Hypothesis
Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
npx -y skills add richard-kim-79/archora-skills --skill hypothesisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Generates falsifiable, testable research hypotheses from notes, documents, and research content. Use when the user asks to brainstorm hypotheses, generate research questions, identify testable predictions, or discover patterns across their notes. Do NOT use for general Q&A — only when structured hypothesis output is needed.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.5 KB, as published. Nobody here has run it
Hypothesis Generation
Generate falsifiable, testable research hypotheses from the user's notes and research content.
Workflow
- Read available content — scan the notes, documents, or files the user provides
- Identify themes — find recurring concepts, claims, relationships, and open questions
- Generate hypotheses — produce 4–6 specific, falsifiable hypotheses
- Assign confidence — rate each hypothesis HIGH / MEDIUM / LOW based on evidence in the content
- Format output — present in structured markdown
Output Format
# 🧪 Hypothesis Analysis
## Summary
[2–3 sentences describing the main themes and what the hypotheses cover]
## Generated Hypotheses
### 🔴 [Hypothesis Title] — HIGH confidence
**Hypothesis:** [Specific, falsifiable statement with measurable prediction]
**Rationale:** [Which sources/notes support this, with specific references]
**Testable:** Yes | **Confidence:** HIGH
---
### 🟡 [Hypothesis Title] — MEDIUM confidence
...
Confidence levels
- 🔴 HIGH — directly supported by multiple sources in the content
- 🟡 MEDIUM — partially supported or requires inference across sources
- 🟢 LOW — speculative but worth investigating; limited direct support
Quality criteria for good hypotheses
- Falsifiable: Can be proven wrong — avoid "X may affect Y"
- Specific: Mentions measurable variables, not vague concepts
- Grounded: Traceable to actual content provided, not general knowledge
- Novel: Connects ideas across sources rather than restating the obvious
Example
Input: Notes on predictive coding and synaptic plasticity
Good hypothesis:
"Precision-weighted prediction errors in the Rao and Ballard model are encoded through spike-timing-dependent plasticity (STDP) in the visual cortex, such that altering STDP timing windows disrupts receptive field formation."
Poor hypothesis:
"Synaptic plasticity is important for learning." ← not falsifiable, too vague