{"id":"b17596b2-705e-43c5-bbca-085cc50f9649","shortId":"ERjrFV","kind":"skill","title":"scientific-writing","tagline":"This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.","description":"# Scientific Writing\n\n## Overview\n\n**This is the core skill for the deep research and writing tool**—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.\n\nScientific writing is a process for communicating research with precision and clarity. Write manuscripts using IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Apply this skill for research papers and journal submissions.\n\n**Critical Principle: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript.** Use a two-stage process: first create section outlines with key points using research-lookup, then convert those outlines into complete paragraphs.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Writing or revising any section of a scientific manuscript (abstract, introduction, methods, results, discussion)\n- Structuring a research paper using IMRAD or other standard formats\n- Formatting citations and references in specific styles (APA, AMA, Vancouver, Chicago, IEEE)\n- Creating, formatting, or improving figures, tables, and data visualizations\n- Applying study-specific reporting guidelines (CONSORT for trials, STROBE for observational studies, PRISMA for reviews)\n- Drafting abstracts that meet journal requirements (structured or unstructured)\n- Preparing manuscripts for submission to specific journals\n- Improving writing clarity, conciseness, and precision\n- Ensuring proper use of field-specific terminology and nomenclature\n- Addressing reviewer comments and revising manuscripts\n\n## Visual Enhancement with Scientific Schematics\n\n**⚠️ MANDATORY: Every scientific paper MUST include a graphical abstract plus 1-2 additional AI-generated figures using the scientific-schematics skill.**\n\nThis is not optional. Scientific papers without visual elements are incomplete. Before finalizing any document:\n1. **ALWAYS generate a graphical abstract** as the first visual element\n2. Generate at minimum ONE additional schematic or diagram using scientific-schematics\n3. Prefer 3-4 total figures for comprehensive papers (graphical abstract + methods flowchart + results visualization + conceptual diagram)\n\n### Graphical Abstract (REQUIRED)\n\n**Every scientific writeup MUST include a graphical abstract.** This is a visual summary of your paper that:\n- Appears before or immediately after the text abstract\n- Captures the entire paper's key message in one image\n- Is suitable for journal table of contents display\n- Uses landscape orientation (typically 1200x600px)\n\n**Generate the graphical abstract FIRST:**\n```bash\npython scripts/generate_schematic.py \"Graphical abstract for [paper title]: [brief description showing workflow from input → methods → key findings → conclusions]\" -o figures/graphical_abstract.png\n```\n\n**Graphical Abstract Requirements:**\n- **Content**: Visual summary showing workflow, key methods, main findings, and conclusions\n- **Style**: Clean, professional, suitable for journal TOC\n- **Elements**: Include 3-5 key steps/concepts with connecting arrows or flow\n- **Text**: Minimal labels, large readable fonts\n- Log: `[HH:MM:SS] GENERATED: Graphical abstract for paper summary`\n\n### Additional Figures (GENERATE EXTENSIVELY)\n\n**⚠️ CRITICAL: Use BOTH scientific-schematics AND generate-image EXTENSIVELY throughout all documents.**\n\nEvery document should be richly illustrated. Generate figures liberally - when in doubt, add a visual.\n\n**MINIMUM Figure Requirements:**\n\n| Document Type | Minimum | Recommended |\n|--------------|---------|-------------|\n| Research Papers | 5 | 6-8 |\n| Literature Reviews | 4 | 5-7 |\n| Market Research | 20 | 25-30 |\n| Presentations | 1/slide | 1-2/slide |\n| Posters | 6 | 8-10 |\n| Grants | 4 | 5-7 |\n| Clinical Reports | 3 | 4-6 |\n\n**Use scientific-schematics EXTENSIVELY for technical diagrams:**\n```bash\npython scripts/generate_schematic.py \"your diagram description\" -o figures/output.png\n```\n\n- Study design and methodology flowcharts (CONSORT, PRISMA, STROBE)\n- Conceptual framework diagrams\n- Experimental workflow illustrations\n- Data analysis pipeline diagrams\n- Biological pathway or mechanism diagrams\n- System architecture visualizations\n- Neural network architectures\n- Decision trees, algorithm flowcharts\n- Comparison matrices, timeline diagrams\n- Any technical concept that benefits from schematic visualization\n\n**Use generate-image EXTENSIVELY for visual content:**\n```bash\npython scripts/generate_image.py \"your image description\" -o figures/output.png\n```\n\n- Photorealistic illustrations of concepts\n- Medical/anatomical illustrations\n- Environmental/ecological scenes\n- Equipment and lab setup visualizations\n- Artistic visualizations, infographics\n- Cover images, header graphics\n- Product mockups, prototype visualizations\n- Any visual that enhances understanding or engagement\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/ directory\n\n**When in Doubt, Generate a Figure:**\n- Complex concept → generate a schematic\n- Data discussion → generate a visualization\n- Process description → generate a flowchart\n- Comparison → generate a comparison diagram\n- Reader benefit → generate a visual\n\nFor detailed guidance, refer to the scientific-schematics and generate-image skill documentation.\n\n---\n\n## Core Capabilities\n\n### 1. Manuscript Structure and Organization\n\n**IMRAD Format**: Guide papers through the standard Introduction, Methods, Results, And Discussion structure used across most scientific disciplines. This includes:\n- **Introduction**: Establish research context, identify gaps, state objectives\n- **Methods**: Detail study design, populations, procedures, and analysis approaches\n- **Results**: Present findings objectively without interpretation\n- **Discussion**: Interpret results, acknowledge limitations, propose future directions\n\nFor detailed guidance on IMRAD structure, refer to `references/imrad_structure.md`.\n\n**Alternative Structures**: Support discipline-specific formats including:\n- Review articles (narrative, systematic, scoping)\n- Case reports and case series\n- Meta-analyses and pooled analyses\n- Theoretical/modeling papers\n- Methods papers and protocols\n\n### 2. Section-Specific Writing Guidance\n\n**Abstract Composition**: Craft concise, standalone summaries (100-250 words) that capture the paper's purpose, methods, results, and conclusions. Support both structured abstracts (with labeled sections) and unstructured single-paragraph formats.\n\n**Introduction Development**: Build compelling introductions that:\n- Establish the research problem's importance\n- Review relevant literature systematically\n- Identify knowledge gaps or controversies\n- State clear research questions or hypotheses\n- Explain the study's novelty and significance\n\n**Methods Documentation**: Ensure reproducibility through:\n- Detailed participant/sample descriptions\n- Clear procedural documentation\n- Statistical methods with justification\n- Equipment and materials specifications\n- Ethical approval and consent statements\n\n**Results Presentation**: Present findings with:\n- Logical flow from primary to secondary outcomes\n- Integration with figures and tables\n- Statistical significance with effect sizes\n- Objective reporting without interpretation\n\n**Discussion Construction**: Synthesize findings by:\n- Relating results to research questions\n- Comparing with existing literature\n- Acknowledging limitations honestly\n- Proposing mechanistic explanations\n- Suggesting practical implications and future research\n\n### 3. Citation and Reference Management\n\nApply citation styles correctly across disciplines. For comprehensive style guides, refer to `references/citation_styles.md`.