[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M716618J5EDTN4RW41JZ4W4Z":3,"skill-same:01M716618J5EDTN4RW41JZ4W4Z":131},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":34,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":73,"commitSha":74,"skillDirectory":75,"forksCount":14,"repositoryHtmlUrl":76,"repositoryHomepageUrl":6,"ownerHtmlUrl":77,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":78,"install":79,"resources":92},"01M716618J5EDTN4RW41JZ4W4Z","hypothesis-generation",null,"Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.","fadrienne\u002FMyGitHub","fadrienne","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197874571?v=4","01M6X64V8VWCRSMFZ4EPS2BWXG","Francesca Adrienne","01M6X64VD5MW4F9PHDWQKS7ZAF",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"hypothesis","hypothesis generation","generation","write","when","hypothesis formulation","features","you","scientific","predictions","false","edit","testing","read","openrouter","Bash","open","api","data","design","2026-11-10 10:12:30",false,"---\nname: hypothesis-generation\ndescription: Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.\nallowed-tools: Read Write Edit Bash\nlicense: MIT license\nrequired_environment_variables: [{\"name\": \"OPENROUTER_API_KEY\", \"prompt\": \"OpenRouter API key for the skill's LLM-powered steps.\", \"required_for\": \"optional features\"}]\nmetadata: {\"version\": \"1.1\", \"skill-author\": \"K-Dense Inc.\", \"openclaw\": {\"primaryEnv\": \"OPENROUTER_API_KEY\", \"envVars\": [{\"name\": \"OPENROUTER_API_KEY\", \"required\": false, \"description\": \"OpenRouter API key for the skill's LLM-powered steps.\"}]}}\n---\n\n# Scientific Hypothesis Generation\n\n## Overview\n\nHypothesis generation is a systematic process for developing testable explanations. Formulate evidence-based hypotheses from observations, design experiments, explore competing explanations, and develop predictions. Apply this skill for scientific inquiry across domains.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Developing hypotheses from observations or preliminary data\n- Designing experiments to test scientific questions\n- Exploring competing explanations for phenomena\n- Formulating testable predictions for research\n- Conducting literature-based hypothesis generation\n- Planning mechanistic studies across scientific domains\n\n## Visual Enhancement with Scientific Schematics\n\n**⚠️ MANDATORY: Every hypothesis generation report MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.**\n\nThis is not optional. Hypothesis reports without visual elements are incomplete. Before finalizing any document:\n1. Generate at minimum ONE schematic or diagram (e.g., hypothesis framework showing competing explanations)\n2. Prefer 2-3 figures for comprehensive reports (mechanistic pathway, experimental design flowchart, prediction decision tree)\n\n**How to generate figures:**\n- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams\n- Simply describe your desired diagram in natural language\n- Nano Banana Pro will automatically generate, review, and refine the schematic\n\n**How to generate schematics:**\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o figures\u002Foutput.png\n```\n\nThe AI will automatically:\n- Create publication-quality images with proper formatting\n- Review and refine through multiple iterations\n- Ensure accessibility (colorblind-friendly, high contrast)\n- Save outputs in the figures\u002F directory\n\n**When to add schematics:**\n- Hypothesis framework diagrams showing competing explanations\n- Experimental design flowcharts\n- Mechanistic pathway diagrams\n- Prediction decision trees\n- Causal relationship diagrams\n- Theoretical model visualizations\n- Any complex concept that benefits from visualization\n\nFor detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.\n\n---\n\n## Workflow\n\nFollow this systematic process to generate robust scientific hypotheses:\n\n### 1. Understand the Phenomenon\n\nStart by clarifying the observation, question, or phenomenon that requires explanation:\n\n- Identify the core observation or pattern that needs explanation\n- Define the scope and boundaries of the phenomenon\n- Note any constraints or specific contexts\n- Clarify what is already known vs. what is uncertain\n- Identify the relevant scientific domain(s)\n\n### 2. Conduct Comprehensive Literature Search\n\nSearch existing scientific literature to ground hypotheses in current evidence. Use both PubMed (for biomedical topics) and general web search (for broader