Daily Literature Search

Automated daily literature search system for academic researchers. Performs scheduled searches across PubMed, OpenAlex, and Semantic Scholar with automatic d...

Security Scan

The skill largely matches its stated purpose (automated literature search and local paper organization) but contains metadata/instruction mismatches, a few code bugs, and runtime behavior (executing another skill's script and creating cron/.env) that you should review before installing.

Purpose & Capability

Name/description (daily literature searches, OA download, classification) match the included scripts (search, dedupe, classify, upload analyzer). However the package metadata/registry claims no required environment variables while SKILL.md and install.sh expect USER_EMAIL and optional API keys and notification creds — this is an inconsistency that should be clarified.

Instruction Scope

Runtime instructions and scripts perform network searches, OA checks, and downloads (expected). Notably, the main script invokes an external script via subprocess: papers_dir.parent/skills/literature-review/scripts/lit_search.py — that means this skill will execute code from another 'literature-review' skill located in the workspace, so you must trust whatever lives there. The installer writes a .env with notification webhooks and optional SMTP creds; if you populate these, notifications could send data externally. No evidence of hidden endpoints, but the ability to call arbitrary webhook(s) is present if configured.

Install Mechanism

There is no registry install spec, but an install.sh is provided that copies config.example.yaml, creates directories, writes a .env file, installs Python deps via pip3, and adds a cron job. The install script uses eval for dry-run execution and crontab modification; running it will write files and schedule cron — review it before running. The origin is 'unknown' and there's no homepage link.

Credentials

Registry metadata lists no required env vars, but SKILL.md and install.sh expect USER_EMAIL and optionally SEMANTIC_SCHOLAR_API_KEY and OPENALEX_API_KEY, plus optional EMAIL_USERNAME/EMAIL_PASSWORD and webhook variables. Requesting email/webhook credentials is reasonable for notifications, but because the registry failed to declare these, there's a mismatch that reduces transparency. Only provide notification/email credentials if you trust the code and wish to enable notifications.

Persistence & Privilege

The skill is not 'always:true' and allows autonomous invocation (default). The installer writes config, .env, and adds a cron job (persistent presence on the host) — that is expected for scheduled tasks, but you should be aware this makes the skill persistently scheduled to run daily until uninstalled.

What to consider before installing

What to check before installing: - Metadata mismatch: registry shows no required env vars but SKILL.md and install.sh expect USER_EMAIL and optional API keys and notification creds. Confirm which env vars you must set and why. - Review install.sh before running. It will create a .env with placeholders, make directories under your home workspace, install Python packages with pip3, and add a cron job. Run with --dry-run first and inspect the produced .env and config files. - Inspect/verify the 'literature-review' skill (workspace/skills/literature-review) or ensure the referenced script exists and is trusted: the main script executes that script via subprocess, so any code there will run with your user privileges when this job runs. - Be cautious with notification webhooks and email credentials: if you fill those in, the skill may send data (e.g., counts or filenames) externally. Only provide webhook or SMTP credentials to endpoints you trust. - The code has at least one clear bug (a truncated variable name in deduplication) that will likely cause runtime errors; consider running tests (pytest) and doing a dry-run before enabling cron. - If you are not comfortable reviewing code, do not install on a sensitive system. Install into an isolated environment or VM, run manually once, verify behavior and network calls, then enable scheduled runs. If you want, I can: (1) point out the exact lines with the bug(s), (2) generate a safe dry-run checklist of commands to run, or (3) craft a minimal config.yaml and .env for a non-network test run.

Daily Literature Search Skill

Automated literature search system for academic researchers. Performs scheduled searches across multiple databases (PubMed, OpenAlex, Semantic Scholar), automatically deduplicates results, downloads open-access papers, and generates daily reports.

🎯 Use Cases

• Daily literature monitoring for specific research topics
• Automated paper collection for literature reviews
• Stay updated on latest publications in your field
• Build personal paper library with automatic categorization

📦 Components

1. Core Search Script (daily_literature_search.py)

Main execution script with the following features:

• Multi-source search: PubMed, OpenAlex, Semantic Scholar
• Automatic deduplication: By DOI (within batch + against local library)
• OA detection: Uses Unpaywall API to identify open-access papers
• Auto-download: Downloads OA papers from PubMed Central or publisher sites
• Smart categorization: Classifies papers by topic (configurable keywords)
• Daily reports: Generates Markdown reports with search statistics

2. Upload Analyzer (analyze_uploaded.py)

Analyzes and categorizes manually uploaded papers:

• Filename-based classification: Uses keyword matching
• DOI extraction: From filenames and metadata
• Batch processing: Handles multiple files at once
• Report generation: Creates categorization summary

