paper-tweet-generator

> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
# Paper Reading Tweet Generator

This skill analyzes an academic paper (PDF, Word, or Text) and generates a structured reading tweet including basic info, background, results, and conclusion. It can highlight specific product/drug advantages and ensures standardized terminology.

## When to Use

- Use this skill when the request matches its documented task boundary.
- Use it when the user can provide the required inputs and expects a structured deliverable.
- Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming.

## Key Features

- Scope-focused workflow aligned to: Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages. Use when the user wants to turn a document into a social media post or reading summary.
- Packaged executable path(s): `scripts/extract_pdf.py` plus 1 additional script(s).
- Reference material available in `references/` for task-specific guidance.
- Structured execution path designed to keep outputs consistent and reviewable.

## Dependencies

- `Python`: `3.10+`. Repository baseline for current packaged skills.
- `Third-party packages`: `not explicitly version-pinned in this skill package`. Add pinned versions if this skill needs stricter environment control.

## Example Usage

```bash
cd "20260316/scientific-skills/Others/paper-tweet-generator"
python -m py_compile scripts/extract_pdf.py
python scripts/extract_pdf.py --help
```

Example run plan:
1. Confirm the user input, output path, and any required config values.
2. Edit the in-file `CONFIG` block or documented parameters if the script uses fixed settings.
3. Run `python scripts/extract_pdf.py` with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

## Implementation Details

See `## Workflow` above for related details.

- Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
- Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
- Primary implementation surface: `scripts/extract_pdf.py` with additional helper scripts under `scripts/`.
- Reference guidance: `references/` contains supporting rules, prompts, or checklists.
- Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
- Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

## Workflow

To generate a tweet, follow these steps sequentially:

### 1. Locate and Extract Content
First, locate the file and extract its text content.
- **Locate File**: If the user provides a file path, use it. If not (e.g., "uploaded file"), use `Glob` to search for `.pdf`, `.docx`, or `.txt` files in the **entire workspace** (pattern: `**/*.pdf`). Select the most relevant file (e.g., recently added).
- **Extract Text**: 
  - Recommend using an output file to avoid console buffer limits.
  - Run: `python scripts/extract_text.py <file_path> extracted_content.txt`
  - Read the content: `Read extracted_content.txt`
- **Handle Output**:
    - If the extraction fails or returns empty text (check stderr logs), inform the user.
    - If "Warning: No text extracted" is logged, the PDF is likely a scanned image.
- **Fallback**: If the script fails, try reading the file directly with built-in tools (only for text files).

### 2. Generate Tweet Sections
Use the extracted text to generate the following sections using the prompts in `references/prompt_templates.md`.
*Note: If the extracted text is very long (> 50k chars), focus on the Abstract, Introduction, Results, and Conclusion sections.*

- **Basic Info**: Extract title, authors, journal, DOI.
- **Background**: Summarize the research background (< 500 words).
- **Results**: Summarize key findings highlighting the product (< 800 words).
- **Conclusion**: Summarize the main conclusion.

### 3. Final Assembly
- **Title**: Generate a catchy title based on the extracted info.
- **Assembly**: Assemble the final tweet in Markdown including all sections.

## Requirements

*   Python environment with `pypdf` and `python-docx` installed.
*   Access to an LLM for content extraction.

## Scripts

*   `scripts/extract_text.py`: Extracts raw text from PDF, Word, or Text files. Supports output to file for large documents.

## References

*   `references/prompt_templates.md`: Prompts for extracting and summarizing each section.

## When Not to Use

- Do not use this skill when the required source data, identifiers, files, or credentials are missing.
- Do not use this skill when the user asks for fabricated results, unsupported claims, or out-of-scope conclusions.
- Do not use this skill when a simpler direct answer is more appropriate than the documented workflow.

## Required Inputs

- A clearly specified task goal aligned with the documented scope.
- All required files, identifiers, parameters, or environment variables before execution.
- Any domain constraints, formatting requirements, and expected output destination if applicable.

## Output Contract

- Return a structured deliverable that is directly usable without reformatting.
- If a file is produced, prefer a deterministic output name such as `paper_tweet_generator_result.md` unless the skill documentation defines a better convention.
- Include a short validation summary describing what was checked, what assumptions were made, and any remaining limitations.

## Validation and Safety Rules

- Validate required inputs before execution and stop early when mandatory fields or files are missing.
- Do not fabricate measurements, references, findings, or conclusions that are not supported by the provided source material.
- Emit a clear warning when credentials, privacy constraints, safety boundaries, or unsupported requests affect the result.
- Keep the output safe, reproducible, and within the documented scope at all times.

## Failure Handling

- If validation fails, explain the exact missing field, file, or parameter and show the minimum fix required.
- If an external dependency or script fails, surface the command path, likely cause, and the next recovery step.
- If partial output is returned, label it clearly and identify which checks could not be completed.

## Quick Validation

Run this minimal verification path before full execution when possible:

```bash
python scripts/extract_pdf.py --help
```

Expected output format:

```text
Result file: paper_tweet_generator_result.md
Validation summary: PASS/FAIL with brief notes
Assumptions: explicit list if any
```