scientific domains):\n\n**For biomedical topics:**\n- Use WebFetch with PubMed URLs to access relevant literature\n- Search for recent reviews, meta-analyses, and primary research\n- Look for similar phenomena, related mechanisms, or analogous systems\n\n**For all scientific domains:**\n- Use WebSearch to find recent papers, preprints, and reviews\n- Search for established theories, mechanisms, or frameworks\n- Identify gaps in current understanding\n\n**Search strategy:**\n- Begin with broad searches to understand the landscape\n- Narrow to specific mechanisms, pathways, or theories\n- Look for contradictory findings or unresolved debates\n- Consult `references\u002Fliterature_search_strategies.md` for detailed search techniques\n\n### 3. Synthesize Existing Evidence\n\nAnalyze and integrate findings from literature search:\n\n- Summarize current understanding of the phenomenon\n- Identify established mechanisms or theories that may apply\n- Note conflicting evidence or alternative viewpoints\n- Recognize gaps, limitations, or unanswered questions\n- Identify analogies from related systems or domains\n\n### 4. Generate Competing Hypotheses\n\nDevelop 3-5 distinct hypotheses that could explain the phenomenon. Each hypothesis should:\n\n- Provide a mechanistic explanation (not just description)\n- Be distinguishable from other hypotheses\n- Draw on evidence from the literature synthesis\n- Consider different levels of explanation (molecular, cellular, systemic, population, etc.)\n\n**Strategies for generating hypotheses:**\n- Apply known mechanisms from analogous systems\n- Consider multiple causative pathways\n- Explore different scales of explanation\n- Question assumptions in existing explanations\n- Combine mechanisms in novel ways\n\n### 5. Evaluate Hypothesis Quality\n\nAssess each hypothesis against established quality criteria from `references\u002Fhypothesis_quality_criteria.md`:\n\n**Testability:** Can the hypothesis be empirically tested?\n**Falsifiability:** What observations would disprove it?\n**Parsimony:** Is it the simplest explanation that fits the evidence?\n**Explanatory Power:** How much of the phenomenon does it explain?\n**Scope:** What range of observations does it cover?\n**Consistency:** Does it align with established principles?\n**Novelty:** Does it offer new insights beyond existing explanations?\n\nExplicitly note the strengths and weaknesses of each hypothesis.\n\n### 6. Design Experimental Tests\n\nFor each viable hypothesis, propose specific experiments or studies to test it. Consult `references\u002Fexperimental_design_patterns.md` for common approaches:\n\n**Experimental design elements:**\n- What would be measured or observed?\n- What comparisons or controls are needed?\n- What methods or techniques would be used?\n- What sample sizes or statistical approaches are appropriate?\n- What are potential confounds and how to address them?\n\n**Consider multiple approaches:**\n- Laboratory experiments (in vitro, in vivo, computational)\n- Observational studies (cross-sectional, longitudinal, case-control)\n- Clinical trials (if applicable)\n- Natural experiments or quasi-experimental designs\n\n### 7. Formulate Testable Predictions\n\nFor each hypothesis, generate specific, quantitative predictions:\n\n- State what should be observed if the hypothesis is correct\n- Specify expected direction and magnitude of effects when possible\n- Identify conditions under which predictions should hold\n- Distinguish predictions between competing hypotheses\n- Note predictions that would falsify the hypothesis\n\n### 8. Present Structured Output\n\nGenerate a professional LaTeX document using the template in `assets\u002Fhypothesis_report_template.tex`. The report should be well-formatted with colored boxes for visual organization and divided into a concise main text with comprehensive appendices.\n\n**Document Structure:**\n\n**Main Text (Maximum 4 pages):**\n1. **Executive Summary** - Brief overview in summary box (0.5-1 page)\n2. **Competing Hypotheses** - Each hypothesis in its own colored box with brief mechanistic explanation and key evidence (2-2.5 pages for 3-5 hypotheses)\n   - **IMPORTANT:** Use `\\newpage` before each hypothesis box to prevent content overflow\n   - Each box should be ≤0.6 pages maximum\n3. **Testable Predictions** - Key predictions in amber boxes (0.5-1 page)\n4. **Critical Comparisons** - Priority comparison boxes (0.5-1 page)\n\nKeep main text highly concise - only the most essential information. All details go to appendices.