AutoResearchClaw: Skill for Claude Code

.claude/skills/hypothesis-formulation/SKILL.md

hypothesis-formulation is a skill for Claude Code from aiming-lab/AutoResearchClaw. It costs 27 tokens per session (521 once invoked), scanned A, original, MIT.

A structured method for forming scientific hypotheses from observations. A hypothesis is a testable explanation, and the method also covers null hypotheses, competing explanations, and predictions.

In plain words
What is it for?
It is for writing testable hypotheses, comparing alternative explanations, identifying confounding factors, and designing experiments that distinguish between them.
Why use it?
It helps separate known facts from uncertainty and makes proposed explanations specific enough to test or disprove.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is aiming-lab/AutoResearchClaw's own configuration. It tells Claude Code how to work on AutoResearchClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AutoResearchClaw configures →

About the project

AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.

aiming-lab/AutoResearchClaw · 14,352 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to aiming-lab/AutoResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aiming-lab/AutoResearchClaw/main/.claude/skills/hypothesis-formulation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw

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 hypothesis-formulation

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/hypothesis-formulation.svg)](https://agentmods.dev/skills/aiming-lab/autoresearchclaw/hypothesis-formulation)
Your own site
<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/hypothesis-formulation"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/hypothesis-formulation.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 521 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
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00027 $0.00521
Opus 5 $0.00014 $0.00260
Sonnet 5 $0.00005 $0.00104
Haiku 4.5 $0.00003 $0.00052

Measured 8d ago against content hash 9f8f83a882b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hypothesis-formulation 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 8d 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.

.claude/skills/hypothesis-formulation/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hypothesis Formulation Best Practice

Structured Hypothesis Development

  1. Start with a clear observation or pattern that requires explanation
  2. Review existing literature for known mechanisms and prior explanations
  3. Identify what is already established vs. what remains uncertain
  4. Formulate the hypothesis as a specific, testable statement
  5. Ensure the hypothesis is falsifiable — define what outcome would refute it

Hypothesis Format

  1. Null hypothesis (H0): There is no effect or no difference
  2. Alternative hypothesis (H1): There is a specific, directional effect
  3. State both explicitly; design experiments to reject H0
  4. Use "If... then... because..." structure for mechanistic hypotheses:
    • If [independent variable is manipulated], then [predicted outcome], because [proposed mechanism]

Generating Competing Hypotheses

  1. Propose at least 2-3 plausible explanations for the same observation
  2. For each, identify unique predictions that distinguish it from alternatives
  3. Rank hypotheses by parsimony, consistency with prior evidence, and testability
  4. Design experiments that can discriminate between competing hypotheses
  5. Consider confounding variables that could produce the same observation

Testable Predictions

  1. Derive specific, measurable predictions from each hypothesis
  2. Define expected effect direction AND approximate magnitude
  3. Specify what experimental conditions would confirm vs. refute the prediction
  4. Identify potential confounds and plan controls to address them
  5. Ensure predictions are achievable with available methods and resources

Aligning with Experimental Design

  1. Map each hypothesis to a concrete experimental condition or comparison
  2. Ensure sample size is adequate to detect the predicted effect (power analysis)
  3. Pre-register hypotheses and analysis plans when possible
  4. Distinguish confirmatory (hypothesis-testing) from exploratory analyses
  5. Plan for both positive and null results — what will you conclude in each case?

Read the full file on GitHub · 50 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. 8d ago First seen · 50 lines · 27 tokens per session scan A 9f8f83a882b5

Subscribe to this mod's changes

hypothesis-formulation is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,352 stars, last pushed 19d ago), licensed MIT. It adds 27 tokens to every session and 521 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

aclawdemy

The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.

LeoYeAI/openclaw-master-skills · 30 tokens

adme-property-predictor

Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.

LeoYeAI/openclaw-master-skills · 61 tokens

arxiv-summarizer-orchestrator

End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).

InternLM/WildClawBench · 75 tokens

baseline-comparison-audit

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…

wanshuiyin/Anti-Autoresearch · 310 tokens

eval-design-forensics

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…

wanshuiyin/Anti-Autoresearch · 458 tokens

proof-derivation-forensics

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …

wanshuiyin/Anti-Autoresearch · 222 tokens