AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Paper Finder

skill-jesamkim-oh-my-skills-paper-finder · by jesamkim

|

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-jesamkim-oh-my-skills-paper-finder

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jesamkim-oh-my-skills-paper-finder)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
9d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Paper Finder? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Paper Finder

Overview

Search academic papers across multiple APIs and produce structured results with citation counts, abstracts, and links. Designed for PoC research, technical exploration, and literature review.

Workflow

1. Keyword Search

Run the search script with user's keywords:

python3 {SKILL_DIR}/scripts/search_papers.py search "" --limit 10

The script searches Semantic Scholar first. On rate limit (429) or failure, falls back to OpenAlex.

To search a specific source:

python3 {SKILL_DIR}/scripts/search_papers.py search "" --source semantic
python3 {SKILL_DIR}/scripts/search_papers.py search "" --source openalex
python3 {SKILL_DIR}/scripts/search_papers.py search "" --source arxiv

2. Paper Lookup by ID

Look up a specific paper by ArXiv ID or DOI:

python3 {SKILL_DIR}/scripts/search_papers.py lookup --arxiv 2301.00234
python3 {SKILL_DIR}/scripts/search_papers.py lookup --doi 10.1145/1234567.1234568

3. Output Options

Markdown table (default): Displays results in terminal as a formatted table.

Save to file:

python3 {SKILL_DIR}/scripts/search_papers.py search "" --output docs/papers/results.md

BibTeX export:

python3 {SKILL_DIR}/scripts/search_papers.py search "" --bibtex docs/papers/results.bib

Sort by citations:

python3 {SKILL_DIR}/scripts/search_papers.py search "" --sort citations

4. Present Results

After running the script, present results to the user as a markdown table:

| # | Title | Authors | Year | Citations | Link | |---|-------|---------|------|-----------|------|

Include a brief summary of what was found and highlight the most relevant papers based on citation count and recency.

Key Behaviors

  • Always run the search script rather than constructing curl commands manually
  • If the script is unavailable or fails, fall back to curl commands documented in references/api_reference.md
  • Create docs/papers/ directory before saving if it doesn't exist
  • When user provides ArXiv IDs (e.g., 2301.00234), use the lookup command
  • For broad research topics, suggest refining keywords if results are too generic
  • Present results in Korean explanations with English paper titles preserved

Rate Limit Notes

| API | Limit | Notes | |-----|-------|-------| | Semantic Scholar | 100 req/5min (no key) | Strict; get free key for higher limits | | OpenAlex | ~100K req/day | Very generous; preferred fallback | | ArXiv | 3 req/sec | Generous for normal use |

If Semantic Scholar returns 429, the script automatically retries with OpenAlex.

Source & license

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

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.