\n\n**Major Citation Styles:**\n- **AMA (American Medical Association)**: Numbered superscript citations, common in medicine\n- **Vancouver**: Numbered citations in square brackets, biomedical standard\n- **APA (American Psychological Association)**: Author-date in-text citations, common in social sciences\n- **Chicago**: Notes-bibliography or author-date, humanities and sciences\n- **IEEE**: Numbered square brackets, engineering and computer science\n\n**Best Practices:**\n- Cite primary sources when possible\n- Include recent literature (last 5-10 years for active fields)\n- Balance citation distribution across introduction and discussion\n- Verify all citations against original sources\n- Use reference management software (Zotero, Mendeley, EndNote)\n\n### 4. Figures and Tables\n\nCreate effective data visualizations that enhance comprehension. For detailed best practices, refer to `references/figures_tables.md`.\n\n**When to Use Tables vs. Figures:**\n- **Tables**: Precise numerical data, complex datasets, multiple variables requiring exact values\n- **Figures**: Trends, patterns, relationships, comparisons best understood visually\n\n**Design Principles:**\n- Make each table/figure self-explanatory with complete captions\n- Use consistent formatting and terminology across all display items\n- Label all axes, columns, and rows with units\n- Include sample sizes (n) and statistical annotations\n- Follow the \"one table/figure per 1000 words\" guideline\n- Avoid duplicating information between text, tables, and figures\n\n**Common Figure Types:**\n- Bar graphs: Comparing discrete categories\n- Line graphs: Showing trends over time\n- Scatterplots: Displaying correlations\n- Box plots: Showing distributions and outliers\n- Heatmaps: Visualizing matrices and patterns\n\n### 5. Reporting Guidelines by Study Type\n\nEnsure completeness and transparency by following established reporting standards. For comprehensive guideline details, refer to `references/reporting_guidelines.md`.\n\n**Key Guidelines:**\n- **CONSORT**: Randomized controlled trials\n- **STROBE**: Observational studies (cohort, case-control, cross-sectional)\n- **PRISMA**: Systematic reviews and meta-analyses\n- **STARD**: Diagnostic accuracy studies\n- **TRIPOD**: Prediction model studies\n- **ARRIVE**: Animal research\n- **CARE**: Case reports\n- **SQUIRE**: Quality improvement studies\n- **SPIRIT**: Study protocols for clinical trials\n- **CHEERS**: Economic evaluations\n\nEach guideline provides checklists ensuring all critical methodological elements are reported.\n\n### 6. Writing Principles and Style\n\nApply fundamental scientific writing principles. For detailed guidance, refer to `references/writing_principles.md`.\n\n**Clarity**:\n- Use precise, unambiguous language\n- Define technical terms and abbreviations at first use\n- Maintain logical flow within and between paragraphs\n- Use active voice when appropriate for clarity\n\n**Conciseness**:\n- Eliminate redundant words and phrases\n- Favor shorter sentences (15-20 words average)\n- Remove unnecessary qualifiers\n- Respect word limits strictly\n\n**Accuracy**:\n- Report exact values with appropriate precision\n- Use consistent terminology throughout\n- Distinguish between observations and interpretations\n- Acknowledge uncertainty appropriately\n\n**Objectivity**:\n- Present results without bias\n- Avoid overstating findings or implications\n- Acknowledge conflicting evidence\n- Maintain professional, neutral tone\n\n### 7. Writing Process: From Outline to Full Paragraphs\n\n**CRITICAL: Always write in full paragraphs, never submit bullet points in scientific papers.**\n\nScientific papers must be written in complete, flowing prose. Use this two-stage approach for effective writing:\n\n**Stage 1: Create Section Outlines with Key Points**\n\nWhen starting a new section:\n1. Use the research-lookup skill to gather relevant literature and data\n2. Create a structured outline with bullet points marking:\n   - Main arguments or findings to present\n   - Key studies to cite\n   - Data points and statistics to include\n   - Logical flow and organization\n3. These bullet points serve as scaffolding—they are NOT the final manuscript\n\n**Example outline (Introduction section):**\n```\n- Background: AI in drug discovery gaining traction\n  * Cite recent reviews (Smith 2023, Jones 2024)\n  * Traditional methods are slow and expensive\n- Gap: Limited application to rare diseases\n  * Only 2 prior studies (Lee 2022, Chen 2023)\n  * Small datasets remain a challenge\n- Our approach: Transfer learning from common diseases\n  * Novel architecture combining X and Y\n- Study objectives: Validate on 3 rare disease datasets\n```\n\n**Stage 2: Convert Key Points to Full Paragraphs**\n\nOnce the outline is complete, expand each bullet point into proper prose:\n\n1. **Transform bullet points into complete sentences** with subjects, verbs, and objects\n2. **Add transitions** between sentences and ideas (however, moreover, in contrast, subsequently)\n3. **Integrate citations naturally** within sentences, not as lists\n4. **Expand with context and explanation** that bullet points omit\n5. **Ensure logical flow** from one sentence to the next within each paragraph\n6. **Vary sentence structure** to maintain reader engagement\n\n**Example conversion to prose:**\n\n```\nArtificial intelligence approaches have gained significant traction in drug discovery \npipelines over the past decade (Smith, 2023; Jones, 2024). While these computational \nmethods show promise for accelerating the identification of therapeutic candidates, \ntraditional experimental approaches remain slow and resource-intensive, often requiring \nyears of laboratory work and substantial financial investment. However, the application \nof AI to rare diseases has been limited, with only two prior studies demonstrating \nproof-of-concept results (Lee, 2022; Chen, 2023). The primary obstacle has been the \nscarcity of training data for conditions affecting small patient populations. \n\nTo address this challenge, we developed a transfer learning approach that leverages \nknowledge from well-characterized common diseases to predict therapeutic targets for \nrare conditions. Our novel neural architecture combines convolutional layers for \nmolecular feature extraction with attention mechanisms for protein-ligand interaction \nmodeling. The objective of this study was to validate our approach across three \nindependent rare disease datasets, assessing both predictive accuracy and biological \ninterpretability of the results.