paper-ranker
Apply a conservative screening rubric to rank papers and separate selected, ambiguous, and rejected items with reasons and evidence references. Use when a candidate set already exists and final ranking or grouping is needed.
Best use case
paper-ranker is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Apply a conservative screening rubric to rank papers and separate selected, ambiguous, and rejected items with reasons and evidence references. Use when a candidate set already exists and final ranking or grouping is needed.
Teams using paper-ranker should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/paper-ranker/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How paper-ranker Compares
| Feature / Agent | paper-ranker | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Apply a conservative screening rubric to rank papers and separate selected, ambiguous, and rejected items with reasons and evidence references. Use when a candidate set already exists and final ranking or grouping is needed.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# paper-ranker ## Name paper-ranker ## Description Apply a conservative screening rubric to separate selected, ambiguous, and rejected papers with reasons and evidence references. ## Use When - the user wants final selection or ranking - a candidate set already exists - abstract and optional full-text evidence need to be turned into decisions - the workflow must produce reproducible, structured outputs ## Inputs - normalized paper records - evidence entries - inclusion criteria - exclusion criteria - rubric dimensions and thresholds - `require_fulltext_for_selection` ## Outputs - relevance score - decision: `selected`, `ambiguous`, or `rejected` - reasons - evidence references - grouped result sets ## Workflow 1. Start from the `screening_candidates` set. 2. Review criteria and available evidence. 3. Score each paper on: - topic relevance - method match - dataset match - supervision or annotation match - evidence confidence 4. Check exclusion criteria and missing required evidence. 5. Apply conservative decision rules. 6. Return grouped outputs and recommended follow-up actions. ## Guardrails - Apply the rubric conservatively. - Separate `selected`, `ambiguous`, and `rejected`. - Do not convert uncertainty into selection. - If full text is required for selection and unavailable, keep the paper ambiguous. - Provide reasons and evidence references for every decision. ## Online And Offline Behavior - works in either mode because ranking depends on normalized evidence, not on network access - weak evidence in offline-only metadata should reduce confidence rather than inflate score ## Example Decision pattern: - `selected`: strong topic and supervision match with sufficient evidence - `ambiguous`: promising paper but missing method, dataset, or full-text confirmation - `rejected`: exclusion triggered or relevance too weak
Related Skills
paper-search
Retrieve candidate papers and perform conservative coarse screening using title and abstract evidence. Use when the user needs a candidate paper set, abstract-level screening, or a first-pass shortlist before full-text review.
paper-reader
Read abstracts and, when available, full text to extract structured evidence for literature screening. Use when a paper is ambiguous after abstract screening or the user needs method, dataset, supervision, or limitation details.
paper-reach
Run evidence-aware literature screening with Paper-Reach. Search candidate papers, screen abstracts conservatively, review full text when available, and emit structured JSON.
paperproof-validator
Formal Proof Visualization and Verification for Lean 4
hatchery-papers
Chicken Scheme Hatchery eggs and academic papers for color logic, 2TDX, colored operads, and higher observational type theory.
template-academic-paper
Template-native manuscript planning, outline, drafting, revision, formatting, citation check, and AI-use disclosure routing. USE WHEN the user asks to write, outline, revise, format, or prepare a paper inside the Research Project Template.
template-academic-paper-reviewer
Read-only manuscript review, methodology review, re-review, and calibration workflow for template projects. USE WHEN the user asks for peer review, referee-style critique, methods/statistics review, or verification that revisions addressed prior comments.
paper-2-web
This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.
pubmed-paper-exploration
Deep exploration from a key paper using related, citing, reference, and citation tree tools. Triggers: 這篇論文的相關研究, 誰引用這篇, 類似文章, related articles, citation tree, paper exploration
paper-scout
9 源学术论文搜索与筛选（arXiv, Semantic Scholar, OpenAlex, PubMed, CrossRef, DBLP, Europe PMC, bioRxiv, Papers with Code），利用本机已安装工具，零额外依赖
paper-analyzer
从学术论文中提取结构化信息，生成标准化笔记和文献对比矩阵
paper-making
Handcraft paper from plant fibres — fibre harvesting, pulping, sheet forming with a mould and deckle, pressing, and drying. Covers fibre sources (cotton, kozo, abaca, recycled paper), beating methods, sizing, and decorative techniques. Use when making handmade paper for art, stationery, or bookbinding, when creating unique textured or embedded paper for special projects, or when learning traditional paper making as a craft practice.