research-refine

research-refine is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 101 tokens per session (7,773 once invoked), scanned A, original, MIT.

A research-planning guide that turns a broad research idea into a specific method and a small validation plan.

In plain words
What is it for?
Use it to refine research ideas, break down technical problems, and create an implementation-oriented method plan.
Why use it?
It helps when the research question is clear but the technical approach is still vague or overloaded.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - **[Output Versioning Protocol](../shared-references/output-versioning.md)** — write timestamped file first, then copy to fixed name.

Good fit Use it to refine research ideas, break down technical problems, and create an implementation-oriented method plan.

Compare 6 skills from other repositories ↓
About the project

ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.

wanshuiyin/Auto-claude-code-research-in-sleep · 15,970 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
agentmods
npx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for research-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/research-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 13 May 2026
  • Snyk warn 13 May 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 106
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • medium Excessive Agency · line 732
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.07773
Opus 5 $0.00051 $0.03887
Sonnet 5 $0.00020 $0.01555
Haiku 4.5 $0.00010 $0.00777

Measured 4d ago against content hash 2888a5d78cce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/research-refine/SKILL.md · 771 lines

How it starts

The opening of the file, as written. The whole thing — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement

Refine and concretize: $ARGUMENTS

Overview

Use this skill when the research problem is already visible but the technical route is still fuzzy. The goal is not to produce a bloated proposal or a benchmark shopping list. The goal is to turn a vague direction into a problem -> focused method -> minimal validation document that is concrete enough to implement, elegant enough to feel paper-worthy, and current enough to resonate in the foundation-model era.

Four principles dominate this skill:

  1. Do not lose the original problem. Freeze an immutable Problem Anchor and reuse it in every round.
  2. The smallest adequate mechanism wins. Prefer the minimal intervention that directly fixes the bottleneck.
  3. One paper, one dominant contribution. Prefer one sharp thesis plus at most one supporting contribution.
  4. Modern leverage is a prior, not a decoration. When LLM / VLM / Diffusion / RL / distillation / inference-time scaling naturally fit the bottleneck, use them concretely. Do not bolt them on as buzzwords.
User input (PROBLEM + vague APPROACH)
  -> Phase 0 (Claude): Freeze Problem Anchor
  -> Phase 1 (Claude): Scan grounding papers -> identify technical gap -> choose the sharpest route -> write focused proposal
  -> Phase 2 (Codex/GPT-6-Astra): Review for fidelity, specificity, contribution quality, and frontier leverage
  -> Phase 3 (Claude): Anchor check + simplicity check -> revise method -> rewrite full proposal
  -> Phase 4 (Codex, same thread): Re-evaluate revised proposal
  -> Repeat Phase 3-4 until OVERALL SCORE >= 9 or MAX_ROUNDS reached
  -> Phase 5: Save full history to refine-logs/
  -> Optional handoff: /experiment-plan for a detailed execution-ready experiment roadmap

Constants

  • REVIEWER_MODEL = gpt-6-astra — Reviewer model used via Codex MCP.
  • MAX_ROUNDS = 5 — Maximum review-revise rounds.
  • SCORE_THRESHOLD = 9 — Minimum overall score to stop.
  • OUTPUT_DIR = refine-logs/ — Directory for round files and final report.
  • MAX_LOCAL_PAPERS = 15 — Maximum local papers/notes to scan for grounding.
  • MAX_CORE_EXPERIMENTS = 3 — Default cap for core validation blocks inside this skill.
  • MAX_PRIMARY_CLAIMS = 2 — Soft cap for paper-level claims. Prefer one dominant claim plus one supporting claim.
  • MAX_NEW_TRAINABLE_COMPONENTS = 2 — Soft cap for genuinely new trainable pieces. Exceed only if the paper breaks otherwise.

Read the full file on GitHub · 771 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago Changed · -2 tokens per session 2888a5d78cce
  2. 8d ago First seen · 771 lines · 103 tokens per session scan A 2cbda5055760

Subscribe to this mod's changes

research-refine is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 7,773 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

figure-style

Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…

aipoch/open-science · 91 tokens

remote-compute-ssh

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.

aipoch/open-science · 53 tokens

ligandmpnn

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…

aipoch/open-science · 100 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens

memory

Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.

Muuuun/luxas · 30 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens