scientific-writing
Skill42 starsChanged 18 days agoMITView on GitHub
Comprehensive scientific writing guidance for research papers, grants, and technical documentation. Covers paper structure (IMRAD), methods writing, results presentation, figure/table design, citation formatting, abstract writing, and revision responses. Use when users are writing scientific papers, formatting manuscripts, responding to reviewers, writing grant proposals, or need help with any aspect of scientific communication. Triggers include 'write a paper,' 'scientific writing,' 'format my manuscript,' 'methods section,' 'respond to reviewers,' or any research writing task.
41 other projects use a version of this.
Adopted by
Most recently taken up by
- tomjanus/water-skillstheir own version, first seen Nov 8, 2026
- OpenLAIR/dr-clawtheir own version, first seen Nov 8, 2026
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- K-Dense-AI/claude-scientific-writertheir own version, first seen Nov 7, 2026
- LARi-UQAC/ResearchToolstheir own version, first seen Nov 5, 2026
- dbosk/claude-skillstheir own version, first seen Nov 3, 2026
Used with
Projects with it also use usfiscaldata, research-grants and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
yf8578Skillusfiscaldata
Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics.
Also in 7 projects that use this
garri333Skillresearch-grants
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
Also in 10 projects that use this
garri333Skillarboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
Also in 9 projects that use this
Hongyu-yuSkilltorch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
Also in 9 projects that use this
SoljournerSkillget-available-resources
Enumerate installed packages, databases, and tools for engineering workflows
Also in 9 projects that use this
- +7 more from garri333
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- aiming-lab/AutoResearchClaw★ 15ksame name
- K-Dense-AI/claude-scientific-writer★ 2.6ksame name
- OpenLAIR/dr-claw★ 1.2ksame name
- wu-yc/LabClaw★ 1.1ksame name
- LeonChaoX/qinyan-academic-skills★ 910same name
- Boom5426/Nature-Paper-Skills★ 661same name
- qinyan-ai/qinyan-academic-skills★ 80same name
- the-omega-institute/automath★ 72same name
- Chanw-research/claude-code-paper-writing★ 42same name
- Xevos117/mcp-zotero★ 38same name
31 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository44 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- phd-qualifierSkill
- citation-verifierSkill
- brainstormingSkill
- elevenlabsSkill
- image-generationSkill
- presentationsSkill
- video-storytellingSkill
- code-reviewerSkill
- ralph-wiggumSkill
- tddSkill
- version-controlSkill
- opentrons-absorbance-readerSkill
- opentrons-gripperSkill
- opentrons-heater-shakerSkill
- opentrons-magnetic-blockSkill
- opentronsSkill
- opentrons-temperature-moduleSkill
- opentrons-thermocyclerSkill
- planningSkill
- claude-lightSkill
- emacs-lispSkill
- fairchemSkill
- idaesSkill
- materials-propertiesSkill
- pycalphadSkill
- pymatgenSkill
- python-aseSkill
- python-best-practicesSkill
- python-jaxSkill
- python-multiobjective-optimizationSkill
- python-optimizationSkill
- python-plottingSkill
- python-regression-statisticsSkill
- vaspSkill
- pycseSkill
- elnSkill
- literature-reviewSkill
- materials-databasesSkill
- scientific-data-extractionSkill
- scientific-reviewerSkill
- scientific-workflowsSkill
- design-of-experimentsSkill
- troubleshootingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 38 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 40
Use IMRAD structure (see references/paper-structure.md)
- Distinctive: line 79
No interpretation (save for discussion)
- Distinctive: line 100
Use when precise values needed
- Distinctive: line 121
Check all in-text citations have references
- Distinctive: line 122
Check all references are cited
- Distinctive: line 219
Use headings matching criteria
- Distinctive: line 287
Test statistic, df, exact p-value
- Distinctive: line 295
Don't just say "see Figure X"
- Distinctive: line 314
Don't introduce obscure limitations
- Distinctive: line 354
Avoid hedging excessively ("relatively," "quite," "very")
- Distinctive: line 361
Don't overstate conclusions
- Distinctive: line 386
Don't explain fundamental concepts
- Distinctive: line 387
Do explain novel techniques or applications
“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Scientific Writing
Systematic guidance for writing research papers, grants, and scientific communications with emphasis on clarity, reproducibility, and adherence to field conventions.