\n```\n\n**Key Differences Between Outlines and Final Text:**\n\n| Outline (Planning Stage) | Final Manuscript |\n|--------------------------|------------------|\n| Bullet points and fragments | Complete sentences and paragraphs |\n| Telegraphic notes | Full explanations with context |\n| List of citations | Citations integrated into prose |\n| Abbreviated ideas | Developed arguments with transitions |\n| For your eyes only | For publication and peer review |\n\n**Common Mistakes to Avoid:**\n\n- ❌ **Never** leave bullet points in the final manuscript\n- ❌ **Never** submit lists where paragraphs should be\n- ❌ **Don't** use numbered or bulleted lists in Results or Discussion sections (except for specific cases like study hypotheses or inclusion criteria)\n- ❌ **Don't** write sentence fragments or incomplete thoughts\n- ✅ **Do** use occasional lists only in Methods (e.g., inclusion/exclusion criteria, materials lists)\n- ✅ **Do** ensure every section flows as connected prose\n- ✅ **Do** read paragraphs aloud to check for natural flow\n\n**When Lists ARE Acceptable (Limited Cases):**\n\nLists may appear in scientific papers only in specific contexts:\n- **Methods**: Inclusion/exclusion criteria, materials and reagents, participant characteristics\n- **Supplementary Materials**: Extended protocols, equipment lists, detailed parameters\n- **Never in**: Abstract, Introduction, Results, Discussion, Conclusions\n\n**Abstract Format Rule:**\n- ❌ **NEVER** use labeled sections (Background:, Methods:, Results:, Conclusions:)\n- ✅ **ALWAYS** write as flowing paragraph(s) with natural transitions\n- Exception: Only use structured format if journal explicitly requires it in author guidelines\n\n**Integration with Research Lookup:**\n\nThe research-lookup skill is essential for Stage 1 (creating outlines):\n1. Search for relevant papers using research-lookup\n2. Extract key findings, methods, and data\n3. Organize findings as bullet points in your outline\n4. Then convert the outline to full paragraphs in Stage 2\n\nThis two-stage process ensures you:\n- Gather and organize information systematically\n- Create logical structure before writing\n- Produce polished, publication-ready prose\n- Maintain focus on the narrative flow\n\n### 8. Professional Report Formatting (Non-Journal Documents)\n\nFor research reports, technical reports, white papers, and other professional documents that are NOT journal manuscripts, use the `scientific_report.sty` LaTeX style package for a polished, professional appearance.\n\n**When to Use Professional Report Formatting:**\n- Research reports and technical reports\n- White papers and policy briefs\n- Grant reports and progress reports\n- Industry reports and technical documentation\n- Internal research summaries\n- Feasibility studies and project deliverables\n\n**When NOT to Use (Use Venue-Specific Formatting Instead):**\n- Journal manuscripts → Use `venue-templates` skill\n- Conference papers → Use `venue-templates` skill\n- Academic theses → Use institutional templates\n\n**The `scientific_report.sty` Style Package Provides:**\n\n| Feature | Description |\n|---------|-------------|\n| Typography | Helvetica font family for modern, professional appearance |\n| Color Scheme | Professional blues, greens, and accent colors |\n| Box Environments | Colored boxes for key findings, methods, recommendations, limitations |\n| Tables | Alternating row colors, professional headers |\n| Figures | Consistent caption formatting |\n| Scientific Commands | Shortcuts for p-values, effect sizes, confidence intervals |\n\n**Box Environments for Content Organization:**\n\n```latex\n% Key findings (blue) - for major discoveries\n\\begin{keyfindings}[Title]\nContent with key findings and statistics.\n\\end{keyfindings}\n\n% Methodology (green) - for methods highlights\n\\begin{methodology}[Study Design]\nDescription of methods and procedures.\n\\end{methodology}\n\n% Recommendations (purple) - for action items\n\\begin{recommendations}[Clinical Implications]\n\\begin{enumerate}\n    \\item Specific recommendation 1\n    \\item Specific recommendation 2\n\\end{enumerate}\n\\end{recommendations}\n\n% Limitations (orange) - for caveats and cautions\n\\begin{limitations}[Study Limitations]\nDescription of limitations and their implications.\n\\end{limitations}\n```\n\n**Professional Table Formatting:**\n\n```latex\n\\begin{table}[htbp]\n\\centering\n\\caption{Results Summary}\n\\begin{tabular}{@{}lccc@{}}\n\\toprule\n\\textbf{Variable} & \\textbf{Treatment} & \\textbf{Control} & \\textbf{p} \\\\\n\\midrule\nOutcome 1 & \\meansd{42.5}{8.3} & \\meansd{35.2}{7.9} & <.001\\sigthree \\\\\n\\rowcolor{tablealt} Outcome 2 & \\meansd{3.8}{1.2} & \\meansd{3.1}{1.1} & .012\\sigone \\\\\nOutcome 3 & \\meansd{18.2}{4.5} & \\meansd{17.8}{4.2} & .58\\signs \\\\\n\\bottomrule\n\\end{tabular}\n\n{\\small \\siglegend}\n\\end{table}\n```\n\n**Scientific Notation Commands:**\n\n| Command | Output | Purpose |\n|---------|--------|---------|\n| `\\pvalue{0.023}` | *p* = 0.023 | P-values |\n| `\\psig{< 0.001}` | ***p* = < 0.001** | Significant p-values (bold) |\n| `\\CI{0.45}{0.72}` | 95% CI [0.45, 0.72] | Confidence intervals |\n| `\\effectsize{d}{0.75}` | d = 0.75 | Effect sizes |\n| `\\samplesize{250}` | *n* = 250 | Sample sizes |\n| `\\meansd{42.5}{8.3}` | 42.5 ± 8.3 | Mean with SD |\n| `\\sigone`, `\\sigtwo`, `\\sigthree` | *, **, *** | Significance stars |\n\n**Getting Started:**\n\n```latex\n\\documentclass[11pt,letterpaper]{report}\n\\usepackage{scientific_report}\n\n\\begin{document}\n\\makereporttitle\n    {Report Title}\n    {Subtitle}\n    {Author Name}\n    {Institution}\n    {Date}\n\n% Your content with professional formatting\n\\end{document}\n```\n\n**Compilation**: Use XeLaTeX or LuaLaTeX for proper Helvetica font rendering:\n```bash\nxelatex report.tex\n```\n\nFor complete documentation, refer to:\n- `assets/scientific_report.sty`: The style package\n- `assets/scientific_report_template.tex`: Complete template example\n- `assets/REPORT_FORMATTING_GUIDE.md`: Quick reference guide\n- `references/professional_report_formatting.md`: Comprehensive formatting guide\n\n### 9. Journal-Specific Formatting\n\nAdapt manuscripts to journal requirements:\n- Follow author guidelines for structure, length, and format\n- Apply journal-specific citation styles\n- Meet figure/table specifications (resolution, file formats, dimensions)\n- Include required statements (funding, conflicts of interest, data availability, ethical approval)\n- Adhere to word limits for each section\n- Format according to template requirements when provided\n\n### 10. Field-Specific Language and Terminology\n\nAdapt language, terminology, and conventions to match the specific scientific discipline. Each field has established vocabulary, preferred phrasings, and domain-specific conventions that signal expertise and ensure clarity for the target audience.\n\n**Identify Field-Specific Linguistic Conventions:**\n- Review terminology used in recent high-impact papers in the target journal\n- Note field-specific abbreviations, units, and notation systems\n- Identify preferred terms (e.g., \"participants\" vs. \"subjects,\" \"compound\" vs. \"drug,\" \"specimens\" vs. \"samples\")\n- Observe how methods, organisms, or techniques are typically described\n\n**Biomedical and Clinical Sciences:**\n- Use precise anatomical and clinical terminology (e.g., \"myocardial infarction\" not \"heart attack\" in formal writing)\n- Follow standardized disease nomenclature (ICD, DSM, SNOMED-CT)\n- Specify drug names using generic names first, brand names in parentheses if needed\n- Use \"patients\" for clinical studies, \"participants\" for community-based research\n- Follow Human Genome Variation Society (HGVS) nomenclature for genetic variants\n- Report lab values with standard units (SI units in most international journals)\n\n**Molecular Biology and Genetics:**\n- Use italics for gene symbols (e.g., *TP53*), regular font for proteins (e.g., p53)\n- Follow species-specific gene nomenclature (uppercase for human: *BRCA1*; sentence case for mouse: *Brca1*)\n- Specify organism names in full at first mention, then use accepted abbreviations (e.g., *Escherichia coli*, then *E. coli*)\n- Use standard genetic notation (e.g., +/+, +/-, -/- for genotypes)\n- Employ established terminology for molecular techniques (e.g., \"quantitative PCR\" or \"qPCR,\" not \"real-time PCR\")\n\n**Chemistry and Pharmaceutical Sciences:**\n- Follow IUPAC nomenclature for chemical compounds\n- Use systematic names for novel compounds, common names for well-known substances\n- Specify chemical structures