\n\n**Page Break Strategy:**\n- Always use `\\newpage` before hypothesis boxes to ensure they start on fresh pages\n- This prevents content from overflowing off page boundaries\n- LaTeX boxes (tcolorbox) do not automatically break across pages\n\n**Appendices (Comprehensive, Detailed):**\n- **Appendix A:** Comprehensive literature review with extensive citations\n- **Appendix B:** Detailed experimental designs with full protocols\n- **Appendix C:** Quality assessment tables and detailed evaluations\n- **Appendix D:** Supplementary evidence and analogous systems\n\n**Colored Box Usage:**\n\nUse the custom box environments from `hypothesis_generation.sty`:\n\n- `hypothesisbox1` through `hypothesisbox5` - For each competing hypothesis (blue, green, purple, teal, orange)\n- `predictionbox` - For testable predictions (amber)\n- `comparisonbox` - For critical comparisons (steel gray)\n- `evidencebox` - For supporting evidence highlights (light blue)\n- `summarybox` - For executive summary (blue)\n\n**Each hypothesis box should contain (keep concise for 4-page limit):**\n- **Mechanistic Explanation:** 1-2 brief paragraphs (6-10 sentences max) explaining HOW and WHY\n- **Key Supporting Evidence:** 2-3 bullet points with citations (most important evidence only)\n- **Core Assumptions:** 1-2 critical assumptions\n\nAll detailed explanations, additional evidence, and comprehensive discussions belong in the appendices.\n\n**Critical Overflow Prevention:**\n- Insert `\\newpage` before each hypothesis box to start it on a fresh page\n- Keep each complete hypothesis box to ≤0.6 pages (approximately 15-20 lines of content)\n- If content exceeds this, move additional details to Appendix A\n- Never let boxes overflow off page boundaries - this creates unreadable PDFs\n\n**Citation Requirements:**\n\nAim for extensive citation to support all claims:\n- **Main text:** 10-15 key citations for most important evidence only (keep concise for 4-page limit)\n- **Appendix A:** 40-70+ comprehensive citations covering all relevant literature\n- **Total target:** 50+ references in bibliography\n\nMain text citations should be selective - cite only the most critical papers. All comprehensive citation and detailed literature discussion belongs in the appendices. Use `\\citep{author2023}` for parenthetical citations.\n\n**LaTeX Compilation:**\n\nThe template requires XeLaTeX or LuaLaTeX for proper rendering:\n\n```bash\nxelatex hypothesis_report.tex\nbibtex hypothesis_report\nxelatex hypothesis_report.tex\nxelatex hypothesis_report.tex\n```\n\n**Required packages:** The `hypothesis_generation.sty` style package must be in the same directory or LaTeX path. It requires: tcolorbox, xcolor, fontspec, fancyhdr, titlesec, enumitem, booktabs, natbib.\n\n**Page Overflow Prevention:**\n\nTo prevent content from overflowing on pages, follow these critical guidelines:\n\n1. **Monitor Box Content Length:** Each hypothesis box should fit comfortably on a single page. If content exceeds ~0.7 pages, it will likely overflow.\n\n2. **Use Strategic Page Breaks:** Insert `\\newpage` before boxes that contain substantial content:\n   ```latex\n   \\newpage\n   \\begin{hypothesisbox1}[Hypothesis 1: Title]\n   % Long content here\n   \\end{hypothesisbox1}\n   ```\n\n3. **Keep Main Text Boxes Concise:** For the 4-page main text limit:\n   - Each hypothesis box: Maximum 0.5-0.6 pages\n   - Mechanistic explanation: 1-2 brief paragraphs only (6-10 sentences max)\n   - Key evidence: 2-3 bullet points only\n   - Core assumptions: 1-2 items only\n   - If content is longer, move details to appendices\n\n4. **Break Long Content:** If a hypothesis requires extensive explanation, split across main text and appendix:\n   - Main text box: Brief mechanistic overview + 2-3 key evidence points\n   - Appendix A: Detailed mechanism explanation, comprehensive evidence, extended discussion\n\n5. **Test Page Boundaries:** Before each new box, consider if remaining page space is sufficient. If less than 0.6 pages remain, use `\\newpage` to start the box on a fresh page.\n\n6. **Appendix Page Management:** In appendices, use `\\newpage` between major sections to avoid overflow in detailed content areas.\n\n**Quick Reference:** See `assets\u002FFORMATTING_GUIDE.md` for detailed examples of all box types, color schemes, and common formatting patterns.\n\n## Quality Standards\n\nEnsure all generated hypotheses meet these standards:\n\n- **Evidence-based:** Grounded in existing literature with citations\n- **Testable:** Include specific, measurable predictions\n- **Mechanistic:** Explain how\u002Fwhy, not just what\n- **Comprehensive:** Consider alternative explanations\n- **Rigorous:** Include experimental designs to test predictions\n\n## Resources\n\n### references\u002F\n\n- `hypothesis_quality_criteria.md` - Framework for evaluating hypothesis quality (testability, falsifiability, parsimony, explanatory power, scope, consistency)\n- `experimental_design_patterns.md` - Common experimental approaches across domains (RCTs, observational studies, lab experiments, computational models)\n- `literature_search_strategies.md` - Effective search techniques for PubMed and general scientific sources\n\n### assets\u002F\n\n- `hypothesis_generation.sty` - LaTeX style package providing colored boxes, professional formatting, and custom environments for hypothesis reports\n- `hypothesis_report_template.tex` - Complete LaTeX template with main text structure and comprehensive appendix sections\n- `FORMATTING_GUIDE.md` - Quick reference guide with examples of all box types, color schemes, citation practices, and troubleshooting tips\n\n### Related Skills\n\nWhen preparing hypothesis-driven research for publication, consult the **venue-templates** skill for writing style guidance:\n- `venue_writing_styles.md` - Master guide comparing styles across venues\n- Venue-specific guides for Nature\u002FScience, Cell Press, medical journals, and ML\u002FCS conferences\n- `reviewer_expectations.md` - What reviewers look for when evaluating research hypotheses\n\n","# Scientific Hypothesis Generation\n\n## Overview\n\nHypothesis generation is a systematic process for developing testable explanations. Formulate evidence-based hypotheses from observations, design experiments, explore competing explanations, and develop predictions. Apply this skill for scientific inquiry across domains.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Developing hypotheses from observations or preliminary data\n- Designing experiments to test scientific questions\n- Exploring competing explanations for phenomena\n- Formulating testable predictions for research\n- Conducting literature-based hypothesis generation\n- Planning mechanistic studies across scientific domains\n\n## Visual Enhancement with Scientific Schematics\n\n**⚠️ MANDATORY: Every hypothesis generation report MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.**\n\nThis is not optional. Hypothesis reports without visual elements are incomplete. Before finalizing any document:\n1. Generate at minimum ONE schematic or diagram (e.g., hypothesis framework showing competing explanations)\n2. Prefer 2-3 figures for comprehensive reports (mechanistic pathway, experimental design flowchart, prediction decision tree)\n\n**How to generate figures:**\n- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams\n- Simply describe your desired diagram in natural language\n- Nano Banana Pro will automatically generate, review, and refine the schematic\n\n**How to generate schematics:**\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o figures\u002Foutput.png\n```\n\nThe AI will automatically:\n- Create publication-quality images with proper formatting\n- Review and refine through multiple iterations\n- Ensure accessibility (colorblind-friendly, high contrast)\n- Save outputs in the figures\u002F directory\n\n**When to add schematics:**\n- Hypothesis framework diagrams showing competing explanations\n- Experimental design flowcharts\n- Mechanistic pathway diagrams\n- Prediction decision trees\n- Causal relationship diagrams\n- Theoretical model visualizations\n- Any complex concept that benefits from visualization\n\nFor detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.\n\n---\n\n## Workflow\n\nFollow this systematic process to generate robust scientific hypotheses:\n\n### 1. Understand the Phenomenon\n\nStart by clarifying the observation, question, or phenomenon that requires explanation:\n\n- Identify the core observation or pattern that needs explanation\n- Define the scope and boundaries of the phenomenon\n- Note any constraints or specific contexts\n- Clarify what is already known vs. what is uncertain\n- Identify the relevant scientific domain(s)\n\n### 2. Conduct Comprehensive Literature Search\n\nSearch existing scientific literature to ground hypotheses in current evidence. Use both PubMed (for biomedical topics) and general web search (for broader scientific domains):\n\n**For biomedical topics:**\n- Use WebFetch with PubMed URLs to access relevant literature\n- Search for recent reviews, meta-analyses, and primary research\n- Look for similar phenomena, related mechanisms, or analogous systems\n\n**For all scientific domains:**\n- Use WebSearch to find recent papers, preprints, and reviews\n- Search for established theories, mechanisms, or frameworks\n- Identify gaps in current understanding\n\n**Search strategy:**\n- Begin with broad searches to understand the landscape\n- Narrow to specific mechanisms, pathways, or theories\n- Look for contradictory findings or unresolved debates\n- Consult `references\u002Fliterature_search_strategies.md` for detailed search techniques\n\n### 3. Synthesize Existing Evidence\n\nAnalyze and integrate findings from literature search:\n\n- Summarize current understanding of the phenomenon\n- Identify established mechanisms or theories that may apply\n- Note conflicting evidence or alternative viewpoints\n- Recognize gaps, limitations, or unanswered questions\n- Identify analogies from related systems or domains\n\n### 4. Generate Competing Hypotheses\n\nDevelop 3-5 distinct hypotheses that could explain the phenomenon. Each hypothesis should:\n\n- Provide a mechanistic explanation (not just description)\n- Be distinguishable from other hypotheses\n- Draw on evidence from the literature synthesis\n- Consider different levels of explanation (molecular, cellular, systemic, population, etc.)\n\n**Strategies for generating hypotheses:**\n- Apply known mechanisms from analogous systems\n- Consider multiple causative pathways\n- Explore different scales of explanation\n- Question assumptions in existing explanations\n- Combine mechanisms in novel ways\n\n### 5. Evaluate Hypothesis Quality\n\nAssess each hypothesis against established quality criteria from `references\u002Fhypothesis_quality_criteria.md`:\n\n**Testability:** Can the hypothesis be empirically tested?\n**Falsifiability:** What observations would disprove it?\n**Parsimony:** Is it the simplest explanation that fits the evidence?\n**Explanatory Power:** How much of the phenomenon does it explain?\n**Scope:** What range of observations does it cover?\n**Consistency:** Does it align with established principles?\n**Novelty:** Does it offer new insights beyond existing explanations?\n\nExplicitly note the strengths and weaknesses of each hypothesis.\n\n### 6. Design Experimental Tests\n\nFor each viable hypothesis, propose specific experiments or studies to test it. Consult `references\u002Fexperimental_design_patterns.md` for common approaches:\n\n**Experimental design elements:**\n- What would be measured or observed?\n- What comparisons or controls are needed?\n- What methods or techniques would be used?\n- What sample sizes or statistical approaches are appropriate?\n- What are potential confounds and how to address them?\n\n**Consider multiple approaches:**\n- Laboratory experiments (in vitro, in vivo, computational)\n- Observational studies (cross-sectional, longitudinal, case-control)\n- Clinical trials (if applicable)\n- Natural experiments or quasi-experimental designs\n\n### 7. Formulate Testable Predictions\n\nFor each hypothesis, generate specific, quantitative predictions:\n\n- State what should be observed if the hypothesis is correct\n- Specify expected direction and magnitude of effects when possible\n- Identify conditions under which predictions should hold\n- Distinguish predictions between competing hypotheses\n- Note predictions that would falsify the hypothesis\n\n### 8. Present Structured Output\n\nGenerate a professional LaTeX document using the template in `assets\u002Fhypothesis_report_template.tex`. The report should be well-formatted with colored boxes for visual organization and divided into a concise main text with comprehensive appendices.\n\n**Document Structure:**\n\n**Main Text (Maximum 4 pages):**\n1. **Executive Summary** - Brief overview in summary box (0.5-1 page)\n2. **Competing Hypotheses** - Each hypothesis in its own colored box with brief mechanistic explanation and key evidence (2-2.5 pages for 3-5 hypotheses)\n   - **IMPORTANT:** Use `\\newpage` before each hypothesis box to prevent content overflow\n   - Each box should be ≤0.6 pages maximum\n3. **Testable Predictions** - Key predictions in amber boxes (0.5-1 page)\n4. **Critical Comparisons** - Priority comparison boxes (0.5-1 page)\n\nKeep main text highly concise - only the most essential information. All details go to appendices.