Skip to content

LeoYeAI/agent-master-skills / skills/biomedical-paper-billing

biomedical-paper

Verified

AI-powered biomedical manuscript generation with docx output. Activates when user provides Chinese draft/outline and requests full English research paper. Includes: Abstract, Introduction, Methods, Results, Discussion, References. Specialized for: GBD epidemiology, cohort studies (CHARLS/NHANES), cross-sectional mediation analyses, pharmacovigilance (FAERS). Also supports: Chinese graduate/doctoral thesis (学位论文) formatting. Features: python-docx generation, Vancouver numbered references, journal-specific formatting. Confidence: High (validated workflow with 30+ successful papers)

FileKindSize
SKILL.mdskill md19.7 KB
_meta.jsonconfig309 B
assets/docx_builder.pyscript7.0 KB
package.jsonmanifest442 B
references/section-templates.mdmarkdown6.0 KB
references/style-guide.mdmarkdown2.0 KB

references/section-templates.md

View on GitHub
# Section Templates

## Abstract (GBD epidemiology style)

```
**Background:** [Disease X] is [brief definition and global significance]. Comparative analyses of [metric] between [countries/regions] remain limited. Using [GBD year] data, this study characterised [outcome] in [countries] from [year] to [year], with projections to [year].

**Methods:** [Key data extracted]. [Statistical methods: Joinpoint, ARIMA, decomposition, attribution]. All rates are per 100,000 population.

**Results:** From [year] to [year], [Country A] showed [key finding with numbers and CI/AAPC]. [Country B] showed [key finding]. [Projection result]. [Decomposition result]. [Attribution result].

**Conclusions:** [Burden level comparison]. [Divergent future trajectories]. [Mechanistic difference]. These findings provide evidence for [policy implication].
```

## Introduction

**Paragraph 1 — Disease overview:**
[Disease] is [definition] and [global significance/ranking]. Patients typically [clinical course]. Despite effective treatment, [residual burden: % unable to walk/mortality]. [Pathogenesis: antecedent trigger → immune mechanism]. [Recent etiological context: COVID-19/vaccine].

**Paragraph 2 — Epidemiological context + population aging:**
The epidemiology of [disease] varies substantially [geographic pattern]. [Subtype differences: country A vs country B]. [Aging as driver, cite GBD nervous system paper]. [COVID-19 pandemic impact, cite recent paper].

**Paragraph 3 — Research gap:**
Despite [context], long-term comparative analyses of [disease] burden between countries at [different SDI/development stage] remain limited. Most existing studies are [regional/cross-sectional/limited duration]. [Country A], [description]; [Country B], [description]. These contrasting settings offer a unique framework for [research rationale].

**Paragraph 4 — Study aims:**
Using [GBD year] data, this study aimed to: (i) characterise [outcome 1]; (ii) project [outcome 2]; (iii) quantify [decomposition]; and (iv) identify [attribution].

## Methods: Data Source

```
All data were extracted from the publicly available GBD [year] database (http://ghdx.healthdata.org/gbd-results-tool). The GBD study integrates multiple epidemiological data sources—including population registries, surveys, published literature, hospital records, and cause-of-death data—using standardised modelling frameworks to generate comparable burden estimates across countries and time periods. [Disease] was identified using ICD-10 code [X] and ICD-9 code [Y]. Four primary outcomes were extracted for [Countries] for [years]: prevalence case counts, YLDs case counts, age-standardized prevalence rates, and age-standardized YLDs rates, all expressed per 100,000 population, standardised against the GBD global standard population. This study used publicly available, de-identified aggregate data and received ethical clearance from the Institutional Review Board of the University of Washington; no additional ethical approval was required.
```

## Methods: Statistical Analysis — Joinpoint

```
Joinpoint regression was applied to age-standardized [rate] from [years] to identify statistically significant trend breakpoints. The optimal number of joinpoints was determined via Monte Carlo permutation tests. APC and 95% confidence intervals (CIs) were estimated for each trend segment; AAPC was calculated across the full study period to summarise the overall direction and magnitude of change.
```

## Methods: Statistical Analysis — ARIMA

```
Autoregressive integrated moving average (ARIMA) models were fitted to age-standardized GBS YLDs rates for each country using [years] historical data. Optimal model orders (p, d, q) were selected by the auto.arima algorithm based on the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). Forecasts for [years] are presented as point estimates with 95% prediction intervals (PIs).
```

## Methods: Demographic Decomposition

```
To disentangle the contributions of demographic and epidemiological factors to changes in total [disease]-related YLDs between [years], a standard three-component decomposition method was applied [cite]:

ΔYLDs = f(population growth) + f(population ageing) + f(age-specific rate change)

Population growth captures the effect of overall population size change; population ageing captures shifts in age structure; and age-specific rate change reflects the net epidemiological contribution independent of demographic factors.
```

## Discussion: Opening Paragraph (Core Findings)

```
This study provides [first/most comprehensive] longitudinal comparison of [disease] burden between [countries], integrating [N] years of historical data with [N]-year forward projections. Three key findings emerge. First, [burden level finding with magnitude]. Second, [trajectory finding: stable vs. rising]. Third, [mechanistic/driver finding: fundamental difference].
```

## Discussion: Limitations Paragraph

```
Several limitations should be acknowledged. First, GBD estimates for [rare/common] conditions carry inherent model-based uncertainty, particularly in settings with sparse primary epidemiological data; [specific issue, e.g., underdiagnosis in Country X] may lead to systematic [over/under]estimation. Second, the ecological study design precludes causal inference. Third, [disease-specific limitation, e.g., cannot distinguish subtypes]. Fourth, ARIMA projections assume continuation of historical trends and cannot fully account for future disruptions such as [new pandemic/policy changes].
```

## Discussion: Conclusion Paragraph

```
In conclusion, [main burden comparison finding]. [Divergent trajectory statement]. The mechanistic pathways driving burden change differ fundamentally: [Country A] is shaped by [driver], while [Country B]'s burden is primarily driven by [driver], with [offset factor] largely [containing/exacerbating] the total impact. These findings provide a critical evidence base for country-specific, targeted [disease] prevention and management strategies, and highlight the need for enhanced [surveillance/collaboration/research].
```
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall