literature-extensive-read
Rapidly skim and summarize academic papers (default:PDF-to-Markdown full text with `## Page XX` pagination and image references) and output a structured extensive-reading summary in Markdown when you need to quickly understand research questions, methods, key results, conclusions, and decide whether intensive reading is worthwhile.
Best use case
literature-extensive-read is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Rapidly skim and summarize academic papers (default:PDF-to-Markdown full text with `## Page XX` pagination and image references) and output a structured extensive-reading summary in Markdown when you need to quickly understand research questions, methods, key results, conclusions, and decide whether intensive reading is worthwhile.
Teams using literature-extensive-read 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/literature-extensive-read/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How literature-extensive-read Compares
| Feature / Agent | literature-extensive-read | 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?
Rapidly skim and summarize academic papers (default:PDF-to-Markdown full text with `## Page XX` pagination and image references) and output a structured extensive-reading summary in Markdown when you need to quickly understand research questions, methods, key results, conclusions, and decide whether intensive reading is worthwhile.
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 and need a fast, structured overview before deciding to read it deeply. - You need to extract the research question, methodology, main findings, and conclusions for literature triage. - You are reviewing many papers and want consistent summaries using a fixed template. - You want a quick interpretation of figures/tables referenced as images in the Markdown (only based on what is explicitly shown/described). - You need to produce a UTF-8 Markdown summary file saved to a standard output directory for later review. ## Key Features - Rapid extensive reading workflow: prioritize title/abstract/conclusion, then scan methods and results. - Structured output using a predefined Markdown template. - Supports PDF-to-Markdown inputs that include `## Page XX` pagination headers. - Allows using embedded image references (e.g., ``) to briefly describe charts/tables when explicitly interpretable. - Strictly summarizes only explicit content from the provided text (no speculation); missing items are marked as **“Not specified”**. - Standardized output location: saves results to `outputs/` (created if missing). ## Dependencies - `pdf-extract` (version: Not specified) — used only when the input is PDF and must be converted to Markdown first. - `securityclaw` (version: Not specified) — optional security audit report saved alongside outputs. ## Example Usage ### Input Assume you have one of the following: 1) A PDF-to-Markdown file (recommended): - `paper.md` (contains full text, may include `## Page XX` and image references) 2) Only a PDF: - `paper.pdf` (convert it first using `pdf-extract`) ### Steps 1) **(Optional) Convert PDF to Markdown** ```bash pdf-extract paper.pdf > paper.md ``` 2) **Read and summarize using the template** - Read `paper.md`, prioritizing: **Title → Abstract → Conclusion**, then scan **Methods** and **Results**. - Follow requirements and quality checks in: - `references/guide.md` - Fill the output template: - `assets/rapid_summary_template.md` - If any field cannot be found in the text, write: **Not specified**. 3) **Save output** - Save the completed summary as a UTF-8 encoded Markdown file to: - `outputs/rapid_summary.md` 4) **(Optional) Save security audit report** - If generated, save the `securityclaw` report to: - `outputs/` ## Implementation Details - **Input format** - Default input is full-text Markdown converted from PDF. - Pagination headers like `## Page XX` may appear and should be treated as page markers, not section headings. - Image references (e.g., ``) may be used to support brief figure/table descriptions **only when the content is explicitly interpretable**. - **Reading strategy (algorithm)** 1. Extract bibliographic and high-level intent from **Title/Abstract**. 2. Identify the **research question(s)** and scope. 3. Scan **Methods** to capture: data, experimental setup, models, baselines, evaluation metrics, and key parameters (only if explicitly stated). 4. Scan **Results** to capture the main quantitative/qualitative findings and comparisons. 5. Read **Conclusion/Discussion** to capture claims, limitations, and future work. 6. Produce an **intensive-reading recommendation** based on the paper’s stated contributions, clarity of evidence, and relevance to the user’s goal (when provided). - **Output rules** - Use `assets/rapid_summary_template.md` as the sole structure for the final summary. - If information is missing or unclear in the source text, write **Not specified** (do not infer). - Output must be Markdown (`.md`) and saved in **UTF-8** to avoid encoding issues. - Default output language is Chinese unless the user explicitly requests another language.
Related Skills
word-read-write
Create and read Microsoft Word (.docx) documents. Use this skill when you need to generate reports/letters/templates as .docx or extract readable text from existing .docx files.
spreadsheet-ops
Spreadsheet processing and analysis for CSV/Excel; trigger when users ask to merge/clean tabular data, run statistics, add/edit Excel formulas, apply formatting, generate charts, or force workbook recalculation.
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.
literature-statistics
Generate statistics for publication-year and journal distributions from local references or PDFs; use when you need standardized Year/Journal tables and a summary without any network access.
literature-management
Import local literature into a managed library; trigger when you need offline deduplication, tagging, and a searchable index.
content-proofreading
An academic proofreading skill for Chinese/English manuscripts, triggered when you need automated checks for spelling, grammar, terminology consistency, and formatting before submission.
literature-filtering
Filter literature by publication year, journal, and predefined screening rules to produce inclusion/exclusion lists; use when conducting preliminary screening or systematic review screening to narrow the literature scope.
literature-experiment-extract
Extract experimental models, experimental methods, and biomarker information from paper Markdown (typically produced by PDF-to-Markdown tools) when a user provides paper Markdown and needs a structured, evidence-backed summary (1 Markdown + 3 CSVs).
literature-close-read
Produce a structured close-reading report from a paper's full PDF-to-Markdown text (with `## Page XX` pagination and image references) when you need to systematically extract background, research questions, methods, results, limitations, and reproducible experimental details.
multi-database-literature-collector
Collects candidate biomedical literature across multiple databases, adapts search logic by database, preserves source metadata, and organizes results into a structured, screening-ready candidate pool. Always use this skill when a user wants cross-database literature collection, search strategy construction, candidate paper aggregation, or first-pass evidence organization before deduplication, screening, layered reading, or review planning. Requires real and verifiable literature records only. Every formal literature item must include a real link and DOI when available; never fabricate citations, titles, authors, years, journals, abstracts, PMIDs, or DOIs. If a DOI is unavailable or cannot be verified, state that explicitly rather than inventing one.
medical-research-literature-reader-pro
A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title. Triggers include requests like "analyze this paper", "critique this study", "is this a strong paper?", "give me similar studies", "prepare me for journal club", "help me understand this bioinformatics paper", "what are the weaknesses here?", or "turn this into a mind map". Also activate for any downstream deliverables such as journal club kits, comparison tables, PI decision briefs, replication starters, or follow-up experiment designs. Do NOT treat as a generic summarizer — this skill performs structured evidence-type classification, track-specific critical appraisal, interpretation-boundary judgment, and research-grade follow-up generation.
figure-first-paper-reader
Reads a paper figure by figure before re-integrating the full narrative, so the user can identify the core findings quickly and check whether each visual actually supports the authors' main claims. Always separate figure content, figure-linked claim, evidentiary strength, and unsupported interpretation. Never fabricate references, PMIDs, DOIs, figure content, panel labels, result values, or study details that were not actually provided.