Scientific Writing Workflow
1. Identify Document Type and Requirements
Determine what you're writing:
- Research article → Full paper with novel findings
- Review article → Synthesis of existing literature
- Grant proposal → Funding application
- Conference abstract → Brief standalone summary
- Revision response → Reply to peer reviewers
- Technical report → Documentation of work
Gather venue requirements:
- Target journal/conference/funder name
- Word/page limits by section
- Citation style required
- Figure/table format specifications
- Submission guidelines and templates
2. Select Structure and Route to Guidance
For research articles:
- Use IMRAD structure (see references/paper-structure.md)
- Introduction: references/introduction-writing.md
- Methods: references/methods-writing.md
- Results: references/results-writing.md
- Discussion: references/discussion-writing.md
- Abstract: references/abstract-writing.md
For review articles:
- See references/review-writing.md for thematic organization
- Focus on synthesis, not chronological listing
- Critical evaluation of literature
For grant proposals:
- See references/grant-writing.md for funder-specific guidance
- Specific Aims structure
- Significance, Innovation, Approach
For revision responses:
- See references/revision-response.md for point-by-point format
- Diplomatic language and tracking changes
3. Write Section by Section
Follow section-specific guidance:
Introduction (references/introduction-writing.md)
- Funnel structure: Broad → Narrow → Gap → Objective
- Establish context and importance
- Identify knowledge gap
- State clear objective
Methods (references/methods-writing.md)
- Reproducibility is paramount
- Include all essential details: equipment, reagents, software, statistics
- Organize chronologically or by subsystem
- Past tense, field-appropriate voice
Results (references/results-writing.md)
- Report observations objectively
- No interpretation (save for discussion)
- Integrate figures and tables
- Include statistical details
- Past tense
Discussion (references/discussion-writing.md)
- Interpret findings in context
- Compare with literature
- Acknowledge limitations honestly
- Discuss implications and future work
- Mix of present (facts) and past (your results)
4. Create Figures and Tables
Figures (references/figure-design.md)
- Match figure type to data type
- Publication quality: 300+ DPI, readable fonts, vector when possible
- Complete captions with all essential information
- Colorblind-friendly palettes
Tables (references/table-design.md)
- Use when precise values needed
- Clear headers with units
- Consistent decimal places
- Descriptive captions
Tools:
# Generate publication-quality figures
python scripts/figure_generator.py data.csv config.yaml --output fig1.pdf
# Format tables for journals
python scripts/table_formatter.py data.csv --format latex --journal nature5. Manage Citations and References
Citation formatting (references/citation-management.md)
- Match journal's required style:
- Numbered: [1], [2,3], [1-5]
- Author-year: (Smith, 2020; Jones, 2021)
- Author-number: Smith (1)
- Check all in-text citations have references
- Check all references are cited
- Consistent formatting throughout
Tools:
# Validate citation consistency
python scripts/citation_checker.py manuscript.docx --style apa6. Improve Clarity and Conciseness
Language clarity (references/language-clarity.md)
- Active voice preferred (field norms vary)
- Concise: remove filler words and redundancies
- Precise: avoid vague terms ("very," "quite," "many")
- One main idea per sentence
- Logical paragraph flow
Tools:
# Analyze readability
python scripts/readability_analyzer.py section.txt
# Count words by section
python scripts/word_counter.py manuscript.docx7. Review Against Requirements
Pre-submission checklist:
- Word limits met for each section
- All figures/tables referenced in text
- All citations formatted consistently
- Statistical details complete
- Methods reproducible
- Limitations discussed
- Abstract within word limit
- Keywords selected
- Author contributions stated
- Conflicts of interest disclosed
- Data availability statement
- Ethics approvals included
Document Type Routing
Research Article → IMRAD Structure
Structure overview (references/paper-structure.md)
IMRAD sections:
- /I/ntroduction: Background, gap, objective
- /M/ethods: Reproducible experimental details
- /R/esults: Objective observations with data
- /A/nd
- /D/iscussion: Interpretation, implications, limitations
What goes where:
- Introduction: Why this work matters, what's unknown, what you'll do
- Methods: How you did it (enough detail to reproduce)
- Results: What you found (observations, not interpretations)
- Discussion: What it means, how it fits, what's next
Common mistakes to avoid:
- ❌ Interpretation in results section
- ❌ New results in discussion section
- ❌ Methods scattered in results
- ❌ Missing gap identification in introduction
- ❌ Ignoring limitations
Review Article → Thematic Organization
See references/review-writing.md
Types:
- Narrative review: Broad overview
- Systematic review: Structured search (PRISMA)
- Meta-analysis: Quantitative synthesis
Key principles:
- Synthesize thematically, not chronologically
- Critical evaluation, not just summary
- Identify patterns, gaps, controversies
- Future directions
Grant Proposal → Funder-Specific Structure
See references/grant-writing.md
Common elements:
- Specific Aims (1 page): Clear, testable objectives
- Significance: Why it matters, current knowledge, impact
- Innovation: What's novel about approach
- Approach: Methods, timeline, pitfalls, alternatives
- Preliminary data: Feasibility demonstration
Review criteria alignment:
- Address all criteria explicitly
- Use headings matching criteria
- Make reviewers' job easy
Revision Response → Point-by-Point
See references/revision-response.md
Structure:
- Thank reviewers
- Summary of major changes
- Point-by-point responses with line numbers
- Track changes in manuscript
Response strategies:
- Agree and comply: Describe changes made
- Agree but can't comply: Explain why, offer alternative
- Disagree: Provide evidence diplomatically
Section-Specific Guidance
Introduction Writing
See references/introduction-writing.md
Funnel structure:
- Broad context (why general topic matters)
- Narrow to specific problem area
- Identify gap in knowledge
- State objective of this work
- Brief approach overview (optional)
Length: Typically 1-3 pages
Tense: Present for established facts, past for previous studies
Methods Writing
See references/methods-writing.md
Reproducibility checklist:
- Equipment: manufacturer, model, specs
- Reagents: source, catalog #, concentration
- Software: name, version, parameters
- Statistical tests with corrections
- Sample size justification
- Ethics approvals
Organization:
- Chronological (when order matters)
- By subsystem (complex systems)
- By measurement type (multiple assays)
Detail level:
- Standard procedures: Brief + citation
- Novel procedures: Full detail
- Modified procedures: Highlight changes
Results Writing
See references/results-writing.md
Objectivity principles:
- Report observations, not interpretations
- "Data show" not "data prove"
- Present negative results honestly
- Save interpretation for discussion
Statistical reporting:
- Test statistic, df, exact p-value
- Effect sizes and confidence intervals
- Multiple comparison corrections
- Measures of variability (SD, SE, CI)
Figure integration:
- Reference every figure/table in text
- Describe key finding from each
- Don't just say "see Figure X"
Discussion Writing
See references/discussion-writing.md
Structure:
- Restate main findings (brief)
- Interpret in context of literature
- Compare with previous work
- Explain unexpected findings
- Acknowledge limitations
- Discuss implications
- Suggest future directions
Limitations:
- Be honest but not self-defeating
- Explain impact of limitations
- Suggest how to address
- Don't introduce obscure limitations
Abstract Writing
See references/abstract-writing.md
Essential elements:
- Background (1-2 sentences)
- Objective
- Methods (brief approach)
- Results (key findings with data)
- Conclusions (significance)
Word limit strategies:
- Typical: 150-300 words
- Prioritize results and conclusions
- Remove modifiers
- Define abbreviations sparingly
- No citations (usually)
Self-contained requirement:
- Understandable without reading paper
- Include actual data, not just "significant"
Universal Scientific Writing Principles
1. Clarity Over Complexity
- Simple words over complex when meaning is same
- Short sentences preferred
- One idea per sentence
- Active voice when possible (field norms vary)
- Define specialized terms
2. Precision in Language