\n\n**Page Break Strategy:**\n- Always use `\\newpage` before hypothesis boxes to ensure they start on fresh pages\n- This prevents content from overflowing off page boundaries\n- LaTeX boxes (tcolorbox) do not automatically break across pages\n\n**Appendices (Comprehensive, Detailed):**\n- **Appendix A:** Comprehensive literature review with extensive citations\n- **Appendix B:** Detailed experimental designs with full protocols\n- **Appendix C:** Quality assessment tables and detailed evaluations\n- **Appendix D:** Supplementary evidence and analogous systems\n\n**Colored Box Usage:**\n\nUse the custom box environments from `hypothesis_generation.sty`:\n\n- `hypothesisbox1` through `hypothesisbox5` - For each competing hypothesis (blue, green, purple, teal, orange)\n- `predictionbox` - For testable predictions (amber)\n- `comparisonbox` - For critical comparisons (steel gray)\n- `evidencebox` - For supporting evidence highlights (light blue)\n- `summarybox` - For executive summary (blue)\n\n**Each hypothesis box should contain (keep concise for 4-page limit):**\n- **Mechanistic Explanation:** 1-2 brief paragraphs (6-10 sentences max) explaining HOW and WHY\n- **Key Supporting Evidence:** 2-3 bullet points with citations (most important evidence only)\n- **Core Assumptions:** 1-2 critical assumptions\n\nAll detailed explanations, additional evidence, and comprehensive discussions belong in the appendices.\n\n**Critical Overflow Prevention:**\n- Insert `\\newpage` before each hypothesis box to start it on a fresh page\n- Keep each complete hypothesis box to ≤0.6 pages (approximately 15-20 lines of content)\n- If content exceeds this, move additional details to Appendix A\n- Never let boxes overflow off page boundaries - this creates unreadable PDFs\n\n**Citation Requirements:**\n\nAim for extensive citation to support all claims:\n- **Main text:** 10-15 key citations for most important evidence only (keep concise for 4-page limit)\n- **Appendix A:** 40-70+ comprehensive citations covering all relevant literature\n- **Total target:** 50+ references in bibliography\n\nMain text citations should be selective - cite only the most critical papers. All comprehensive citation and detailed literature discussion belongs in the appendices. Use `\\citep{author2023}` for parenthetical citations.\n\n**LaTeX Compilation:**\n\nThe template requires XeLaTeX or LuaLaTeX for proper rendering:\n\n```bash\nxelatex hypothesis_report.tex\nbibtex hypothesis_report\nxelatex hypothesis_report.tex\nxelatex hypothesis_report.tex\n```\n\n**Required packages:** The `hypothesis_generation.sty` style package must be in the same directory or LaTeX path. It requires: tcolorbox, xcolor, fontspec, fancyhdr, titlesec, enumitem, booktabs, natbib.\n\n**Page Overflow Prevention:**\n\nTo prevent content from overflowing on pages, follow these critical guidelines:\n\n1. **Monitor Box Content Length:** Each hypothesis box should fit comfortably on a single page. If content exceeds ~0.7 pages, it will likely overflow.\n\n2. **Use Strategic Page Breaks:** Insert `\\newpage` before boxes that contain substantial content:\n   ```latex\n   \\newpage\n   \\begin{hypothesisbox1}[Hypothesis 1: Title]\n   % Long content here\n   \\end{hypothesisbox1}\n   ```\n\n3. **Keep Main Text Boxes Concise:** For the 4-page main text limit:\n   - Each hypothesis box: Maximum 0.5-0.6 pages\n   - Mechanistic explanation: 1-2 brief paragraphs only (6-10 sentences max)\n   - Key evidence: 2-3 bullet points only\n   - Core assumptions: 1-2 items only\n   - If content is longer, move details to appendices\n\n4. **Break Long Content:** If a hypothesis requires extensive explanation, split across main text and appendix:\n   - Main text box: Brief mechanistic overview + 2-3 key evidence points\n   - Appendix A: Detailed mechanism explanation, comprehensive evidence, extended discussion\n\n5. **Test Page Boundaries:** Before each new box, consider if remaining page space is sufficient. If less than 0.6 pages remain, use `\\newpage` to start the box on a fresh page.\n\n6. **Appendix Page Management:** In appendices, use `\\newpage` between major sections to avoid overflow in detailed content areas.\n\n**Quick Reference:** See `assets\u002FFORMATTING_GUIDE.md` for detailed examples of all box types, color schemes, and common formatting patterns.