using standard notation (e.g., SMILES, InChI for databases)\n- Report concentrations with appropriate units (mM, μM, nM, or % w/v, v/v)\n- Describe synthesis routes using accepted reaction nomenclature\n- Use terms like \"bioavailability,\" \"pharmacokinetics,\" \"IC50\" consistently with field definitions\n\n**Ecology and Environmental Sciences:**\n- Use binomial nomenclature for species (italicized: *Homo sapiens*)\n- Specify taxonomic authorities at first species mention when relevant\n- Employ standardized habitat and ecosystem classifications\n- Use consistent terminology for ecological metrics (e.g., \"species richness,\" \"Shannon diversity index\")\n- Describe sampling methods with field-standard terms (e.g., \"transect,\" \"quadrat,\" \"mark-recapture\")\n\n**Physics and Engineering:**\n- Follow SI units consistently unless field conventions dictate otherwise\n- Use standard notation for physical quantities (scalars vs. vectors, tensors)\n- Employ established terminology for phenomena (e.g., \"quantum entanglement,\" \"laminar flow\")\n- Specify equipment with model numbers and manufacturers when relevant\n- Use mathematical notation consistent with field standards (e.g., ℏ for reduced Planck constant)\n\n**Neuroscience:**\n- Use standardized brain region nomenclature (e.g., refer to atlases like Allen Brain Atlas)\n- Specify coordinates for brain regions using established stereotaxic systems\n- Follow conventions for neural terminology (e.g., \"action potential\" not \"spike\" in formal writing)\n- Use \"neural activity,\" \"neuronal firing,\" \"brain activation\" appropriately based on measurement method\n- Describe recording techniques with proper specificity (e.g., \"whole-cell patch clamp,\" \"extracellular recording\")\n\n**Social and Behavioral Sciences:**\n- Use person-first language when appropriate (e.g., \"people with schizophrenia\" not \"schizophrenics\")\n- Employ standardized psychological constructs and validated assessment names\n- Follow APA guidelines for reducing bias in language\n- Specify theoretical frameworks using established terminology\n- Use \"participants\" rather than \"subjects\" for human research\n\n**General Principles:**\n\n**Match Audience Expertise:**\n- For specialized journals: Use field-specific terminology freely, define only highly specialized or novel terms\n- For broad-impact journals (e.g., *Nature*, *Science*): Define more technical terms, provide context for specialized concepts\n- For interdisciplinary audiences: Balance precision with accessibility, define terms at first use\n\n**Define Technical Terms Strategically:**\n- Define abbreviations at first use: \"messenger RNA (mRNA)\"\n- Provide brief explanations for specialized techniques when writing for broader audiences\n- Avoid over-defining terms well-known to the target audience (signals unfamiliarity with field)\n- Create a glossary if numerous specialized terms are unavoidable\n\n**Maintain Consistency:**\n- Use the same term for the same concept throughout (don't alternate between \"medication,\" \"drug,\" and \"pharmaceutical\")\n- Follow a consistent system for abbreviations (decide on \"PCR\" or \"polymerase chain reaction\" after first definition)\n- Apply the same nomenclature system throughout (especially for genes, species, chemicals)\n\n**Avoid Field Mixing Errors:**\n- Don't use clinical terminology for basic science (e.g., don't call mice \"patients\")\n- Avoid colloquialisms or overly general terms in place of precise field terminology\n- Don't import terminology from adjacent fields without ensuring proper usage\n\n**Verify Terminology Usage:**\n- Consult field-specific style guides and nomenclature resources\n- Check how terms are used in recent papers from the target journal\n- Use domain-specific databases and ontologies (e.g., Gene Ontology, MeSH terms)\n- When uncertain, cite a key reference that establishes terminology\n\n### 11. Common Pitfalls to Avoid\n\n**Top Rejection Reasons:**\n1. Inappropriate, incomplete, or insufficiently described statistics\n2. Over-interpretation of results or unsupported conclusions\n3. Poorly described methods affecting reproducibility\n4. Small, biased, or inappropriate samples\n5. Poor writing quality or difficult-to-follow text\n6. Inadequate literature review or context\n7. Figures and tables that are unclear or poorly designed\n8. Failure to follow reporting guidelines\n\n**Writing Quality Issues:**\n- Mixing tenses inappropriately (use past tense for methods/results, present for established facts)\n- Excessive jargon or undefined acronyms\n- Paragraph breaks that disrupt logical flow\n- Missing transitions between sections\n- Inconsistent notation or terminology\n\n## Workflow for Manuscript Development\n\n**Stage 1: Planning**\n1. Identify target journal and review author guidelines\n2. Determine applicable reporting guideline (CONSORT, STROBE, etc.)\n3. Outline manuscript structure (usually IMRAD)\n4. Plan figures and tables as the backbone of the paper\n\n**Stage 2: Drafting** (Use two-stage writing process for each section)\n1. Start with figures and tables (the core data story)\n2. For each section below, follow the two-stage process:\n   - **First**: Create outline with bullet points using research-lookup\n   - **Second**: Convert bullet points to full paragraphs with flowing prose\n3. Write Methods (often easiest to draft first)\n4. Draft Results (describing figures/tables objectively)\n5. Compose Discussion (interpreting findings)\n6. Write Introduction (setting up the research question)\n7. Craft Abstract (synthesizing the complete story)\n8. Create Title (concise and descriptive)\n\n**Remember**: Bullet points are for planning only—the final manuscript must be in complete paragraphs.\n\n**Stage 3: Revision**\n1. Check logical flow and \"red thread\" throughout\n2. Verify consistency in terminology and notation\n3. Ensure figures/tables are self-explanatory\n4. Confirm adherence to reporting guidelines\n5. Verify all citations are accurate and properly formatted\n6. Check word counts for each section\n7. Proofread for grammar, spelling, and clarity\n\n**Stage 4: Final Preparation**\n1. Format according to journal requirements\n2. Prepare supplementary materials\n3. Write cover letter highlighting significance\n4. Complete submission checklists\n5. Gather all required statements and forms\n\n## Integration with Other Scientific Skills\n\nThis skill works effectively with:\n- **Data analysis skills**: For generating results to report\n- **Statistical analysis**: For determining appropriate statistical presentations\n- **Literature review skills**: For contextualizing research\n- **Figure creation tools**: For developing publication-quality visualizations\n- **Venue-templates skill**: For venue-specific writing styles and formatting (journal manuscripts)\n- **scientific_report.sty**: For professional reports, white papers, and technical documents\n\n### Professional Reports vs. Journal Manuscripts\n\n**Choose the right formatting approach:**\n\n| Document Type | Formatting Approach |\n|---------------|---------------------|\n| Journal manuscripts | Use `venue-templates` skill |\n| Conference papers | Use `venue-templates` skill |\n| Research reports | Use `scientific_report.sty` (this skill) |\n| White papers | Use `scientific_report.sty` (this skill) |\n| Technical reports | Use `scientific_report.sty` (this skill) |\n| Grant reports | Use `scientific_report.sty` (this skill) |\n\n### Venue-Specific Writing Styles\n\n**Before writing for a specific venue, consult the venue-templates skill for writing style guides:**\n\nDifferent venues have dramatically different writing expectations:\n- **Nature/Science**: Accessible, story-driven, broad significance\n- **Cell Press**: Mechanistic depth, graphical abstracts, Highlights\n- **Medical journals (NEJM, Lancet)**: Structured abstracts, evidence language\n- **ML conferences (NeurIPS, ICML)**: Contribution bullets, ablation studies\n- **CS conferences (CHI, ACL)**: Field-specific conventions\n\nThe venue-templates skill provides:\n- `venue_writing_styles.md`: Master style comparison\n- Venue-specific guides: `nature_science_style.md`, `cell_press_style.md`, `medical_journal_styles.md`, `ml_conference_style.md`, `cs_conference_style.md`\n- `reviewer_expectations.md`: What reviewers look for at each venue\n- Writing examples in `assets/examples/`\n\n**Workflow**: First use this skill for general scientific writing principles (IMRAD, clarity, citations), then consult venue-templates for venue-specific style adaptation.