科研 Skill
食品营养论文图表系统
food-figure
Builds publication-ready figures (bar/box, dose-response, PCA, heatmaps, forest plots) to a target journal’s spec, with a privacy scan before delivery. Use for a journal-ready figure.
SKILL.md
Food-Figure — Data-Driven Figure System for Food & Nutrition Science
Turn a dataset (or a described result) into the right submission-grade figure. The chart serves the scientific logic; polish is subordinate to making the core conclusion clear, defensible, and reviewable. Original work; architecture informed by open community figure skills (see the repo README Acknowledgements).
Load reference files as needed (progressive disclosure) — don't read them all
up front. The map is in the frontmatter references list.
Workflow
flowchart TD
A[Data or described result] --> B[1. Analyze the data<br/>scripts/analyze_data.py -> profile]
B --> C[2. Recommend figures<br/>references/data-to-figure.md]
C --> D[3. Figure contract<br/>references/figure-contract.md]
D --> E{Backend?}
E -- unknown --> Eq[Ask 'Python or R?' once<br/>scripts/backend_pref.py]
E -- known --> F
Eq --> F[4. Render<br/>python-guide.md OR r-guide.md + food-recipes.md]
F --> G[5. Export at journal spec<br/>references/journal-specs.md]
G --> H[6. QA<br/>references/qa-checklist.md]
H --> OUT[Journal-ready SVG/PDF/TIFF + editable source]
1 — Analyze the data
If the user supplies a data file (CSV/TSV/Excel) or table, profile it first:
run scripts/analyze_data.py <file> to get, per column, the type
(numeric/categorical/datetime), cardinality, missingness, distribution summary,
and the detected structure (grouping factors, repeated measures, time/dose axis,
wide sensory/composition matrix). If the user only describes a result, elicit the
same: what varies, what's measured, n, and the error type. See
references/data-to-figure.md.
2 — Recommend the figure(s)
From the profile, propose the best figure type(s) with a one-line rationale
each, and say what each would show. Prefer the figure that makes the paper's
claim most directly; note honest alternatives. The decision rules and a full
catalog are in references/data-to-figure.md and references/chart-types.md.
Never force a chart the data can't support (e.g. bar-of-means where a
distribution matters → box/violin + points).
3 — Figure contract + provenance (before code)
Fix the conclusion, evidence logic, export needs (target journal), and review
risks (references/figure-contract.md). Open a figure trace card
(references/figure-provenance.md): the real data source, the script that makes
the figure, what it shows, and the claim it supports — so the plotted values match
the reported statistics. Choose the palette by data type
(references/color-palettes.md).
For a dense Figure 1/2-style request, first design the complete evidence story
with references/figure-story-design.md: experimental sequence, evidence
hierarchy, non-redundant panel questions, source-data map, opening schematic, and
an integrated synthesis panel. Do not start by filling a grid with chart types.
4 — Backend gate (blocking)
- Data figures → Python or R (always). Resolve the backend by priority:
explicit request → language of the user's input files/data → saved preference
(
python scripts/backend_pref.py get) → ask once ("Python or R? I'll remember this") and save it (backend_pref.py set python|r). The chosen backend does all data graphics, preview, and export; the other may only help with data prep/conversion. - AI image route (opt-in, schematics only). Only if the user explicitly
asks to generate the image with Gemini, ChatGPT, or Claude (or another
named image model) — and only for conceptual visuals (mechanism diagrams,
graphical abstracts, process schematics) — use that model instead. Never use
an AI image model for a data-bearing figure, and never let it invent data. See
references/ai-image-generation.md.
5 — Render & export
Use the selected backend's guide (python-guide.md = matplotlib/seaborn/
subplot_mosaic/statsmodels; r-guide.md = ggplot2/patchwork/ComplexHeatmap/
ggrepel + svglite/cairo_pdf/ragg) plus food-recipes.md for the food/nutrition
figure types. Start from the template library — examples/python_food_figures.py
or examples/r_food_figures.R — which has a ready function for every figure type;
adapt it to the user's data. Export vector (PDF/SVG) for line/bar/scatter and
TIFF (LZW) at the journal DPI for raster/microscopy; keep an editable source.
Pull DPI, column width, font, and format from the target journal via
references/journal-specs.md; if no journal is set, default to 300 dpi, ~90/190 mm
widths, TIFF+PDF, Arial 7–9 pt.
6 — QA
Run references/qa-checklist.md before delivering (error bars defined + n;
statistics shown consistently; axes honest; colorblind-safe; labels legible at
final size; matches journal spec; every panel cited). Privacy: any code or
legend you hand back must use relative paths, never local machine paths — scan
with python3 scripts/privacy_scan.py (see
food-paper/references/privacy-and-confidentiality.md).
Deliver
Hand back, per figure: the file(s) (vector + raster), the figure trace card,
a self-contained caption (APA 7.0 or the journal's style — see
references/figure-provenance.md), and the plotting code. For a .tex build,
include the \includegraphics environment.
Modes
- recommend — analyze data and suggest figures, no rendering yet.
- make (default) — full pipeline to a rendered, exported figure + caption + trace card.