\n\n## Quality Standards\n\nEnsure all generated hypotheses meet these standards:\n\n- **Evidence-based:** Grounded in existing literature with citations\n- **Testable:** Include specific, measurable predictions\n- **Mechanistic:** Explain how\u002Fwhy, not just what\n- **Comprehensive:** Consider alternative explanations\n- **Rigorous:** Include experimental designs to test predictions\n\n## Resources\n\n### references\u002F\n\n- `hypothesis_quality_criteria.md` - Framework for evaluating hypothesis quality (testability, falsifiability, parsimony, explanatory power, scope, consistency)\n- `experimental_design_patterns.md` - Common experimental approaches across domains (RCTs, observational studies, lab experiments, computational models)\n- `literature_search_strategies.md` - Effective search techniques for PubMed and general scientific sources\n\n### assets\u002F\n\n- `hypothesis_generation.sty` - LaTeX style package providing colored boxes, professional formatting, and custom environments for hypothesis reports\n- `hypothesis_report_template.tex` - Complete LaTeX template with main text structure and comprehensive appendix sections\n- `FORMATTING_GUIDE.md` - Quick reference guide with examples of all box types, color schemes, citation practices, and troubleshooting tips\n\n### Related Skills\n\nWhen preparing hypothesis-driven research for publication, consult the **venue-templates** skill for writing style guidance:\n- `venue_writing_styles.md` - Master guide comparing styles across venues\n- Venue-specific guides for Nature\u002FScience, Cell Press, medical journals, and ML\u002FCS conferences\n- `reviewer_expectations.md` - What reviewers look for when evaluating research hypotheses\n\n",{"name":5,"license":60,"metadata":61,"description":7,"allowed-tools":69,"required_environment_variables":70},"MIT license",{"version":62,"openclaw":63,"skill-author":68},"1.1",{"envVars":64,"primaryEnv":66},[65],{"name":66,"required":56,"description":67},"OPENROUTER_API_KEY","OpenRouter API key for the skill's LLM-powered steps.","K-Dense Inc.","Read Write Edit Bash",[71],{"name":66,"prompt":67,"required_for":72},"optional features","main","4aa39efd1cdab0b4657ecee16c92a92011a5b10f","scientific-agent-skills\u002Fskills\u002Fhypothesis-generation","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub","https:\u002F\u002Fgithub.com\u002Ffadrienne","2026-10-28 00:43:09",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add fadrienne\u002FMyGitHub --skill hypothesis-generation",{"tool":85,"command":86},"bunx","bunx skills add fadrienne\u002FMyGitHub --skill hypothesis-generation",{"tool":88,"command":89},"pnpm","pnpm dlx skills add fadrienne\u002FMyGitHub --skill hypothesis-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002FSKILL.md",true,[93,99,103,107,113,117,121,127],{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"assets\u002FFORMATTING_GUIDE.md","ASSET","资产文件",19304,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Fassets\u002FFORMATTING_GUIDE.md",{"path":100,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":101,"sourceHtmlUrl":102},"assets\u002Fhypothesis_generation.sty",7625,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Fassets\u002Fhypothesis_generation.sty",{"path":104,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":105,"sourceHtmlUrl":106},"assets\u002Fhypothesis_report_template.tex",20148,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Fassets\u002Fhypothesis_report_template.tex",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fexperimental_design_patterns.md","REFERENCE","参考文档",14208,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Freferences\u002Fexperimental_design_patterns.md",{"path":114,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fhypothesis_quality_criteria.md",8051,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Freferences\u002Fhypothesis_quality_criteria.md",{"path":118,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Fliterature_search_strategies.md",20277,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Freferences\u002Fliterature_search_strategies.md",{"path":122,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Fgenerate_schematic_ai.py","SCRIPT","脚本",32647,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Fscripts\u002Fgenerate_schematic_ai.py",{"path":128,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Fgenerate_schematic.py",5146,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fhypothesis-generation\u002Fscripts\u002Fgenerate_schematic.py",[132,157,180,206,233,259],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":55},"01M7167B28PK20HP7R7ZED2DY0","statistical-power","Sample size calculation, power analysis, and effect size conversion for scientific studies. Use BEFORE data collection (a priori) to determine required N, or after (post-hoc) to compute achieved power. Covers parametric tests (t-test, ANOVA, chi-square, proportions, correlation, regression), simulation-based power for complex\u002Fclustered\u002Fnested designs, and power curves. Use this skill when someone asks 'how many samples do I need', 'what is my power', 'what effect size can I detect', or any variant. Pairs with \u002Fexperimental-design (choose design first, then compute power) and \u002Fstatistical-analysis (analyze data after collection).