Borrowing it
Nothing to install: this file belongs to Guo-Chenxu/paper-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Guo-Chenxu/paper-agent/main/.claude/skills/paper-screener/SKILL.mdgit clone --depth 1 https://github.com/Guo-Chenxu/paper-agentWrote 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.
[](https://agentmods.dev/skills/guo-chenxu/paper-agent/paper-screener)<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/paper-screener"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/paper-screener/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.
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/paper-screener"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/paper-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.02915 |
| Opus 5 | $0.00023 | $0.01458 |
| Sonnet 5 | $0.00009 | $0.00583 |
| Haiku 4.5 | $0.00005 | $0.00292 |
Grade A, and why
paper-screener scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Screener
Skill Goal
Automated two-round paper screening and structured summarization:
- Round 1: Title+abstract pre-screening with 3 parallel agents for fast coarse filtering
- Round 2: Full-text deep screening with 3 parallel agents reading complete PDFs
- Score aggregation with arbitration when agent disagreement exceeds threshold
- Structured paper summaries for high-scoring papers, generated from full-text reading
- Comprehensive screening report with statistics, rankings, and traceability
When To Use
- After paper crawling produces abstracts and metadata
- Need to filter and rank candidate papers by quality and relevance
- Want structured, full-text-based summaries of selected papers
- Preparing input for literature review or research idea generation
Prerequisites
Required inputs from a prior crawl run:
./papers/abstracts/*.txt— abstract text files./papers/metadata/papers_*.json— paper metadata records./papers/pdfs/*.pdf— full-text PDFs (required for Round 2; download if missing)
Required Python packages:
python -m pip install requests
Scripts
- Load papers for screening:
./scripts/load_papers_for_screening.py
Workflow
Step 1: Load and Prepare Papers
python .claude/skills/paper-screener/scripts/load_papers_for_screening.py \
--abstracts-dir ./papers/abstracts \
--metadata-dir ./papers/metadata \
--output screening_input.json
This produces a JSON file with paper titles, abstracts, venues, years, and authors for agent scoring.
Step 2: Round 1 — Title+Abstract Pre-Screening
Purpose: Fast coarse filtering to reduce the candidate set. Scores from this round are NOT used as final quality judgments.
Spawn 3 parallel subagents, each scoring every paper independently. Each agent receives only the title and abstract.
Scoring Criteria (1–10 total):
| Dimension | Points | Description |
|---|---|---|
| Relevance | 5 | Fit with the target research domain |
| Potential Innovation | 3 | Novelty indicated in the abstract |
| Publication Quality | 2 | Venue tier, citation count |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 297 lines · 45 tokens per session scan A 5d12663e7dd5
paper-screener is a skill published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,915 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…