claude-scientific-writer: Skill for Claude Code

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

hypothesis-generation is a skill for Claude Code from K-Dense-AI/claude-scientific-writer. It costs 58 tokens per session (2,916 once invoked), scanned A, a copy of hypothesis-generation, MIT.

A research-planning guide for turning an observation into testable explanations, predictions, measurements, and a preregistration-ready analysis plan. It keeps hypotheses separate from established findings, diagnoses, or recommendations.

In plain words
What is it for?
Use it to frame scientific questions, compare rival explanations, choose ways to distinguish them, and plan analyses before collecting or examining data.
Why use it?
It helps prevent guesses, associations, and model outputs from being presented as proven causes or facts. It also highlights when unpublished, sensitive, or regulated material needs authorization and human review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is K-Dense-AI/claude-scientific-writer's own configuration. It tells Claude Code how to work on claude-scientific-writer 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 claude-scientific-writer configures →

About the project

Claude Scientific Writer is an AI-assisted research and writing tool that searches literature and produces documents such as scientific papers, reports, posters, grant proposals, and reviews with citations. Researchers and technical writers can use it as a Claude Code plugin, Python package, or command-line tool, with the catalogue entries defining agent workflows for it.

K-Dense-AI/claude-scientific-writer · 2,324 stars · on GitHub · k-dense.ai

Reuse

Borrowing it

Nothing to install: this file belongs to K-Dense-AI/claude-scientific-writer. 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/K-Dense-AI/claude-scientific-writer/main/.claude/skills/hypothesis-generation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/claude-scientific-writer

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-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation/github.svg)](https://agentmods.dev/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation)
Your own site
<a href="https://agentmods.dev/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation"><img src="https://agentmods.dev/badge/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation/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 hypothesis-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation"><img src="https://agentmods.dev/badge/skills/k-dense-ai/claude-scientific-writer/hypothesis-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,916 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.
Origin 100% copy Near-identical to another mod 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 $0.00058 $0.02916
Opus 5 $0.00029 $0.01458
Sonnet 5 $0.00012 $0.00583
Haiku 4.5 $0.00006 $0.00292

Measured 11d ago against content hash 039881416522, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hypothesis-generation 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 11d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/_common.py, scripts/audit_evidence_ledger.py, scripts/check_falsification_controls.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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

This is a copy

100% identical to hypothesis-generation — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/hypothesis-generation/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Hypothesis Generation

Turn an observation into a transparent set of candidate explanations and tests. A hypothesis is a proposal to be challenged, not a finding, fact, diagnosis, or recommendation.

Non-negotiable boundaries

Before using unpublished, sensitive, controlled, personal, proprietary, export-controlled, or security-relevant material:

  1. Confirm authorization and the applicable institutional, funder, publisher, data-use, privacy, and AI policies.
  2. Keep the material local unless an authorized human explicitly approves a named external destination and data scope.
  3. Minimize inputs. Do not place sensitive or unpublished data in web searches or external AI systems without authorization.
  4. Stop at the appropriate human, animal, biosafety, dual-use, data-governance, or regulatory gate.

Never:

  • present a hypothesis, mechanism, causal effect, citation, or apparent pattern as established evidence;
  • claim novelty because a quick search found nothing;
  • infer causation from association, temporal order alone, predictive accuracy, or model output;
  • supply patient-specific diagnosis, treatment, dose, prognosis, or other clinical advice;
  • provide harmful experimental optimization or operational detail for pathogens, toxins, weapons, evasion, or other misuse;
  • bypass IRB/REC, IACUC, IBC, biosafety, dual-use, privacy, legal, or regulatory review;
  • fabricate sources, identifiers, search coverage, data, results, approvals, or preregistration;
  • automatically score, rank, select, accept, or reject scientific hypotheses.

If a request crosses a safety gate, produce only a high-level risk/oversight note and route it to the qualified local authority. Do not continue with operational detail.

Keep the objects distinct

Object Meaning
Observation What was measured, noticed, or reported, with provenance and uncertainty
Research question The answerable question that defines scope
Hypothesis A candidate explanatory or relational proposition
Mechanism The proposed process connecting conditions to an outcome
Causal estimand The precisely defined causal contrast to estimate
Prediction An observable implication derived before checking the target result
Alternative explanation A rival account, including bias or non-causal explanations
Null hypothesis A specified no-effect/no-difference model used by an analysis
Negative control A control expected not to operate through the proposed mechanism
Operationalization How a construct becomes a variable, measurement, intervention, or category
Analysis plan Prespecified transformations, models, contrasts, uncertainty, and decision rules
Evidence Observations or sources that bear on a claim; never the claim itself

Read the full file on GitHub · 265 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. 11d ago First seen · 265 lines · 58 tokens per session scan A 039881416522

Subscribe to this mod's changes

hypothesis-generation is a skill published in the GitHub repository K-Dense-AI/claude-scientific-writer (2,324 stars, last pushed 23d ago), licensed MIT. It adds 58 tokens to every session and 2,916 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hypothesis-generation, differing in 19 lines, and is treated as a copy.

Related

Other skills, from other repositories

health-nutrition-expert

Apply cutting-edge 2025 nutrition science on longevity, metabolic health, gut microbiome, and evidence-based dietary patterns for optimal vitality and disease prevention. Use when planning a diet, evaluating a nutrition claim, or applying evidence-based guidance on longevity, metabolic, and gut health.

frankxai/claude-skills-library · 62 tokens

tabpfn-regress

Run a TabPFN regression baseline, generate the first submission, then optimize with GBT ensembles and regression-specific post-processing (clipping, target transforms, rank blending). Use after tabpfn-explore has prepared the data and CV folds.

dianaprior/kaggle-competition-agent-skill · 55 tokens

tabpfn-explore

EDA, data profiling, adversarial validation, preprocessing checks, CV scheme setup, and API budget verification for tabular Kaggle competitions. Run at the start of every new competition before any modeling.

dianaprior/kaggle-competition-agent-skill · 45 tokens

drug-discovery

Drug discovery: ChEMBL search, drug-likeness, interactions.

NousResearch/hermes-agent · 19 tokens

aaai-experiments

Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.

brycewang-stanford/Awesome-Journal-Skills · 66 tokens

acl-experiments

Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…

brycewang-stanford/Awesome-Journal-Skills · 59 tokens