Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add drpwchen/paper-review-and-digest --skill paper-reviewgit clone --depth 1 https://github.com/drpwchen/paper-review-and-digestWrote 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/drpwchen/paper-review-and-digest/paper-review)<a href="https://agentmods.dev/skills/drpwchen/paper-review-and-digest/paper-review"><img src="https://agentmods.dev/badge/skills/drpwchen/paper-review-and-digest/paper-review/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/drpwchen/paper-review-and-digest/paper-review"><img src="https://agentmods.dev/badge/skills/drpwchen/paper-review-and-digest/paper-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 203 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00136 | $0.08281 |
| Opus 5 | $0.00068 | $0.04140 |
| Sonnet 5 | $0.00027 | $0.01656 |
| Haiku 4.5 | $0.00014 | $0.00828 |
Grade A, and why
paper-review 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 — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Review — 單篇論文深度評讀
Overview
This skill performs a 360-degree deep dive into a single academic paper, covering journal credibility,
author backgrounds, publication history, historical context, reference verification, critical appraisal,
and citation impact analysis. The output is a structured Obsidian note in ${vault.papers_dir} plus a
daily note entry under ${vault.daily_section}.
Reviews should be clinically grounded, teachable (journal-club ready), and honest about what the
evidence can and cannot support. Tone, language, specialty framing, and external-validity checks are
driven by ${persona} (see Configuration).
Configuration (read FIRST, every run)
Before Phase 0, read config.yaml in this skill's directory (copy config.example.yaml →
config.yaml on first setup). It defines the values this document references as ${section.key}:
${vault.papers_dir},${vault.medicine_dir},${vault.inbox_note},${vault.daily_section}${fulltext.*}(inbox, Zotero, Elsevier, SFX resolver, institution) — consumed viafulltext-acquisition.md${secrets.backend}— how bundled scripts read API keys${persona}— language, specialty, audience, locale, reimbursement system. This is user-authored; it sets whether output is 繁體中文/English, which clinical lens, and whether coverage lookups run.
Wherever this SKILL writes ${...}, substitute the config value. A blank/placeholder value means
"skip that route". The bundled scripts (grade_judge.py, argdown_lint.py) need no config.
Input
Accepts any of:
- DOI (e.g.,
10.1097/PHM.0000000000002700) - PMID (e.g.,
39056432) - Paper title (partial or full)
- PDF file path (local file)
- Pasted content (abstract or full text in the conversation)
Effort tiers (pick before starting — token budget)
- Quick (daily-note
[x]checkbox): Phases 1 + Critical Appraisal +白話導讀only. No author/journal deep-dive, no citation analysis, no reference verification. ~1 model, cheap. - Deep (
/paper-review): all 7 phases. Token-heavy (many MCP + WebFetch calls). Before starting, offer the user a focused deep: "全跑 (Phases 1-7) 還是只跑關鍵幾關 (2 期刊/6 引用查核/appraisal)?" Respect a "skip" after any phase. Don't silently run all 7 if the user wanted a spot-check. - Either tier: reuse
journal_cache.json/author_cache.jsonbefore any WebSearch.
What ships with it
8 files 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 · 547 lines · 136 tokens per session scan A b49188957a29
paper-review is a skill published in the GitHub repository drpwchen/paper-review-and-digest (39 stars, last pushed 21d ago), licensed MIT. It adds 136 tokens to every session and 8,281 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…