- revise / audit — critique or fix an existing figure against the QA checklist and journal spec.
- multi-panel — compose labelled panels (a, b, c) that share a logical thread.
- figure-story — design and render an 8–12 panel journal-style evidence narrative from experimental design through primary results, diagnostics, robustness, and an integrated conclusion.
- schematic — a graphical abstract / mechanism diagram: Python/R by default, or the opt-in AI-image route (
references/ai-image-generation.md) if the user asks.
Scope
Reproducible, code-generated, submission-grade scientific figures for food &
nutrition. Not for dashboards or Illustrator/Figma-first artwork. A
schematic/graphical-abstract (mechanism diagram) is a drawing task: keep it in
Python/R by default, or — only if the user explicitly asks — generate it with an
AI image model (Gemini/ChatGPT/Claude) per references/ai-image-generation.md.
Data figures are always Python/R.
Handoff
Called by food-paper's viz_designer at the journal spec; figures feed the
manuscript's Results.
示例提示词
帮我把这组感官评价数据做成符合目标期刊规范的雷达图。
所属插件
安装该插件会一并获得同领域的 20 个 Skill / MCP。
同插件的其他科研 Skill
- 农业深度研究综述Deep research producing a source-validated literature review for an agricultural question, ranked by journal quartile. Reuses food-deep-research machinery. Use for an agronomy deep dive.
- 农业科学论文撰写系统Multi-subagent manuscript system for agricultural science with field-trial/soil/animal reporting standards. Reuses food-paper machinery. Use for an agronomy or soil-science manuscript.
- 农业研究全流程编排Orchestrates the full agricultural research-to-publication workflow: journal selection, research, writing, figures, peer review, revision. Use to manage an agronomy project end to end.
- 农业综述转可编辑PPTConverts an agricultural-science report or manuscript into a fully editable PowerPoint deck, reusing food-ppt machinery with agronomy framing. Use for slides from a field-trial report.
- 农业遥感作物制图Maps crop types from Sentinel-2 imagery with Random Forest, extracts NDVI phenology, estimates LAI, and predicts yield via Google Earth Engine. Use for field/county crop remote sensing.
- 农业文献证据综合Multi-source literature and evidence-synthesis workflow for agricultural science, ranked by journal quartile. Reuses food-research machinery. Use for an agronomy or soil-science evidence review.
- 农业论文多审稿人模拟Simulates an editorial peer-review panel for an agricultural manuscript, grounded in cited and field literature. Use for a pre-submission review or mock referee report in agriculture.
- 作物生长模拟Simulates crop growth with WOFOST/AquaCrop via PCSE, pulls weather from NASA POWER, and runs yield-gap analysis under climate scenarios. Use for agronomic intervention evidence.
- 田间试验混合模型分析Analyzes RCBD, split-plot, and multi-site field-trial data with mixed models in R (lme4) or Python (statsmodels), using correct error strata. Use for a crop or soil field-trial analysis.
- 通用深度文献综述研究General-purpose deep research producing a source-validated, fully written literature review via a 12-subagent team. Use for a thorough review or deep-dive needing verified sources.
- 学术文献全文合法获取Lawfully acquires full-text PDFs via open access, the user’s reference manager, or their logged-in library session; never bypasses paywalls. Use to fetch papers before research or review.
- 食品科学论文撰写系统Multi-subagent manuscript system for food/nutrition science: frames questions, analyzes data, writes statistics, drafts, polishes, and reformats for a journal. Use to write or revise a paper.
- 食品研究全流程编排Orchestrates the whole food/nutrition research-to-publication workflow with quality gates: journal selection, research, writing, figures, review, revision. Use to manage a paper end to end.
- 食品研究报告转可编辑PPTConverts a food/agriculture report or manuscript into a fully editable PowerPoint deck with python-pptx: outline, grounded slide text, themed layout. Use to make slides from a paper.
- 科研基金申请书编排Orchestrates a food/agriculture funding proposal to a scheme’s format (headings, length limit, criteria), drafting or revising via the research/paper/review skills. Use for a grant application.
- 食品营养文献综合研究Runs a multi-source literature and evidence-synthesis workflow for food/nutrition science: search, two-phase screening, synthesis, evidence grading. Use for a deep review or systematic-review scope.
- 食品论文多审稿人模拟Simulates an editorial peer-review panel for a food/nutrition manuscript, grounded in cited and field literature first. Use for a pre-submission review or mock referee report.
- FAOSTAT食品系统数据分析Analyzes FAOSTAT food-balance, dietary-diversity, and trade/production data for cross-country food-systems indicators. Use for a country-comparison food-security dataset.
- 土壤数据空间分析Pulls and analyzes soil properties from SoilGrids (global) and SSURGO (US-only), computes SOC stock, and runs kriging interpolation. Use for a soil-property or soil-carbon map.
常见问题
食品营养论文图表系统能做什么?
Builds publication-ready figures (bar/box, dose-response, PCA, heatmaps, forest plots) to a target journal’s spec, with a privacy scan before delivery. Use for a journal-ready figure。
如何安装食品营养论文图表系统?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「食品营养论文图表系统」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
食品营养论文图表系统需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
食品营养论文图表系统经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。