$npx -y skills add neuromechanist/research-skills --skill manuscript-writingUse this skill for \"write a paper\", \"draft manuscript\", \"write introduction\", \"write methods section\", \"write results\", \"write discussion\", \"write abstract\", \"structure a paper\", \"academic writing\", \"write for journal\", or when the user wants to draft or revis
| 1 | # Academic Manuscript Writing |
| 2 | |
| 3 | Guide the drafting and revision of academic manuscripts following journal conventions and scientific writing best practices. |
| 4 | |
| 5 | ## When to Use |
| 6 | |
| 7 | - Drafting a new manuscript from scratch |
| 8 | - Writing or revising specific sections (Introduction, Methods, Results, Discussion) |
| 9 | - Structuring a paper from experimental results |
| 10 | - Converting a conference paper to a journal submission |
| 11 | - Responding to reviewer comments with revised text |
| 12 | |
| 13 | ## Manuscript Structure |
| 14 | |
| 15 | ### Standard IMRAD Format |
| 16 | |
| 17 | | Section | Purpose | Tense | Length Guide | |
| 18 | |---------|---------|-------|-------------| |
| 19 | | Title | Convey main finding | N/A | 10-15 words | |
| 20 | | Abstract | Self-contained summary | Past (methods/results), Present (conclusions) | 150-300 words | |
| 21 | | Introduction | Context, gap, hypothesis | Present (known facts), Past (prior work) | 3-5 paragraphs | |
| 22 | | Methods | Reproducibility | Past | As needed | |
| 23 | | Results | Report findings | Past | Parallel to Methods | |
| 24 | | Discussion | Interpret findings | Present (interpretation), Past (what was found) | 4-6 paragraphs | |
| 25 | | Conclusion | Key takeaways | Present | 1-2 paragraphs | |
| 26 | |
| 27 | ### Section-by-Section Guidance |
| 28 | |
| 29 | #### Introduction |
| 30 | Structure as a funnel: |
| 31 | 1. **Broad context** - Establish the field and importance (1-2 paragraphs) |
| 32 | 2. **Narrow focus** - What is known about the specific topic (1-2 paragraphs) |
| 33 | 3. **Gap statement** - What remains unknown or problematic |
| 34 | 4. **Objective/hypothesis** - What this paper addresses and how |
| 35 | |
| 36 | #### Methods |
| 37 | - Enough detail for replication |
| 38 | - Subsections mirror Results sections |
| 39 | - Include: participants/subjects, materials, procedures, analysis |
| 40 | - Statistical methods: specify tests, software, significance thresholds |
| 41 | - Ethics: IRB/IACUC approval statement |
| 42 | |
| 43 | #### Results |
| 44 | - Present findings without interpretation |
| 45 | - Start each subsection with the analysis performed, then the outcome |
| 46 | - Report effect sizes, confidence intervals (not just p-values) |
| 47 | - Reference figures and tables in order |
| 48 | - Use "significant" only for statistical significance |
| 49 | |
| 50 | #### Discussion |
| 51 | Structure: |
| 52 | 1. **Summary of key findings** (1 paragraph) |
| 53 | 2. **Interpretation in context** of prior literature (2-3 paragraphs) |
| 54 | 3. **Limitations** (1 paragraph, honest but not self-defeating) |
| 55 | 4. **Future directions** (1 paragraph) |
| 56 | 5. **Conclusion** (1 paragraph) |
| 57 | |
| 58 | ## Writing Principles |
| 59 | |
| 60 | ### Clarity |
| 61 | - One idea per sentence |
| 62 | - Active voice preferred ("We measured..." not "Measurements were taken...") |
| 63 | - Define abbreviations on first use |
| 64 | - Avoid jargon unless writing for a specialist audience |
| 65 | |
| 66 | ### Precision |
| 67 | - Quantify claims ("increased by 23%" not "significantly increased") |
| 68 | - Cite sources for factual claims |
| 69 | - Distinguish correlation from causation |
| 70 | - Use hedging appropriately ("suggests" vs "proves") |
| 71 | |
| 72 | ### Flow |
| 73 | - Each paragraph: topic sentence, evidence, interpretation |
| 74 | - Transitions between paragraphs connect ideas |
| 75 | - Logical progression within and across sections |
| 76 | - Consistent terminology (don't alternate between synonyms for key concepts) |
| 77 | |
| 78 | ### Citations |
| 79 | - Cite primary sources, not reviews (when possible) |
| 80 | - Recent citations show awareness of current literature |
| 81 | - Cite competing or contradictory findings |
| 82 | - Self-citation should be relevant, not gratuitous |
| 83 | |
| 84 | ## Revision Checklist |
| 85 | |
| 86 | After drafting, check: |
| 87 | - [ ] Abstract accurately reflects the paper content |
| 88 | - [ ] Introduction gap statement matches the study objective |
| 89 | - [ ] Methods are sufficient for replication |
| 90 | - [ ] Results match Methods (parallel structure) |
| 91 | - [ ] Discussion addresses all major findings |
| 92 | - [ ] Figures are referenced in text in order |
| 93 | - [ ] All abbreviations defined on first use |
| 94 | - [ ] References complete and consistently formatted |
| 95 | - [ ] Word/page count within journal limits |
| 96 | - [ ] Run `manuscript:humanizer` as a final natural-writing pass (strips AI tells like significance inflation, em-dashes, "evolving landscape" filler, rule-of-three padding) before review |
| 97 | |
| 98 | ## Additional Resources |
| 99 | |
| 100 | - Reference: [references/section-templates.md](references/section-templates.md) - Templates for each manuscript section |
| 101 | - Reference: [references/revision-response.md](references/revision-response.md) - How to write point-by-point responses to reviewers |
| 102 | - Sister skill: `manuscript:humanizer` - Removes 29 categories of AI-writing tells while respecting academic conventions (e.g., passive voice in Methods, hedging in Discussion). Run after drafting and before peer review. |