# Latest Paper Search

> Search newest academic papers for a specified topic across Google Scholar via SerpAPI, OpenAlex, Crossref, arXiv, and Semantic Scholar, then produce lightweight Markdown/CSV/JSON reports with self-contained deduplication, OA grouping, authors, keywords, abstracts, and links. Use when an agent is asked for latest papers, papers today, papers this week, papers since a year, Google Scholar date-sort…

- **Type:** Skill
- **Install:** `agentstack add skill-123trump-latest-paper-search-latest-paper-search`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [123trump](https://agentstack.voostack.com/s/123trump)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [123trump](https://github.com/123trump)
- **Source:** https://github.com/123trump/latest-paper-search

## Install

```sh
agentstack add skill-123trump-latest-paper-search-latest-paper-search
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Latest Paper Search

Search for papers newly published or newly indexed today, this week, or since a given year, then produce a lightweight report. The skill is self-contained and agent-agnostic: it can be installed under Codex, Claude Code, OpenClaw, project-local skill folders, or run directly from its Python scripts.

## Workflow

1. Choose the time window:
   - `today`: search the past 2 days to buffer indexing lag.
   - `week`: search the past 10 days to buffer indexing lag.
   - `--since-year YEAR`: search from January 1 of that year through today.
2. Route sources:
   - Use OpenAlex only when `OPENALEX_API_KEY` is set.
   - Use arXiv for AI, computer vision, SAR, image processing, foundation model, deep learning, and preprint-heavy topics.
   - Use Crossref for DOI and publisher metadata discovery.
   - Use Semantic Scholar enrichment only when `SEMANTIC_SCHOLAR_API_KEY` is set.
   - Use SerpAPI Google Scholar only when `SERPAPI_API_KEY` is set; treat it as a supplemental discovery source.
3. Run the latest search script from the user's working directory:

```bash
python /scripts/latest_search.py "" --window week
```

Useful options:

```bash
python /scripts/latest_search.py "" --window today --limit 30
python /scripts/latest_search.py "" --sources openalex,arxiv,serpapi
python /scripts/latest_search.py "" --sources serpapi --since-year 2026
python /scripts/latest_search.py "" --language zh --output-dir 
```

4. Report the generated `report.md` path and summarize the top findings briefly.

## Output

Each run writes to the current working directory unless `--output-dir` is provided:

```text
paper-latest-results/__/
  report.md
  papers.csv
  papers.json
  kg.json
  run_log.json
  raw/
```

The report must stay lightweight:

- Topic, time window, and sources used
- Raw hit count and deduplicated paper count
- Chinese or English papers only; filter out papers whose titles are dominated by other writing systems
- Top 3-5 papers worth reading with short reasons
- Full paper list with title, authors, keywords, abstract, OA status, PDF/download link, DOI/page link, and source trace

## Deduplication

Use this skill's `scripts/deduplicate_latest.py` for deduplication and field merging. Do not replace it with title-only merging.

Read `references/deduplication.md` before changing dedup behavior.

## References

- `references/remote_sensing_sources.md`: remote sensing routing and venue/source guidance.
- `references/serpapi_google_scholar.md`: SerpAPI setup, fields, and limitations.
- `references/deduplication.md`: self-contained deduplication and merge behavior.
- `references/report_format.md`: report format and ranking rules.
- `references/agent_portability.md`: how to install and run the skill across Codex, Claude Code, OpenClaw, and direct CLI usage.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [123trump](https://github.com/123trump)
- **Source:** [123trump/latest-paper-search](https://github.com/123trump/latest-paper-search)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-123trump-latest-paper-search-latest-paper-search
- Seller: https://agentstack.voostack.com/s/123trump
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.