literatureimages-interpretation
Interpret figures in academic papers and their captions when the input is a PDF-to-Markdown document with page markers and image links, producing a structured Markdown report for extracting variables, trends, and conclusions.
Best use case
literatureimages-interpretation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Interpret figures in academic papers and their captions when the input is a PDF-to-Markdown document with page markers and image links, producing a structured Markdown report for extracting variables, trends, and conclusions.
Teams using literatureimages-interpretation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/literatureimages-interpretation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How literatureimages-interpretation Compares
| Feature / Agent | literatureimages-interpretation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Interpret figures in academic papers and their captions when the input is a PDF-to-Markdown document with page markers and image links, producing a structured Markdown report for extracting variables, trends, and conclusions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
## When to Use
- You have a paper converted from PDF to Markdown (including `## Page XX` markers and image links) and need a figure-by-figure interpretation report.
- You need to extract key variables, trends, comparisons, and conclusions primarily from charts/plots rather than from the main text.
- You want to align images in a `*-images/` folder with figure numbers (e.g., Figure 1A, Figure 2) using captions and in-text citations.
- You need a standardized, UTF-8 Markdown output suitable for downstream summarization, data extraction, or knowledge base ingestion.
- You must filter out non-figure images (e.g., scanned body text blocks) and interpret only chart-like content.
## Key Features
- Parses Markdown image links and locates the corresponding `*-images/` directory (e.g., `RateSOX2.md` → `RateSOX2-images/`).
- Opens **every** image in the images folder without skipping and classifies each as chart / table / schematic / flowchart / body-text block.
- Builds an internal (non-exported) alignment list to map images to figure numbers using captions and body-text citations.
- Interprets **only chart-type** images (and other figure-like visuals when required), excluding body-text blocks.
- Produces a single structured “Image Interpretation” Markdown report per input file, saved to `outputs/`.
- Enforces evidence-based interpretation: rely only on captions, body text, and visible image content; do not speculate.
## Dependencies
- `pdf-extract` (version: not specified) — used only when the source is PDF and must be converted to Markdown first.
- Markdown template: `assets/figure_interpretation_template.md` (version: not specified)
- Quality/requirements reference: `references/guide.md` (version: not specified)
## Example Usage
### Input layout
```
skill/
literatureimages-interpretation/
inputs/
RateSOX2.md
RateSOX2-images/
image_001.png
image_002.png
...
assets/
figure_interpretation_template.md
references/
guide.md
outputs/
```
### Run (conceptual workflow)
1. If starting from PDF, convert to Markdown first:
```bash
pdf-extract RateSOX2.pdf > skill/literatureimages-interpretation/inputs/RateSOX2.md
```
2. Ensure the images folder exists and matches the literature name:
- `inputs/RateSOX2.md`
- `RateSOX2-images/`
3. Execute the interpretation process:
- Read `inputs/RateSOX2.md` (captions + in-text citations + image links).
- Open every image in `RateSOX2-images/` sequentially.
- Classify images; keep only chart/figure-like items for interpretation.
- Align images to figure numbers (e.g., Figure 1A) when possible; otherwise mark as **Unassigned**.
- Fill `assets/figure_interpretation_template.md`.
- Write exactly one UTF-8 Markdown output to:
- `outputs/RateSOX2_figure_interpretation.md` (example name; keep it concise)
### Output (must be a single Markdown file)
- Location: `outputs/`
- Content: **only** the “Image Interpretation” section (do **not** include the internal image list table)
- Encoding: UTF-8
## Implementation Details
- **Input assumptions**
- Default input is a PDF-to-Markdown file (`.md`) containing:
- page markers like `## Page XX`
- image links
- captions and surrounding body text
- If only a PDF is provided, convert it to Markdown using `pdf-extract` before interpretation.
- **Image discovery**
- Images are typically stored in a folder named `*-images/` matching the literature filename.
- Use Markdown image links and/or folder naming to locate the correct images.
- **Mandatory full pass over images**
- Open **every** image in the `*-images/` folder without skipping.
- Classify each image into one of:
- chart/plot
- table
- schematic
- flowchart
- body text block (to be excluded from interpretation)
- **Figure attribution (alignment)**
- Use captions and in-text citations to assign figure identifiers (e.g., Figure 2, Fig. 3B).
- If attribution cannot be determined, label the item as **Unassigned**.
- Maintain an internal alignment list for processing only; **do not** generate or export any image list file.
- **Interpretation scope and constraints**
- Interpret **only** chart-type (and other figure-like) images that require analysis; exclude body-text blocks.
- Interpretations must be grounded in:
- visible content in the image (axes, legends, labels, values, trends)
- caption text
- relevant body text citations
- Do not infer beyond the evidence; if information is missing, write **“Not specified”**.
- **Output rules**
- Use `assets/figure_interpretation_template.md` as the structure.
- Output exactly **one** Markdown file per input document.
- Save to `outputs/` with a concise filename (avoid redundant phrases).
- Do not include the internal image list table; output only the final “Image Interpretation” content.
- Ensure UTF-8 encoding to prevent character corruption.
- **Quality checks**
- Follow detailed requirements and checkpoints in `references/guide.md`.Related Skills
graph-interpretation
Use when interpreting scientific graphs and charts, explaining data visualizations for research presentations, writing figure captions for publications, or analyzing trends in clinical research data. Converts complex visual data into clear, accurate explanations for academic papers, clinical reports, and public presentations.
skill-auditor
A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.
two-sample-mr-research-planner
Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
research-proposal-generator
Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.
research-grants
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA.
protocol-standardization
Standardize fragmented experimental steps into reproducible protocol documents when you need method organization, lab SOP drafting, or cross-operator reproducibility; missing parameters must be explicitly marked as "To be supplemented/Not provided".
prospero-registration-helper
Assists researchers in generating PROSPERO registration content for meta-analyses from a title and optional protocol. Use when the user wants to draft a PROSPERO registration form.
non-tumor-ml-research-planner
Generates complete non-tumor biomedical machine learning research designs from a user-provided research direction. Always use this skill when users want to plan bioinformatics + ML papers for non-cancer diseases (metabolic, cardiovascular, kidney, inflammatory, autoimmune, infectious, neurological, endocrine, wound healing, chronic multifactor), design diagnostic biomarker studies, combine GEO datasets with feature selection and ML modeling, or generate Lite/Standard/Advanced/Publication+ workload plans. Trigger for:"non-tumor ML study", "bioinformatics paper outside oncology", "key genes and diagnostic model for a disease", "pyroptosis/ferroptosis/senescence/autophagy + disease", "GEO datasets + machine learning", "RF + LASSO diagnostic model", "DEG + feature selection + validation", "immune infiltration + biomarker", "non-cancer biomarker paper". Trigger even for casual phrasings like "I want to study X using machine learning", "help me design a non-tumor bioinformatics paper", or "how do I build a diagnostic model for disease Y".
network-tox-docking-research-planner
Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for:"network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings:"网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
meta-protocol-writer
Generates a PROSPERO-compliant Meta-analysis protocol based on Title and PICOS. Use when the user wants to write a protocol for a systematic review or meta-analysis.
hypothesis-generation
Structured scientific hypothesis formulation from observations; use when you have experimental observations or preliminary data and need testable hypotheses with predictions, mechanisms, and validation experiments.
hypogenic
Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.