agentic-reviewer: Skill for Claude Code

.cursor/skills/explore-recent-papers/SKILL.md

explore-recent-papers is a skill for Claude Code, Cursor from FilippoScaramuzza/agentic-reviewer. It costs 47 tokens per session (841 once invoked), scanned A, original, MIT.

A research-paper tool that finds recent publications, downloads their full text, and converts PDF files into Markdown for analysis. It searches sources such as arXiv, bioRxiv, PubMed Central, and Semantic Scholar; bioRxiv and medRxiv are websites for sharing medical and biological research before formal journal review.

In plain words
What is it for?
Use it to prepare background for a paper review by collecting up to 20 recent publications and recording details such as titles, authors, dates, DOIs, and PDF links.
Why use it?
It removes the manual work of finding recent papers and collecting readable full texts. If a full paper cannot be found, it uses the abstract instead.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is FilippoScaramuzza/agentic-reviewer's own configuration. It tells Claude Code and Cursor how to work on agentic-reviewer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-reviewer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FilippoScaramuzza/agentic-reviewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FilippoScaramuzza/agentic-reviewer/main/.cursor/skills/explore-recent-papers/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FilippoScaramuzza/agentic-reviewer

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for explore-recent-papers

README.md
[![agentmods](https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers/github.svg)](https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers)
Your own site
<a href="https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers"><img src="https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for explore-recent-papers

Your own site · 80×15
<a href="https://agentmods.dev/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers"><img src="https://agentmods.dev/badge/skills/filipposcaramuzza/agentic-reviewer/explore-recent-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00841
Opus 5 $0.00023 $0.00420
Sonnet 5 $0.00009 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured 8d ago against content hash 3f663d03c38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

explore-recent-papers scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L -o "context/<journal-slug>/recent-papers/<slugified-title>.pdf" "<pdf-url>"
.cursor/skills/explore-recent-papers/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Recent Papers

Download and analyze the full text of up to 20 recent publications from the target journal/conference. Read the complete papers — not just abstracts.

Search Strategy

Finding Recent Papers

  1. Search arxiv for recent papers matching the journal name or conference proceedings
  2. Search PubMed Central (open access) for biomedical journals
  3. Search Semantic Scholar for papers with open-access PDFs
  4. Search Google Scholar for the journal's recent publications
  5. Check the journal's website for recent issue tables of contents

For each paper found, collect: title, authors, year, DOI, and PDF URL.

Priority Order for Full-Text Access

  1. arxiv preprinthttps://arxiv.org/pdf/<arxiv-id>.pdf
  2. bioRxiv / medRxiv preprint
  3. PubMed Central
  4. Author's institutional page
  5. Semantic Scholar — links to open-access PDFs

If no full text is available after all attempts, fall back to abstract-only analysis for that paper.

Download Process

Create Paper Directory

mkdir -p "context/<journal-slug>/recent-papers"

Download PDFs

curl -L -o "context/<journal-slug>/recent-papers/<slugified-title>.pdf" "<pdf-url>"

Use a slugified version of the paper title (lowercase, hyphens, remove special characters) for filenames.

Convert PDFs to Markdown

markitdown "context/<journal-slug>/recent-papers/<slugified-title>.pdf" > "context/<journal-slug>/recent-papers/<slugified-title>.md"

After conversion, read the full Markdown text of each paper.

Verify Downloads

After downloading, verify each file:

ls -la "context/<journal-slug>/recent-papers/"

Check that files are not empty and have reasonable sizes (> 10KB for full papers).

Analysis Methodology

What to Extract from Full Papers

After reading the full text of each paper, analyze:

Topics & Themes

  • What subjects are currently popular?
  • What emerging trends exist?
  • Which research gaps are being addressed?

Read the full file on GitHub · 106 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 106 lines · 47 tokens per session scan A 3f663d03c38c

Subscribe to this mod's changes

explore-recent-papers is a skill published in the GitHub repository FilippoScaramuzza/agentic-reviewer (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 841 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

search-math-results

Find program-conditioned math results, constructions, examples, counterexamples, analogies, and background references. Use when the current active program needs repair, mutation, analogy, a program shift, or carefully gated obstruction search.

frenzymath/Danus · 48 tokens

check-referenced-statements

Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.

frenzymath/Danus · 41 tokens

verify-sequential-statements

Verify a markdown proof in the order it is written. Use when the task is to check local correctness, theorem applicability, and reasoning gaps statement by statement through a paper-style proof.

frenzymath/Danus · 42 tokens

construct-counterexamples

Construct candidate counterexamples to test a proposed conjecture, lemma, or intermediate claim by keeping the assumptions true while making the claimed conclusion fail. Use when a proposed conjecture/claim feels fragile or unproved, or when you are stuck in reasoning and want to see where the assumptions take effect…

frenzymath/Danus · 66 tokens

obtain-immediate-conclusions

Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.

frenzymath/Danus · 49 tokens

propose-subgoal-decomposition-plans

Propose multiple subgoal decomposition plans for the current theorem using the information already gathered. Use when enough information has been collected from examples, counterexamples, search results, and previous failures to break the problem into several materially different plans.

frenzymath/Danus · 55 tokens