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.
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.
curl -O https://raw.githubusercontent.com/aiming-lab/AutoResearchClaw/main/.claude/skills/hypothesis-formulation/SKILL.mdgit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWrote 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.
[](https://agentmods.dev/skills/aiming-lab/autoresearchclaw/hypothesis-formulation)<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
- Start with a clear observation or pattern that requires explanation
- Review existing literature for known mechanisms and prior explanations
- Identify what is already established vs. what remains uncertain
- Formulate the hypothesis as a specific, testable statement
- Ensure the hypothesis is falsifiable — define what outcome would refute it
Hypothesis Format
- Null hypothesis (H0): There is no effect or no difference
- Alternative hypothesis (H1): There is a specific, directional effect
- State both explicitly; design experiments to reject H0
- Use "If... then... because..." structure for mechanistic hypotheses:
- If [independent variable is manipulated], then [predicted outcome], because [proposed mechanism]
Generating Competing Hypotheses
- Propose at least 2-3 plausible explanations for the same observation
- For each, identify unique predictions that distinguish it from alternatives
- Rank hypotheses by parsimony, consistency with prior evidence, and testability
- Design experiments that can discriminate between competing hypotheses
- Consider confounding variables that could produce the same observation
Testable Predictions
- Derive specific, measurable predictions from each hypothesis
- Define expected effect direction AND approximate magnitude
- Specify what experimental conditions would confirm vs. refute the prediction
- Identify potential confounds and plan controls to address them
- Ensure predictions are achievable with available methods and resources
Aligning with Experimental Design
- Map each hypothesis to a concrete experimental condition or comparison
- Ensure sample size is adequate to detect the predicted effect (power analysis)
- Pre-register hypotheses and analysis plans when possible
- Distinguish confirmatory (hypothesis-testing) from exploratory analyses
- Plan for both positive and null results — what will you conclude in each case?
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.
- 8d ago First seen · 50 lines · 27 tokens per session scan A 9f8f83a882b5
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.
Other skills, from other repositories
aclawdemy
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
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.
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).
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…
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…
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 …