\n\n## References\n\nThis skill includes comprehensive reference files covering specific aspects of scientific writing:\n\n- `references/imrad_structure.md`: Detailed guide to IMRAD format and section-specific content\n- `references/citation_styles.md`: Complete citation style guides (APA, AMA, Vancouver, Chicago, IEEE)\n- `references/figures_tables.md`: Best practices for creating effective data visualizations\n- `references/reporting_guidelines.md`: Study-specific reporting standards and checklists\n- `references/writing_principles.md`: Core principles of effective scientific communication\n- `references/professional_report_formatting.md`: Guide to professional report styling with `scientific_report.sty`\n\n## Assets\n\nThis skill includes LaTeX style packages and templates for professional report formatting:\n\n- `assets/scientific_report.sty`: Professional LaTeX style package with Helvetica fonts, colored boxes, and attractive tables\n- `assets/scientific_report_template.tex`: Complete report template demonstrating all style features\n- `assets/REPORT_FORMATTING_GUIDE.md`: Quick reference guide for the style package\n\n**Key Features of `scientific_report.sty`:**\n- Helvetica font family for modern, professional appearance\n- Professional color scheme (blues, greens, oranges, purples)\n- Box environments: `keyfindings`, `methodology`, `resultsbox`, `recommendations`, `limitations`, `criticalnotice`, `definition`, `executivesummary`, `hypothesis`\n- Tables with alternating row colors and professional headers\n- Scientific notation commands for p-values, effect sizes, confidence intervals\n- Professional headers and footers\n\n**For venue-specific writing styles** (tone, voice, abstract format, reviewer expectations), see the **venue-templates** skill which provides comprehensive style guides for Nature/Science, Cell Press, medical journals, ML conferences, and CS conferences.\n\nLoad these references as needed when working on specific aspects of scientific writing.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["scientific","writing","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-scientific-writing","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/scientific-writing","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34583 github stars · SKILL.md body (33,497 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T18:52:11.132Z","embedding":null,"createdAt":"2026-04-18T21:43:57.047Z","updatedAt":"2026-04-22T18:52:11.132Z","lastSeenAt":"2026-04-22T18:52:11.132Z","tsv":"'-10':547,1072 '-2':292,542 '-20':1355 '-250':852 '-30':538 '-4':346 '-5':460 '-6':556 '-7':533,551 '-8':528 '/slide':543 '0.001':2413,2415 '0.023':2406,2408 '0.45':2422,2426 '0.72':2423,2427 '0.75':2432,2434 '001':2368 '012':2380 '1':291,319,541,744,1441,1453,1592,2036,2039,2309,2361,3326,3425,3427,3472,3571,3626 '1.1':2379 '1.2':2376 '1/slide':540 '10':2573 '100':851 '1000':1180 '11':3318 '11pt':2460 '1200x600px':410 '15':1354 '17.8':2388 '18.2':2385 '2':330,839,1466,1539,1573,1604,2048,2074,2313,2373,3333,3435,3461,3482,3579,3632 '20':536 '2022':1543,1734 '2023':1523,1545,1676,1736 '2024':1525,1678 '25':537 '250':2438,2440 '3':343,345,459,554,987,1495,1568,1616,2055,2383,3342,3443,3513,3569,3586,3636 '3.1':2378 '3.8':2375 '35.2':2366 '4':531,549,555,1097,1625,2064,3348,3449,3521,3593,3623,3642 '4.2':2389 '4.5':2386 '42.5':2363,2444,2446 '5':526,532,550,1071,1219,1635,3354,3527,3599,3646 '58':2390 '6':527,545,1302,1648,3364,3532,3608 '7':1401,3370,3540,3615 '7.9':2367 '8':546,2104,3380,3547 '8.3':2364,2445,2447 '9':2517 '95':2424 'abbrevi':1327,1858,2636,2780,3143,3210 'ablat':3824 'abstract':186,239,289,324,353,361,370,387,414,420,437,480,845,867,1985,1990,3542,3808,3815,4056 'academ':2197 'acceler':1686 'accent':2223 'accept':1954,2779,2859 'access':684,3132,3797 'accord':2567,3628 'accur':3604 'accuraci':1266,1365,1818 'acknowledg':795,975,1381,1394 'acl':3829 'acronym':3405 'across':763,996,1080,1156,1809 'action':2298,3008 'activ':1075,1339,3017,3021 'adapt':2522,2580,3888 'add':514,1605 'addit':293,335,484 'address':270,1754 'adher':2559,3595 'adjac':3267 'affect':1749,3346 'ai':18,63,295,666,1513,1715 'ai-driven':17,62 'ai-gener':294 'algorithm':604 'allen':2990 'aloud':1945 'altern':809,2236,3199,4027 'alway':126,320,1410,2001 'ama':209,1008,3919 'american':1009,1027 'analys':829,832,1263 'analysi':588,784,3664,3672 'anatom':2669 'anim':1273 'annot':1174 'apa':208,1026,3067,3918 'apa/ama/vancouver':109 'appear':380,1959,2138,2216,4006 'appli':115,222,992,1307,2535,3221 'applic':1534,1713,3437 'approach':785,1436,1552,1662,1694,1762,1808,3725,3729 'appropri':1342,1370,1383,2847,3022,3051,3675 'approv':931,2558 'architectur':597,601,1559,1782 'argument':1476,1861 'arriv':1272 'arrow':465 'articl':818 'artifici':1660 'artist':647 'ask':4128 'aspect':3898,4091 'assess':1815,3064 'asset':3954 'assets/examples':3864 'assets/report_formatting_guide.md':2509,3988 'assets/scientific_report.sty':2501,3967 'assets/scientific_report_template.tex':2505,3980 'associ':1011,1029 'atlas':2988,2992 'attack':2678 'attent':1791 'attract':3978 'audienc':2612,3091,3128,3160,3172 'author':1031,1047,2021,2472,2528,2886,3433 'author-d':1030,1046 'automat':668 'avail':2556 'averag':1357 'avoid':1183,1389,1876,3161,3232,3250,3322 'axe':1162 'back':32,77 'backbon':3456 'background':1512,1997 'balanc':1077,3129 'bar':1194 'base':2713,3023 'bash':416,565,626,2493 'basic':3242 'begin':2268,2284,2300,2304,2324,2340,2347,2466 'behavior':3043 'benefit':614,723 'best':1060,1110,1137,3924 'bias':1388,3071,3350 'bibliographi':1044 'binomi':2877 'bioavail':2865 'biolog':591,1820,2738 'biomed':1024,2663 'blue':2220,2264,4010 'bold':2420 'bottomrul':2392 'boundari':4136 'box':1208,2225,2228,2256,3976,4014 'bracket':1023,1055 'brain':2982,2991,2996,3020 'brand':2698 'brca1':2763,2768 'break':3407 'brief':424,2154,3151 'broad':3111,3801 'broad-impact':3110 'broader':3159 'build':879 'bullet':136,1417,1472,1497,1587,1594,1632,1837,1879,1897,2059,3497,3505,3554,3823 'call':3247 'candid':1691 'capabl':743 'caption':1150,2243,2344 'captur':388,855 'care':1275 'case':822,825,1252,1276,1907,1956,2765 'case-control':1251 'categori':1198 'caution':2323 'caveat':2321 'cell':3036,3803,4073 'cell_press_style.md':3849 'center':2343 'chain':3216 'challeng':1550,1756 'character':1769 'characterist':1974 'check':1947,3285,3572,3609 'checklist':1294,3645,3938 'cheer':1288 'chemic':2818,2834,3231 'chemistri':2810 'chen':1544,1735 'chi':3828 'chicago':211,1041,3921 'choos':3721 'ci':2421,2425 'citat':39,84,108,202,988,993,1006,1014,1020,1036,1078,1086,1618,1853,1854,2539,3602,3877,3915 'cite':1062,1484,1519,3311 'clamp':3038 'clarif':4130 'clariti':102,256,1318,1344,2608,3621,3876 'classif':2898 'clean':451 'clear':899,919,4103 'clinic':552,1286,2302,2665,2671,2707,3239 'cohort':1250 