Agent Skills
LiteratureSearch
Open Access Scout
AIPOCH-AI
When blocked by a Paywall, automatically find legal Open Access versions (Green OA / Preprint) and generate download links.
62
2
FILES
open-access-scout/
skill.md
scripts
main.py
SKILL.md
Open Access Scout
Legal full-text discovery tool.
Use Cases
- Literature access without subscription
- Database-limited environments
- Patient education materials
- Developing country researchers
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
doi | str | No | - | Paper DOI identifier |
title | str | No | - | Article title for search |
authors | list[str] | No | - | Author list for verification |
Returns
- Unpaywall links
- Preprint servers (arXiv/bioRxiv)
- Institutional repository
- Author PDF request
Example
Nature paper → Green OA version found
Risk Assessment
| Risk Indicator | Assessment | Level |
|---|---|---|
| Code Execution | Python/R scripts executed locally | Medium |
| Network Access | No external API calls | Low |
| File System Access | Read input files, write output files | Medium |
| Instruction Tampering | Standard prompt guidelines | Low |
| Data Exposure | Output files saved to workspace | Low |
Security Checklist
- No hardcoded credentials or API keys
- No unauthorized file system access (../)
- Output does not expose sensitive information
- Prompt injection protections in place
- Input file paths validated (no ../ traversal)
- Output directory restricted to workspace
- Script execution in sandboxed environment
- Error messages sanitized (no stack traces exposed)
- Dependencies audited
Prerequisites
No additional Python packages required.
Evaluation Criteria
Success Metrics
- Successfully executes main functionality
- Output meets quality standards
- Handles edge cases gracefully
- Performance is acceptable
Test Cases
- Basic Functionality: Standard input → Expected output
- Edge Case: Invalid input → Graceful error handling
- Performance: Large dataset → Acceptable processing time
Lifecycle Status
- Current Stage: Draft
- Next Review Date: 2026-03-06
- Known Issues: None
- Planned Improvements:
- Performance optimization
- Additional feature support