Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.
Overview
AI-powered academic summarization tool that condenses complex research papers into publication-ready structured abstracts while preserving scientific accuracy and key findings.
Key Capabilities:
Multi-Format Input: Process PDFs, text, URLs, or clipboard content
Structured Output: Background, Objective, Methods, Results, Conclusion format
Word Count Enforcement: Strict 250-word limit with validation
Quantitative Preservation: Retains key numbers, statistics, and effect sizes
Discipline Adaptation: Optimized for STEM, medical, and social sciences
Extract and condense key sections into standard format:
from scripts.summarizer import AbstractSummarizer
summarizer = AbstractSummarizer()
# Generate from PDF
abstract = summarizer.summarize(
source="paper.pdf",
format="structured", # structured, plain, or executive
word_limit=250,
discipline="biomedical"# affects terminology handling
)
print(abstract.text)
# Output: Background → Objective → Methods → Results → Conclusion
Output Structure:
**Background**: [Context and problem statement]
**Objective**: [Research goal and hypotheses]
**Methods**: [Study design, sample, key methods]
**Results**: [Primary findings with statistics]
**Conclusion**: [Implications and significance]
---
Word count: 247/250
2. Quantitative Data Preservation
Ensure numbers and statistics are accurately retained:
# Extract and verify quantitative results
quant_results = summarizer.extract_quantitative(
text=paper_content,
priority="high"# keep all numbers vs. representative samples
)
# Validate against original
validation = summarizer.verify_accuracy(
abstract=abstract,
source=paper_content
)
Preserves:
Sample sizes (n=128)
Effect sizes (Cohen's d = 0.82)
P-values (p < 0.001)
Confidence intervals (95% CI: [0.45, 0.78])
Percentages and absolute numbers
3. Multi-Disciplinary Adaptation
Adjust extraction strategy by field:
# Biomedical paper
python scripts/main.py --input paper.pdf --field biomedical
# Physics paper
python scripts/main.py --input paper.pdf --field physics
# Social science paper
python scripts/main.py --input paper.pdf --field social-science
Field-Specific Handling:
Field
Focus Areas
Special Handling
Biomedical
Study design, statistical significance, clinical relevance
journal_requirements.md - Word limits by publisher
example_abstracts.md - High-quality examples by type
Scripts
Located in scripts/ directory:
main.py - CLI interface for summarization
summarizer.py - Core abstract generation engine
extractor.py - PDF and text extraction
validator.py - Accuracy checking and verification
batch_processor.py - Multi-document processing
adapter.py - Journal-specific formatting
Limitations
Language: Optimized for English-language papers
Length: Papers >50 pages may need section-by-section processing
Complexity: Highly mathematical content may lose nuance
Figures: Cannot interpret images, charts, or graphs (text only)
Domain: Best for empirical research; struggles with pure theory papers
Context: May miss field-specific conventions without discipline flag
📝 Note: This tool generates draft abstracts for efficiency, but all summaries require human review before submission. Always verify that numbers, statistics, and conclusions accurately reflect the original paper.
Parameters
Parameter
Type
Default
Description
--input
str
Required
--text
str
Required
Direct text input
--url
str
Required
URL to fetch paper from
--output
str
Required
Output file path
--format
str
'structured'
Output format
Output Requirements
Every final response should make these items explicit when they are relevant:
Objective or requested deliverable
Inputs used and assumptions introduced
Workflow or decision path
Core result, recommendation, or artifact
Constraints, risks, caveats, or validation needs
Unresolved items and next-step checks
Error Handling
If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
If scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
Do not fabricate files, citations, data, search results, or execution outcomes.
Input Validation
This skill accepts requests that match the documented purpose of abstract-summarizer and include enough context to complete the workflow safely.
Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:
abstract-summarizer only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.
Response Template
Use the following fixed structure for non-trivial requests:
Objective
Inputs Received
Assumptions
Workflow
Deliverable
Risks and Limits
Next Checks
If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.