'coli':2783,2786 'colloqui':3251 'color':2217,2224,2227,2238,3975,4008,4029 'colorblind':686 'colorblind-friend':685 'column':1163 'combin':16,61,1560,1783 'command':2246,2401,2402,4035 'comment':272 'common':1015,1037,1191,1556,1770,1873,2826,3319 'communic':97,3945 'communiti':2712 'community-bas':2711 'compar':971,1196 'comparison':606,717,720,1136,3843 'compel':880 'compil':2483 'complet':164,1149,1226,1428,1584,1597,1841,2497,2506,3545,3566,3643,3914,3981 'complex':702,1125 'compos':3528 'composit':846 'compound':2648,2819,2825 'comprehens':34,79,350,999,1107,1235,2514,3893,4068 'comput':1058,1681 'concentr':2845 'concept':612,637,703,1731,3125,3195 'conceptu':358,581 'concis':257,848,1345,3550 'conclus':433,449,863,1989,2000,3341 'condit':1748,1778 'confer':2190,3737,3819,3827,4078,4081 'confid':2254,2428,4042 'confirm':3594 'conflict':1395,2552 'connect':464,1940 'consent':933 'consist':1152,1373,2242,2868,2900,2931,2969,3187,3207,3581 'consort':228,578,1243,3440 'consort/strobe/prisma':114 'constant':2978 'construct':962,3061 'consult':3276,3779,3879 'content':404,439,625,2259,2271,2477,3912 'context':772,1628,1850,1966,3122,3369 'contextu':3682 'contrast':689,1614 'contribut':3822 'control':1245,1253,2356 'controversi':897 'convent':2584,2602,2618,2934,3003,3833 'convers':1657 'convert':160,1574,2066,3504 'convolut':1784 'coordin':2994 'core':7,52,742,3479,3940 'correct':995 'correl':1207 'count':3611 'cover':650,3638,3896 'craft':847,3541 'creat':149,213,669,1101,1442,1467,2037,2087,3177,3494,3548,3927 'creation':3685 'criteria':1913,1931,1969,4139 'critic':124,488,1297,1409 'criticalnotic':4021 'cross':1255 'cross-sect':1254 'cs':3826,4080 'cs_conference_style.md':3852 'ct':2690 'd':2431,2433 'data':220,587,707,1103,1124,1465,1485,1746,2054,2555,3480,3663,3929 'databas':2843,3301 'dataset':1126,1547,1571,1814 'date':1032,1048,2475 'decad':1674 'decid':3211 'decis':602 'deep':11,20,56,65 'defin':1323,3102,3117,3133,3138,3142,3164 'definit':2871,3220,4022 'deliver':2172 'demonstr':1727,3984 'depth':3806 'describ':2662,2855,2911,3027,3331,3344,3524,4107 'descript':425,570,631,713,918,2208,2288,2328,3552 'design':574,780,1140,2287,3379 'detail':728,778,801,916,1109,1237,1313,1981,3903 'determin':3436,3674 'develop':878,1758,1860,3423,3688 'diagnost':1265 'diagram':338,359,564,569,583,590,595,609,721 'dictat':2935 'differ':1826,3789,3793 'difficult':3360 'difficult-to-follow':3359 'dimens':2547 'direct':799 'directori':695 'disciplin':766,813,997,2590 'discipline-specif':812 'discoveri':1516,1669,2267 'discret':1197 'discuss':190,708,760,792,961,1083,1902,1988,3529 'diseas':1537,1557,1570,1718,1771,1813,2684 'display':405,1158,1206 'disrupt':3409 'distinguish':1376 'distribut':1079,1211 'divers':2909 'document':29,74,318,501,503,520,741,912,921,2111,2122,2164,2467,2482,2498,3715,3726 'documentclass':2459 'domain':2600,3299 'domain-specif':2599,3298 'doubt':513,698 'draft':238,3462,3519,3522 'dramat':3792 'driven':19,64,3800 'drug':1515,1668,2650,2692,3202 'dsm':2687 'duplic':1184 'e':2785 'e.g':1929,2644,2673,2746,2752,2781,2791,2800,2839,2905,2919,2952,2973,2985,3007,3033,3052,3114,3244,3304 'easiest':3517 'ecolog':2872,2903 'econom':1289 'ecosystem':2897 'effect':955,1102,1438,2252,2435,3661,3928,3943,4040 'effects':2430 'element':312,329,457,1299 'elimin':1346 'employ':2794,2893,2947,3058 'end':2277,2293,2314,2316,2334,2393,2397,2481 'endnot':1096 'engag':664,1655 'engin':1056,2927 'enhanc':277,661,1106 'ensur':260,683,913,1225,1295,1636,1935,2080,2607,3270,3587 'entangl':2954 'entir':390 'enumer':2305,2315 'environ':2226,2257,4015,4119 'environment':2874 'environment-specif':4118 'environmental/ecological':640 'equip':642,926,1979,2958 'error':3235 'escherichia':2782 'especi':3227 'essenti':2033 'establish':770,883,1231,2594,2795,2948,2999,3078,3316,3399 'etc':3442 'ethic':930,2557 'evalu':1290 'everi':28,73,282,363,502,1936 'evid':1396,3816 'exact':1130,1367 'exampl':1508,1656,2508,3862 'except':1904,2010 'excess':3401 'executivesummari':4023 'exist':973 'expand':1585,1626 'expect':3795,4059 'expens':1531 'experiment':584,1693 'expert':4124 'expertis':2605,3092 'explain':904 'explan':980,1630,1848,3152 'explanatori':1147,3592 'explicit':2017 'extend':1977 'extens':487,498,561,622 'extracellular':3039 'extract':1789,2049 'eye':1866 'fact':3400 'failur':3381 'famili':2212,4002 'favor':1351 'feasibl':2168 'featur':1788,2207,3987,3997 'field':265,1076,2575,2592,2615,2634,2870,2916,2933,2971,3098,3176,3233,3260,3268,3278,3831 'field-specif':264,2574,2614,2633,3097,3277,3830 'field-standard':2915 'figur':217,297,348,485,509,518,694,701,949,1098,1120,1132,1190,1192,2241,3371,3451,3475,3684 'figure/table':2542 'figures/graphical_abstract.png':435 'figures/output.png':572,633 'figures/tables':110,3525,3588 'file':2545,3895 'final':140,316,1506,1830,1835,1883,3561,3624 'financi':1709 'find':432,447,788,938,964,1391,1478,2051,2057,2231,2263,2274,3531 'fire':3019 'first':148,327,415,1329,2697,2775,2888,3048,3136,3145,3219,3493,3520,3866 'flow':132,467,941,1333,1429,1492,1638,1938,1950,2004,2103,2956,3411,3511,3574 'flowchart':355,577,605,716 'focus':2099 'follow':1175,1230,2527,2682,2715,2754,2814,2928,3002,3066,3205,3362,3383,3487 'font':473,2211,2491,2749,3974,4001 'footer':4047 'form':3652 'formal':2680,3013 'format':25,70,200,201,214,676,750,815,876,1153,1991,2014,2107,2144,2181,2244,2338,2480,2515,2521,2534,2546,2566,3607,3627,3704,3724,3728,3907,3966,4057 'fragment':1840,1918 'framework':582,3076 'freeli':3101 'friend':687 'full':129,1407,1413,1578,1847,2070,2773,3508 'fund':2551 'fundament':1308 'futur':798,985 'gain':1517,1664 'gap':774,895,1532 'gather':1461,2082,3647 'gene':2744,2758,3229,3305 'general':3088,3254,3871 'generat':296,321,331,411,478,486,496,508,620,699,704,709,714,718,724,738,3667 'generate-imag':495,619,737 'generic':2695 'genet':2723,2740,2789 'genom':2717 'genotyp':2793 'get':2456 'glossari':3179 'grammar':3618 'grant':548,2155,3762 'graph':1195,1200 'graphic':288,323,352,360,369,413,419,436,479,653,3807 'green':2221,2280,4011 'guid':751,1001,2512,2516,3281,3788,3847,3904,3917,3947,3991,4070 'guidanc':729,802,844,1314 'guidelin':113,227,1182,1221,1236,1242,1292,2022,2529,3068,3385,3434,3439,3598 'habitat':2895 'header':652,2240,4032,4045 'heart':2677 'heatmap':1214 'helvetica':2210,2490,3973,4000 'hgvs':2720 'hh':475 'high':688,2625,3104 'high-impact':2624 'highlight':2283,3640,3809 'homo':2882 'honest':977 'howev':1611,1711 'htbp':2342 'human':1049,2716,2762,3086 'hypothes':903,1910 'hypothesi':4024 'ic50':2867 'icd':2686 'icml':3821 'idea':1610,1859 'identif':1688 'identifi':773,893,2613,2641,3428 'ieee':212,1052,3922 'illustr':507,586,635,639 'imag':397,497,621,630,651,673,739 'immedi':383 'impact':2626,3112 'implic':983,1393,2303,2333 'import':888,3264 'improv':216,254,1280 'imrad':106,196,749,804,3448,3875,3906 'in-text':1033 'inadequ':3365 'inappropri':3327,3352,3391 'inchi':2841 'includ':286,367,458,768,816,1067,1168,1490,2548,3892,3957 'inclus':1912 'inclusion/exclusion':1930,1968 'incomplet':314,1920,3328 'inconsist':3416 'independ':1811 'index':2910 'industri':2160 'infarct':2675 'infograph':649 'inform':1185,2085 'input':429,4133 'instead':2182 'institut':2200,2474 'insuffici':3330 'integr':947,1617,1855,2023,3653 'intellig':1661 'intens':1700 'interact':1797 'interdisciplinari':3127 'interest':2554 'intern':2165,2735 'interpret':791,793,960,1380,1821,3336,3530 'interv':2255,2429,4043 'introduct':187,756,769,877,881,1081,1510,1986,3534 'invest':1710 'issu':3388 'ital':2742 'italic':2881 'item':1159,2299,2306,2310 'iter':682 'iupac':2815 'jargon':3402 'jone':1524,1677 'journal':122,242,253,401,455,2016,2110,2126,2183,2519,2525,2537,2631,2736,3095,3113,3296,3430,3630,3705,3719,3730,3811,4076 