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-power\u002FSKILL.md",[138],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[140,141,142,143,144,145,54,146,39,50,147,148,149,150,151,152,153,154,155,156],"power","statistical power","effect","scipy","regression","choose","uv","collection","analysis","calculation","ANOVA","conversion","analyze","t-test","chi-square","simulation","sample",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":55},"01M71677EBCM8EPCE9BZCK8505","statistical-analysis","Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-analysis\u002FSKILL.md",[163],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[148,165,140,166,167,168,39,42,169,53,170,171,172,173,174,175,176,177,178,179],"statistical analysis","academic research","implementing","selection","reporting","for","tests","use","with","test","research","results","statsmodels","models","help",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":193,"publishedAt":55},"01M71673R93XAHFH81DBNVNG7H","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[186,189,190],{"categoryNo":187,"categoryName":188,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":191,"categoryName":192,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者",[194,43,195,196,197,198,199,200,201,45,50,52,202,203,49,204,205,48,169,41],"writing","scientific writing","Citations","deep","deep research","never","papers","journal","prisma","structure","Outlines","core skill",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":216,"publishedAt":55},"01M7166ZPKXBF4EBPHVTJPQBB1","scientific-visualization","Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib\u002Fseaborn\u002Fplotly with publication styles. For quick exploration use seaborn or plotly directly.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[212,215],{"categoryNo":213,"categoryName":214,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[217,43,218,219,220,221,222,223,224,201,39,225,226,227,228,229,230,231,170,232],"visualization","scientific visualization","error","ready","quick","exploration","meta-skill","Meta","safe","plotly","annotations","formatting","Publication","figures","panel","submission",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":245,"publishedAt":55},"01M7166VXJWQSSC3RQZP60WBGR","research-code","Debug, profile, review, and restructure Python research and analysis code. Use when analysis scripts crash, produce wrong results, run too slowly, or need a correctness review. Covers: reading tracebacks and diagnosing root causes, hypothesis-driven debugging, reviewing code for common statistical\u002Fnumerical errors, profiling data pipelines, improving reproducibility (seeds, environments, determinism), and structuring analysis scripts for sharing. Distinct from \u002Fexploratory-data-analysis (which understands data) and \u002Fstatistical-analysis (which chooses and runs tests) — this skill focuses on the code itself.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fresearch-code\u002FSKILL.md",[239,242],{"categoryNo":240,"categoryName":241,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":243,"categoryName":244,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师",[246,247,175,248,249,250,251,146,252,39,50,148,253,254,255,256,257,258,48,38],"code","research code","which","memory","data-analysis","errors","debugging","common","review","data pipelines","run","scripts","line",{"skillNo":260,"name":261,"nameZh":6,"description":262,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":263,"licenseFileUrl":6,"sourceHtmlUrl":264,"categories":265,"keywords":272,"publishedAt":55},"01M7166CF5HSR7SVZYZFWTDX55","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fmarkdown-mermaid-writing\u002FSKILL.md",[266,269,270,271],{"categoryNo":267,"categoryName":268,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":187,"categoryName":188,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":191,"categoryName":192,"taxonomyType":32,"taxonomyTypeDesc":33},[194,273,274,275,276,277,217,278,279,39,50,148,280,281,282,283,284,285,43,48],"markdown mermaid writing","mermaid","markdown","community","diagrams","project","default","team","guides","text","documentation","references","diagram"]