⚙️ Configuration

Directory Structure

papers/
├── B-ALL/raw/          # Category 1 (e.g., B-ALL research)
├── MM/raw/             # Category 2 (e.g., Multiple Myeloma)
├── OTHER/raw/          # Other papers
├── daily_search_logs/  # Search logs and reports
└── upload_temp/        # Temporary upload directory

Search Keywords (Customizable)

Edit SEARCH_KEYWORDS in daily_literature_search.py:

SEARCH_KEYWORDS = [
    '"inotuzumab ozogamicin"',
    '"Elranatamab"',
    '"Teclistamab"',
    '"Talquetamab"',
    '"Blinatumomab"',
    '("CAR-T" AND "B-ALL")',
]

Classification Keywords

Edit B_ALL_KEYWORDS and MM_KEYWORDS in analyze_uploaded.py to match your research domains.

🚀 Usage

Manual Execution

# Run daily search
python3 papers/daily_literature_search.py

# Analyze uploaded papers
python3 papers/analyze_uploaded.py

Scheduled Execution (Cron)

Add to crontab for automatic daily searches:

# Daily search at 6:30 AM
30 6 * * * /usr/bin/python3 /path/to/papers/daily_literature_search.py >> /path/to/papers/daily_search_logs/cron.log 2>&1

Configuration Options

Parameter	Default	Description
MAX_RESULTS_PER_KEYWORD	10	Max results per keyword per source
DATE_RANGE_DAYS	7	Search window (recent N days)
SOURCES	["pm", "oa", "s2"]	Search databases
USER_EMAIL	—	For polite API access (env var)

📊 Output

Daily Report Example

# 📚 每日文献检索报告
**检索日期：** 2026-03-18

## 📊 检索汇总
| 分类 | 检索到 | 成功下载 | 付费墙 |
|------|--------|---------|--------|
| B-ALL | 28 | 0 | 28 |
| MM | 24 | 0 | 24 |
| 总计 | 53 | 0 | 53 |

## 🔀 去重统计
- 原始检索结果：130 篇
- 去重后文献：110 篇
- 批次内重复：2 篇
- 库中已有：18 篇

File Organization

• Reports: papers/daily_search_logs/daily_report_YYYY-MM-DD.md
• Logs: papers/daily_search_logs/daily_search_YYYY-MM-DD.log
• Papers: papers/{CATEGORY}/raw/{DOI}.pdf

🔧 Advanced Features

1. Library Deduplication

Automatically checks new results against existing library:

• Scans all category directories for existing DOIs
• Extracts DOIs from filenames and historical logs
• Skips papers already in library
• Reports duplicate statistics

2. Open Access Detection

Uses Unpaywall API to identify OA papers:

is_oa, oa_url = check_open_access(doi)
if is_oa:
    download_paper(oa_url, save_path)

3. PubMed Central Integration

Automatically tries PMC for biomedical papers:

if pmid and str(pmid).isdigit():
    download_from_pubmed(pmid, save_path)

🛠️ Customization Guide

Change Research Topics

1. Edit SEARCH_KEYWORDS in daily_literature_search.py
2. Update category names and keywords
3. Modify directory structure if needed

Add New Categories

1. Create new directory: papers/NEW_CATEGORY/raw/
2. Add classification keywords in classify_paper() function
3. Update report generation to include new category

Integrate with Notification Systems

Add email/Slack/Discord notifications after search completion:

# At end of main()
send_notification(f"Daily search complete: {results['total']} papers found")

📋 Requirements

Python Dependencies

pip install requests
# Most other modules are standard library

API Access (Optional but Recommended)

• Semantic Scholar API Key: Higher rate limits
• OpenAlex API Key: Polite pool access
• Unpaywall: Free, no key needed (email required)

Set environment variables:

export SEMANTIC_SCHOLAR_API_KEY="your-key"
export OPENALEX_API_KEY="your-key"
export USER_EMAIL="[e-mail]"

⚠️ Important Notes

1. Rate Limits: Respect API rate limits, especially without API keys
2. Storage: Monitor disk space for downloaded PDFs
3. Copyright: Only download open-access or legally available papers
4. Email: Set USER_EMAIL for polite API access

🔄 Version History

• 1.0.0 (2026-03-18): Initial release
  • Multi-source search (PubMed, OpenAlex, Semantic Scholar)
  • Automatic deduplication (batch + library)
  • OA detection and download
  • Smart categorization
  • Daily reports with statistics

🤝 Contributing

To contribute improvements:

1. Fork the skill repository
2. Test changes with your own literature search
3. Submit pull request with description of improvements

📄 License

This skill is provided as-is for academic research purposes. Users are responsible for compliance with publisher terms and copyright laws.