'journal-specif':2518,2536 'justif':925 'key':153,393,431,444,461,1241,1446,1481,1575,1825,2050,2230,2262,2273,3313,3996 'keyfind':2269,2278,4016 'knowledg':894,1765 'known':2831,3168 'lab':644,2726 'label':470,869,1160,1995 'laboratori':1705 'laminar':2955 'lancet':3813 'landscap':407 'languag':1322,2577,2581,3049,3073,3817 'larg':471 'last':1070 'latex':2131,2261,2339,2458,3958,3969 'layer':1785 'lccc':2349 'learn':1554,1761 'leav':1878 'lee':1542,1733 'length':2532 'letter':3639 'letterpap':2461 'leverag':1764 'liber':510 'ligand':1796 'like':1908,2864,2989 'limit':796,976,1363,1533,1721,1955,2234,2318,2325,2327,2330,2335,2562,4020,4095 'line':1199 'linguist':2617 'list':1624,1851,1887,1898,1925,1933,1952,1957,1980 'literatur':35,80,529,891,974,1069,1463,3366,3678 'load':4082 'log':474 'logic':940,1332,1491,1637,2088,3410,3573 'look':3856 'lookup':44,89,158,1458,2026,2030,2047,3502 'lualatex':2487 'main':446,1475 'maintain':1331,1397,1653,2098,3186 'major':1005,2266 'make':1142 'makereporttitl':2468 'manag':991,1092 'mandatori':281 'manufactur':2963 'manuscript':104,141,185,248,275,745,1507,1836,1884,2127,2184,2523,3422,3445,3562,3706,3720,3731 'mark':1474,2923 'mark-recaptur':2922 'market':534 'master':3841 'match':2586,3090,4104 'materi':928,1932,1970,1976,3635 'mathemat':2967 'matric':607,1216 'may':1958 'mean':2448 'meansd':2362,2365,2374,2377,2384,2387,2443 'measur':3025 'mechan':594,1792 'mechanist':979,3805 'medic':1010,3201,3810,4075 'medical/anatomical':638 'medical_journal_styles.md':3850 'medicin':1017 'meet':241,2541 'mendeley':1095 'mention':2776,2890 'mesh':3307 'messag':394 'messeng':3147 'meta':828,1262 'meta-analys':827,1261 'method':188,354,430,445,757,777,835,860,911,923,1527,1682,1928,1967,1998,2052,2232,2282,2290,2656,2913,3026,3345,3515 'methodolog':576,1298,2279,2285,2294,4017 'methods/results':3396 'metric':2904 'mice':3248 'midrul':2359 'minim':469 'minimum':333,517,522 'miss':3412,4141 'mistak':1874 'mix':3234,3389 'ml':3818,4077 'ml_conference_style.md':3851 'mm':476,2849 'mockup':655 'model':1270,1798,2960 'modern':2214,4004 'molecular':1787,2737,2798 'moreov':1612 'mous':2767 'mrna':3149 'multipl':681,1127 'must':285,366,1424,3563 'myocardi':2674 'n':1171,2439 'name':2473,2693,2696,2699,2771,2822,2827,3065 'narrat':819,2102 'natur':1619,1949,2008,3115 'nature/science':3796,4072 'nature_science_style.md':3848 'need':2703,4086 'nejm':3812 'network':600 'neural':599,1781,3005,3016 'neurip':3820 'neuron':3018 'neurosci':2979 'neutral':1399 'never':134,1415,1877,1885,1983,1993 'new':1451 'next':1644 'nm':2851 'nomenclatur':269,2685,2721,2759,2816,2861,2878,2984,3224,3283 'non':2109 'non-journ':2108 'notat':2400,2639,2790,2838,2939,2968,3417,3585,4034 'note':1043,1846,2632 'notes-bibliographi':1042 'novel':1558,1780,2824,3107 'novelti':908 'number':1012,1019,1053,1895,2961 'numer':1123,3181 'o':434,571,632 'object':776,789,957,1384,1565,1603,1800,3526 'observ':233,1248,1378,2654 'obstacl':1739 'occasion':1924 'often':1701,3516 'omit':1634 'one':334,396,1177,1640 'ontolog':3303,3306 'option':307 'orang':2319,4012 'organ':748,1494,2056,2084,2260,2657,2770 'orient':408 'origin':1088 'otherwis':2936 'outcom':946,2360,2372,2382 'outlier':1213 'outlin':151,162,1405,1444,1470,1509,1582,1828,1832,2038,2063,2068,3444,3495 'output':27,72,691,2403,4113 'over':3253 'over-defin':3162 'over-interpret':3334 'overst':1390 'overview':48 'p':2250,2358,2407,2410,2414,2418,4038 'p-valu':2249,2409,2417,4037 'p53':2753 'packag':2133,2205,2504,3960,3971,3995 'paper':120,194,284,309,351,378,391,422,482,525,752,834,836,857,1421,1423,1962,2043,2118,2151,2191,2627,3292,3459,3712,3738,3751 'paragraph':130,165,875,1337,1408,1414,1579,1647,1844,1889,1944,2005,2071,3406,3509,3567 'paramet':1982 'parenthes':2701 'particip':1973,2645,2709,3081 'participant/sample':917 'past':1673,3393 'patch':3037 'pathway':592 'patient':1751,2705,3249 'pattern':1134,1218 'pcr':2802,2809,3213 'peer':1871 'peopl':3053 'per':1179 'permiss':4134 'person':3047 'person-first':3046 'pharmaceut':2812,3204 'pharmacokinet':2866 'phenomena':2951 'photorealist':634 'phrase':1350,2597 'physic':2925,2941 'pipelin':589,1670 'pitfal':3320 'place':3257 'plan':1833,3426,3450,3558 'planck':2977 'plot':1209 'plus':290 'point':137,154,1418,1447,1473,1486,1498,1576,1588,1595,1633,1838,1880,2060,3498,3506,3555 'polici':2153 'polish':2093,2136 'polymeras':3215 'pool':831 'poor':3343,3355,3378 'popul':781,1752 'possibl':1066 'poster':544 'potenti':3009 'practic':982,1061,1111,3925 'precis':100,259,1122,1320,1371,2668,3130,3259 'predict':1269,1773,1817 'prefer':344,2596,2642 'prepar':247,3625,3633 'present':539,787,936,937,1385,1480,3397,3677 'press':3804,4074 'primari':943,1063,1738 'principl':125,1141,1304,1311,3089,3874,3941 'prior':1540,1725 'prisma':235,579,1257 'problem':886 'procedur':782,920,2292 'process':95,147,712,1403,2079,3468,3492 'produc':30,75,2092 'product':654 'profession':452,1398,2105,2121,2137,2142,2215,2219,2239,2336,2479,3709,3716,3949,3964,3968,4005,4007,4031,4044 'progress':2158 'project':2171 'promis':1684 'proof':1729 'proof-of-concept':1728 'proofread':3616 'proper':261,675,1590,2489,3031,3271,3606 'propos':797,978 'prose':133,1430,1591,1659,1857,1941,2097,3512 'protein':1795,2751 'protein-ligand':1794 'protocol':838,1284,1978 'prototyp':656 'provid':1293,2206,2572,3121,3150,3839,4067 'psig':2412 'psycholog':1028,3060 'public':671,1869,2095,3690 'publication-qu':670,3689 'publication-readi':2094 'purpl':2296,4013 'purpos':859,2404 'pvalu':2405 'python':417,566,627 'qpcr':2804 'quadrat':2921 'qualifi':1360 'qualiti':672,1279,3357,3387,3691 'quantit':2801 'quantiti':2942 'quantum':2953 'question':901,970,3539 'quick':2510,3989 'random':1244 'rare':1536,1569,1717,1777,1812 'rather':3082 'reaction':2860,3217 'read':1943 'readabl':472 'reader':722,1654 'readi':2096 'reagent':1972 'real':2807 'real-tim':2806 'reason':3325 'recaptur':2924 'recent':1068,1520,2623,3291 'recommend':523,2233,2295,2301,2308,2312,2317,4019 'record':3028,3040 'red':3576 'reduc':2976,3070 'redund':1347 'refer':204,730,806,990,1002,1091,1112,1238,1315,2499,2511,2986,3314,3889,3894,3990,4084 'references/citation_styles.md':1004,3913 'references/figures_tables.md':1114,3923 'references/imrad_structure.md':808,3902 'references/professional_report_formatting.md':2513,3946 'references/reporting_guidelines.md':1240,3931 'references/writing_principles.md':1317,3939 'refin':679 'region':2983,2997 'regular':2748 'reject':3324 'relat':966 'relationship':1135 'relev':890,1462,2042,2892,2965 'remain':1548,1695 'rememb':3553 'remov':1358 'render':2492 'report':112,226,553,823,958,1220,1232,1277,1301,1366,2106,2114,2116,2143,2146,2149,2156,2159,2161,2462,2465,2469,2725,2844,3384,3438,3597,3670,3710,3717,3745,3757,3763,3935,3950,3965,3982 'report.tex':2495 'reproduc':914,3347 'requir':243,362,438,519,1129,1702,2018,2526,2549,2570,3631,3649,4132 'research':12,21,43,57,66,88,98,119,157,193,524,535,771,885,900,969,986,1274,1457,2025,2029,2046,2113,2145,2166,2714,3087,3501,3538,3683,3744 'research-lookup':42,87,156,1456,2028,2045,3500 'resolut':2544 'resourc':1699,3284 'resource-intens':1698 'respect':1361 'result':189,356,758,786,794,861,935,967,1386,1732,1824,1900,1987,1999,2345,3338,3523,3668 'resultsbox':4018 'review':237,271,530,677,817,889,1259,1521,1872,2619,3367,3432,3679,3855,4058,4125 'reviewer_expectations.md':3853 'revis':179,274,3570 'rich':506,2907 'right':3723 'rna':3148 'rout':2857 'row':1165,2237,4028 'rowcolor':2370 'rule':1992 'safeti':4135 'sampl':1169,2441,2653,2912,3353 'samples':2437 'sapien':2883 'save':690 'scaffold':1501 'scalar':2943 'scarciti':1743 'scatterplot':1205 'scene':641 