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 Conradgui/Academic-Paper-Review-Skill --skill paper-reviewgit clone --depth 1 https://github.com/Conradgui/Academic-Paper-Review-SkillWrote 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/conradgui/academic-paper-review-skill/paper-review)<a href="https://agentmods.dev/skills/conradgui/academic-paper-review-skill/paper-review"><img src="https://agentmods.dev/badge/skills/conradgui/academic-paper-review-skill/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/conradgui/academic-paper-review-skill/paper-review"><img src="https://agentmods.dev/badge/skills/conradgui/academic-paper-review-skill/paper-review.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 | $0.00072 | $0.05605 |
| Opus 5 | $0.00036 | $0.02802 |
| Sonnet 5 | $0.00014 | $0.01121 |
| Haiku 4.5 | $0.00007 | $0.00560 |
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 13d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Review
Overview
Produce a concrete manuscript review across two parallel quality tracks:
- Scientific Review: research questions, methods, evidence, variables, equations, figures/tables, citations, and conclusion boundaries.
- Text Quality Review: clarity, terminology, redundancy, paragraph flow, register, and manuscript-style consistency.
Default to a Markdown review report unless the user requests another output format. Scientific validity remains the first priority; text-quality review must not weaken or replace it.
Default Behavior
- Read the full manuscript or all provided manuscript material before writing findings.
- Preserve equations, symbols, citation keys, table/figure labels, and quoted snippets exactly when needed for accuracy.
- Match the user's requested language; default to Simplified Chinese (简体中文) unless specified otherwise.
- Create a new timestamped review file at
paper-reviews/review-YYYY-MM-DD-HHMMSS.mdwhen writing to disk, unless the user gives another path. Treatpaper-reviews/andpaper-revisions/as user-facing deliverable directories. Do not place plans, scratch notes, logs, or temporary files in them. - Do not modify the manuscript unless the user explicitly requests edits or a revision pass.
- Do not require a fixed review template. Use the structure that best exposes actionable issues.
- If the manuscript is incomplete, review what is available and state which checks are limited by missing files.
- Run both review tracks by default. Keep the text-quality result concise unless material problems or an explicit request trigger detailed reporting.
- Do not infer authorship or output an AI probability.
Input Handling
Support Markdown, DOCX, PDF, LaTeX source, and plain text.
- Markdown or plain text: review structure, claims, citations, tables, formulas, and prose directly.
- DOCX: review extractable manuscript content only. Use headings or table text as content-location context when available, but do not assess, repair, preserve, or guarantee layout, styles, pagination, comments, tracked changes, text boxes, field codes, or equation/table rendering.
- PDF: review visible content; note that source-level comments, hidden metadata, and some cross-reference checks may be limited. Do not perform full-manuscript polishing from PDF alone.
- LaTeX: inspect source when available; for LaTeX-specific source, macro, cross-reference, and compileability concerns, prefer
$latex-paper-reviewwhen installed. - Multi-file projects: inspect the main file plus included chapters, bibliography, appendices, tables, figures/captions, and supporting notes when available.
What ships with it
12 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.
- agents/openai.yaml 244 B
- references/ai-trace-candidate-audit.md 6.1 KB
- references/authorial-polishing.md 3.8 KB
- references/claim-strength-calibration.md 2.7 KB
- references/empirical-paper-audit.md 3.2 KB
- references/external-polishing-routing.md 1.9 KB
- references/reference-audit.md 6.4 KB
- references/review-rubric.md 849 B
- references/text-quality-audit.md 5.1 KB
- references/text-quality-en.md 2.9 KB
- references/text-quality-zh.md 3.4 KB
- scripts/proofing_scan.py 8.1 KB runs code
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.
- 13d ago First seen · 337 lines · 72 tokens per session scan A e0f19f9889b9
paper-review is a skill published in the GitHub repository Conradgui/Academic-Paper-Review-Skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 5,605 once invoked, about $0.0004 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
paper-sprint-review
PaperSprint is a Scrum-inspired academic paper agent workflow for conference or journal drafts. Use when Codex needs to clarify paper direction, estimate likely sprint count, set sprint goals and focus areas, assess venue fit, organize reviewer or editor lenses, convert critique into a prioritized revision backlog…
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
paperjury
A tool for reviewing and editing computer-science conference papers in LaTeX or Markdown, the document formats commonly used for research papers. It supports direct edits, structured pre-submission review, and an optional unattended mode for selected fixes.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
academic-paper-writer
Draft economics papers with proper structure and academic style.