- Specific numbers over vague terms
- "Approximately 50%" not "many"
- Distinguish "significant" (statistical) from "important"
- Clear about causation vs correlation
- Avoid hedging excessively ("relatively," "quite," "very")
3. Objectivity in Reporting
- Separate observations (results) from interpretations (discussion)
- Present negative results honestly
- Acknowledge contradictory evidence
- Don't overstate conclusions
- Appropriate level of certainty
4. Reproducibility in Methods
- Include all information needed to reproduce
- Equipment specifications
- Exact concentrations and conditions
- Statistical methods fully described
- Software versions and parameters
- Code availability when applicable
5. Logical Flow of Argument
- Each section builds on previous
- Clear transitions between ideas
- Coherent narrative throughout
- Introduction sets up discussion
- Discussion answers introduction's questions
6. Appropriate Detail for Audience
- Assume audience has field background
- Define specialized terms first use
- Balance between too much and too little detail
- Don't explain fundamental concepts
- Do explain novel techniques or applications
Tense and Voice Usage Guide
Tense by Section
Introduction:
- Present: Established facts ("DNA is composed of...")
- Past: Previous studies ("Smith et al. showed...")
- Present: Your objective ("This study investigates...")
Methods:
- Past: What you did ("Cells were cultured...")
- Past: ("We cultured cells...")
Results:
- Past: Your findings ("Expression increased...")
- Past: ("We observed increased expression...")
Discussion:
- Past: Your results ("Our data showed...")
- Present: Established facts ("This gene regulates...")
- Present: Interpretations ("These results suggest...")
Conclusions:
- Present: General conclusions ("This approach provides...")
Voice by Field
Biology/Medicine:
- More passive acceptable in methods
- Either active or passive in other sections
Engineering/Computer Science:
- Active voice preferred throughout
- "We designed..." rather than "A design was created..."
Physics/Chemistry:
- Varies by journal and author preference
- Either acceptable if consistent
Quick Reference - Common Issues
Results vs Discussion: Keep observations in results, interpretations in discussion
Citation Consistency: Use one style throughout (numbered [1] or author-year)
Figure References: Reference all figures/tables in text with findings, not just "see Figure X"
Statistical Reporting: Include test statistic, df, exact p-value, effect size, variability measure
Methods Detail: Include manufacturer, catalog #, concentrations for reproducibility
Limitations: Be honest but not self-defeating; explain impact, suggest solutions
See individual reference files for detailed examples and guidance.
Tools and Utilities
Citation Checker
python scripts/citation_checker.py manuscript.docx --style apaValidates citation consistency between in-text and reference list.
Figure Generator
python scripts/figure_generator.py data.csv config.yaml --output fig1.pdfCreates publication-quality figures from data.
Word Counter
python scripts/word_counter.py manuscript.docxCounts words by section for length requirements.
Readability Analyzer
python scripts/readability_analyzer.py section.txtAnalyzes text complexity and suggests improvements.
Table Formatter
python scripts/table_formatter.py data.csv --format latex --journal natureFormats tables for specific journals.
Templates
Access templates for common document types:
- assets/templates/manuscript_template.docx - Generic manuscript
- assets/templates/imrad_template.md - IMRAD structure
- assets/templates/grant_aims_template.docx - NIH Specific Aims
- assets/templates/response_letter_template.docx - Revision response
- assets/templates/abstract_template.txt - Structured abstract
- assets/templates/methods_checklist.md - Reproducibility checklist
Style Guides
Journal-specific quick references:
- assets/style-guides/apa_guide.md - APA style
- assets/style-guides/nature_guide.md - Nature requirements
- assets/style-guides/science_guide.md - Science requirements
- assets/style-guides/cell_guide.md - Cell requirements
- assets/style-guides/plos_guide.md - PLOS requirements
- assets/style-guides/nih_guide.md - NIH grant guidelines
- assets/style-guides/nsf_guide.md - NSF grant guidelines
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

