5,416 bytes
Repository stars
18,383
License
MIT

Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Ablation Planner

Systematically design ablation studies that answer the questions reviewers will ask. The reviewer agent leads the design; the local executor reviews feasibility and implements.

## Context: $ARGUMENTS

## When to Use

- Main results pass `/result-to-claim` with `claim_supported = yes` or `partial`
- The user explicitly requests ablation planning
- `/auto-review-loop` identifies missing ablations

## Workflow

### Step 1: Prepare Context

Read available project files to build the full picture:

- Method description and components (from `idea-stage/docs/research_contract.md`, legacy `docs/research_contract.md`, project notes, or method docs)
- Current experiment results (from `EXPERIMENT_LOG.md`, `EXPERIMENT_TRACKER.md`, or W&B)
- Confirmed and intended claims (from `/result-to-claim` output or project notes)
- Available compute resources (from server notes, run configs, or user-provided budget)

### Step 2: Codex Designs Ablations

```text
spawn_agent:
  model: gpt-6-astra
  reasoning_effort: xhigh
  message: |
    You are a rigorous ML reviewer planning ablation studies.
    Given this method and results, design ablations that:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wanshuiyin/auto-claude-code-research-in-sleep/ablation-planner@sha256:8383bc55d53adb29

The line at the top of this page pins the label git:20260906.0472e53, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_l6dsxzfias4cblqw.svg)](https://markdownregistry.com/a/art_l6dsxzfias4cblqw)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 13, 2026 and Sep 6, 2026, about one every 29 days.

versioncommittedcommitsizeaudit
git:20260906.0472e53 latest2026-09-06 0472e53 5,416 BA view · diff
git:20260710.61427152026-07-10 6142715 5,416 BA view · diff
git:20260702.2cf71bf2026-07-02 2cf71bf 5,412 BA view · diff
git:20260529.e5132632026-05-29 e513263 5,365 BA view · diff
git:20260513.d43d77a2026-05-13 d43d77a 5,372 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5416 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wanshuiyin/auto-claude-code-research-in-sleep · 18,383 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_l6dsxzfias4cblqw
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/auto-claude-code-research-in-sleep/ablation-planner
GET https://markdownregistry.com/api/v1/blob/8383bc55d53adb29a36e07cc7da560337ddb32140e268fe737d4c36f94110e7b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wanshuiyin/auto-claude-code-research-in-sleep

ablation-planner SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper…
git:20260906.0472e53 · audit A · 18,383 stars
alphaxiv SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/alphaxiv/SKILL.md · Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain…
git:20260929.2132036 · audit A · 18,383 stars
analyze-results SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/analyze-results/SKILL.md · Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze…
git:20260713.e67ae16 · audit A · 18,383 stars
arxiv SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/arxiv/SKILL.md · Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch…
git:20260714.3c58cac · audit A · 18,383 stars
auto-paper-improvement-loop SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/auto-paper-improvement-loop/SKILL.md · Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use…
git:20261031.d419560 · audit A · 18,383 stars
auto-review-loop-llm SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/auto-review-loop-llm/SKILL.md · Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment…
git:20260713.e67ae16 · audit A · 18,383 stars
auto-review-loop-minimax SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/auto-review-loop-minimax/SKILL.md · Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP…
git:20260713.e67ae16 · audit A · 18,383 stars
auto-review-loop SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/auto-review-loop/SKILL.md · Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck…
git:20261024.f455879 · audit A · 18,383 stars
citation-audit SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/citation-audit/SKILL.md · Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a…
git:20261019.8fdc2d5 · audit A · 18,383 stars
citation-crosscheck SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/citation-crosscheck/SKILL.md · Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second…
git:20261019.19105bb · audit A · 18,383 stars
claims-drafting SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/claims-drafting/SKILL.md · Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants…
git:20261019.8fdc2d5 · audit A · 18,383 stars
comm-lit-review SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/comm-lit-review/SKILL.md · Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about…
git:20260702.5d6e40a · audit A · 18,383 stars

Every file in wanshuiyin/auto-claude-code-research-in-sleep

Other files named ablation-planner

ablation-planner SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper…
git:20260906.0472e53 · audit A · 18,383 stars
ablation-planner SKILL.md skill
autoconference/autoconference-skill · skills/aris/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper…
git:20260924.6751570 · audit A · 13 stars
ablation-planner SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed to answer…
git:20260927.a059f3a · audit A · 12 stars

Browse by kind, by grade A, or by owner.