'schemat':280,302,336,342,493,560,616,706,735 'scheme':2218,4009 'schizophren':3057 'schizophrenia':3055 'scienc':1040,1051,1059,2666,2813,2875,3044,3116,3243 'scientif':2,46,91,184,279,283,301,308,341,364,492,559,734,765,1309,1420,1422,1961,2245,2399,2464,2589,3656,3872,3900,3944,4033,4093 'scientific-schemat':300,340,491,558,733 'scientific-writ':1 'scientific_report.sty':2130,2203,3707,3747,3753,3759,3765,3953,3999 'scope':821,4106 'scripts/generate_image.py':628 'scripts/generate_schematic.py':418,567 'sd':2450 'search':36,81,2040 'second':3503 'secondari':945 'section':150,181,841,870,1256,1443,1452,1511,1903,1937,1996,2565,3415,3471,3485,3614,3910 'section-specif':840,3909 'see':4060 'self':1146,3591 'self-explanatori':1145,3590 'sentenc':1353,1598,1608,1621,1641,1650,1842,1917,2764 'seri':826 'serv':1499 'set':3535 'setup':645 'shannon':2908 'shortcut':2247 'shorter':1352 'show':426,442,1201,1210,1683 'si':2731,2929 'siglegend':2396 'sign':2391 'signal':2604,3173 'signific':910,953,1665,2416,2454,3641,3802 'sigon':2381,2451 'sigthre':2369,2453 'sigtwo':2452 'singl':874 'single-paragraph':873 'size':956,1170,2253,2436,2442,4041 'skill':8,45,53,90,117,170,172,303,740,1459,2031,2189,2196,3657,3659,3665,3680,3696,3736,3743,3749,3755,3761,3767,3784,3838,3869,3891,3956,4065,4098 'skill-scientific-writing' 'slow':1529,1696 'small':1546,1750,2395,3349 'smile':2840 'smith':1522,1675 'snome':2689 'snomed-ct':2688 'social':1039,3041 'societi':2719 'softwar':1093 'sourc':1064,1089 'source-sickn33' 'speci':2756,2880,2889,2906,3230 'special':3094,3105,3124,3154,3182 'species-specif':2755 'specif':206,225,252,266,814,842,929,1906,1965,2180,2307,2311,2520,2538,2543,2576,2588,2601,2616,2635,2757,3032,3099,3279,3300,3700,3770,3777,3832,3846,3886,3897,3911,3934,4051,4090,4120 'specifi':2691,2769,2833,2884,2957,2993,3074 'specimen':2651 'spell':3619 'spike':3011 'spirit':1282 'squar':1022,1054 'squir':1278 'ss':477 'stage':146,1435,1440,1572,1834,2035,2073,2078,3424,3460,3466,3491,3568,3622 'standalon':849 'standard':199,755,1025,1233,2683,2729,2788,2837,2894,2917,2938,2972,2981,3059,3936 'star':2455 'stard':1264 'start':1449,2457,3473 'state':775,898 'statement':934,2550,3650 'statist':922,952,1173,1488,2276,3332,3671,3676 'steps/concepts':462 'stereotax':3000 'stop':4126 'stori':3481,3546,3799 'story-driven':3798 'strateg':3141 'strict':1364 'strobe':231,580,1247,3441 'structur':107,191,244,746,761,805,810,866,1469,1651,2013,2089,2531,2835,3446,3814 'studi':224,234,573,779,906,1223,1249,1267,1271,1281,1283,1482,1541,1564,1726,1803,1909,2169,2286,2326,2708,3825,3933 'study-specif':223,3932 'style':207,450,994,1000,1007,1306,2132,2204,2503,2540,3280,3702,3772,3787,3842,3887,3916,3951,3959,3970,3986,3994,4053,4069 'subject':1600,2647,3084 'submiss':123,250,3644 'submit':135,1416,1886 'subsequ':1615 'substanc':2832 'substanti':1708 'substitut':4116 'subtitl':2471 'success':4138 'suggest':981 'suitabl':399,453 'summari':375,441,483,850,2167,2346 'superscript':1013 'supplementari':1975,3634 'support':811,864 'symbol':2745 'synthes':963,3543 'synthesi':2856 'system':596,2640,3001,3208,3225 'systemat':820,892,1258,2086,2821 'tabl':218,402,951,1100,1118,1121,1188,2235,2337,2341,2398,3373,3453,3477,3979,4025 'table/figure':1144,1178 'tablealt':2371 'tabular':2348,2394 'target':1775,2611,2630,3171,3295,3429 'task':4102 'taxonom':2885 'technic':563,611,1324,2115,2148,2163,3119,3139,3714,3756 'techniqu':2659,2799,3029,3155 'telegraph':1845 'templat':2188,2195,2201,2507,2569,3695,3735,3742,3783,3837,3882,3962,3983,4064 'tens':3390,3394 'tensor':2946 'term':1325,2643,2863,2918,3108,3120,3134,3140,3165,3183,3191,3255,3287,3308 'terminolog':267,1155,1374,2579,2582,2620,2672,2796,2901,2949,3006,3079,3100,3240,3261,3265,3274,3317,3419,3583 'test':4122 'text':386,468,1035,1187,1831,3363 'textbf':2351,2353,2355,2357 'theoret':3075 'theoretical/modeling':833 'therapeut':1690,1774 'these':2198 'thought':1921 'thread':3577 'three':1810 'throughout':499,1375,3196,3226,3578 'time':1204,2808 'timelin':608 'titl':423,2270,2470,3549 'toc':456 'tone':1400,4054 'tool':15,60,3686 'top':3323 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'toprul':2350 'total':347 'tp53':2747 'traction':1518,1666 'tradit':1526,1692 'train':1745 'transect':2920 'transfer':1553,1760 'transform':1593 'transit':1606,1863,2009,3413 'transpar':1228 'treat':4111 'treatment':2354 'tree':603 'trend':1133,1202 'trial':230,1246,1287 'tripod':1268 'two':145,1434,1724,2077,3465,3490 'two-stag':144,1433,2076,3464,3489 'type':521,1193,1224,3727 'typic':409,2661 'typographi':2209 'unambigu':1321 'unavoid':3185 'uncertain':3310 'uncertainti':1382 'unclear':3376 'undefin':3404 'understand':662 'understood':1138 'unfamiliar':3174 'unit':1167,2637,2730,2732,2848,2930 'unless':2932 'unnecessari':1359 'unstructur':246,872 'unsupport':3340 'uppercas':2760 'usag':3272,3275 'use':105,142,155,168,175,195,262,298,339,406,489,557,618,762,1090,1117,1151,1319,1330,1338,1372,1431,1454,1894,1923,1994,2012,2044,2128,2141,2176,2177,2185,2192,2199,2484,2621,2667,2694,2704,2741,2778,2787,2820,2836,2858,2862,2876,2899,2937,2966,2980,2998,3015,3045,3077,3080,3096,3137,3146,3188,3238,3289,3297,3392,3463,3499,3732,3739,3746,3752,3758,3764,3867,4096 'usepackag':2463 'usual':3447 'v/v':2854 'valid':1566,1806,3063,4121 'valu':1131,1368,2251,2411,2419,2727,4039 'vancouv':210,1018,3920 'vari':1649 'variabl':1128,2352 'variant':2724 'variat':2718 'vector':2945 'venu':2179,2187,2194,3694,3699,3734,3741,3769,3778,3782,3790,3836,3845,3860,3881,3885,4050,4063 'venue-specif':2178,3698,3768,3844,3884,4049 'venue-templ':2186,2193,3693,3733,3740,3781,3835,3880,4062 'venue_writing_styles.md':3840 'verb':1601 'verifi':38,83,1084,3273,3580,3600 'visual':221,276,311,328,357,374,440,516,598,617,624,646,648,657,659,711,726,1104,1139,1215,3692,3930 'vocabulari':2595 'voic':1340,4055 'vs':1119,2646,2649,2652,2944,3718 'w/v':2853 'well':24,69,1768,2830,3167 'well-character':1767 'well-format':23,68 'well-known':2829,3166 'white':2117,2150,3711,3750 'whole':3035 'whole-cel':3034 'within':1334,1620,1645 'without':310,790,959,1387,3269 'word':853,1181,1348,1356,1362,2561,3610 'work':1706,3660,4088 'workflow':427,443,585,3420,3865 'write':3,14,47,59,92,103,127,177,255,843,1303,1310,1402,1411,1439,1916,2002,2091,2681,3014,3157,3356,3386,3467,3514,3533,3637,3701,3771,3774,3786,3794,3861,3873,3901,4052,4094 'writeup':365 'written':26,71,1426 'x':1561 'xelatex':2485,2494 'y':1563 'year':1073,1703 'zotero':1094 'μm':2850 'ℏ':2974","prices":[{"id":"e481c712-2ad1-4057-89b7-b9fceae4f62b","listingId":"b17596b2-705e-43c5-bbca-085cc50f9649","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:43:57.047Z"}],"sources":[{"listingId":"b17596b2-705e-43c5-bbca-085cc50f9649","source":"github","sourceId":"sickn33/antigravity-awesome-skills/scientific-writing","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/scientific-writing","isPrimary":false,"firstSeenAt":"2026-04-18T21:43:57.047Z","lastSeenAt":"2026-04-22T18:52:11.132Z"}],"details":{"listingId":"b17596b2-705e-43c5-bbca-085cc50f9649","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"scientific-writing","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34583,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-22T06:40:00Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"2e3f53ed40cfce2da1b3d667dc72d0df6605bb11","skill_md_path":"skills/scientific-writing/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/scientific-writing"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"scientific-writing","license":"MIT license","description":"This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/scientific-writing"},"updatedAt":"2026-04-22T18:52:11.132Z"}}