Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add beita6969/ScienceClaw --skill hypothesis-gengit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/hypothesis-gen)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/hypothesis-gen"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/hypothesis-gen/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.
<a href="https://agentmods.dev/skills/beita6969/scienceclaw/hypothesis-gen"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/hypothesis-gen.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.00732 |
| Opus 5 | $0.00019 | $0.00366 |
| Sonnet 5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
hypothesis-gen 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Generation Skill
Structured workflow for generating testable scientific hypotheses.
When to Use
- "Generate hypotheses for this research question"
- "What could explain this observation?"
- "Propose testable ideas based on this data"
- "Help me formulate H0 and H1"
- "What hypotheses does this gap suggest?"
When NOT to Use
- Testing/verifying hypotheses (use scienceclaw-verification)
- Designing experiments (use experimental-design)
- Literature searching (use literature-search)
- Writing full papers (use paper-writing)
Generation Workflow
Step 1: Observe
Identify the phenomenon, anomaly, or gap:
- What was observed?
- What is unexpected or unexplained?
- What contradicts existing theory?
- What data pattern needs explanation?
Step 2: Contextualize
Ground in existing literature:
- What do current theories predict?
- What related findings exist?
- Where are the knowledge gaps?
- What alternative explanations exist?
Step 3: Formulate
State the hypothesis formally:
Template: "If [independent variable/condition], then [predicted effect on dependent variable], because [proposed mechanism]."
Null Hypothesis (H0): No effect / no difference / no relationship Alternative Hypothesis (H1): The predicted effect exists Directional: Specify direction (increase/decrease) when justified
Step 4: Evaluate
Score each hypothesis on:
| Criterion | Score (1-5) | Description |
|---|---|---|
| Testability | _ | Can be experimentally tested? |
| Falsifiability | _ | Can be proven wrong? |
| Novelty | _ | How new is this idea? |
| Mechanism | _ | Is the proposed mechanism plausible? |
| Feasibility | _ | Can current methods test it? |
| Impact | _ | How significant if confirmed? |
Step 5: Prioritize
Rank hypotheses by:
- Total evaluation score
- Risk-reward ratio (impact / feasibility)
- Alignment with available resources
- Potential for publication
Output Format
## Hypothesis [N]: [Short title]
**Statement**: If [condition], then [prediction], because [mechanism].
**H0**: [Null hypothesis]
**H1**: [Alternative hypothesis]
**Variables**:
- Independent: [variable]
- Dependent: [variable]
- Controls: [variables to hold constant]
**Evaluation**: Testability=[X] Falsifiability=[X] Novelty=[X] Mechanism=[X] Feasibility=[X] Impact=[X]
**Priority Score**: [Total/30]
**Key References**: [relevant citations]
**Suggested Test**: [brief experimental approach]
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 · 101 lines · 38 tokens per session scan A 21f2a23f4b5b
hypothesis-gen is a skill published in the GitHub repository beita6969/ScienceClaw (898 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 732 once invoked, about $0.0002 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.
Other skills, from other repositories
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.