paper-filter
Skill0 starsChanged 4 months agoNo licenceView on GitHub
基于摘要筛选论文，判断是否值得全文阅读。 筛选标准见 references/filter_criteria.md。 针对每篇论文，根据四个维度打分（1-5分）： - 相关性：与研究目标的匹配程度 - 创新性：方法/结论是否新颖 - 可复现性：是否包含足够细节（算法、参数、公式） - 完整性：是否有理论分析 + 实验验证 保留标准：综合评分 ≥ 12 分 且 相关性 ≥ 3 分 综述类文章： - 仅保留发表于近3-5年的高质量期刊/会议综述 - 标注文献类型为"综述" - 优先保留覆盖用户关注子方向的综述
In this repository38 other files it gives its agents.
- academic-pipelineSkill
- author-networkSkill
- autoresearchSkill
- citation-graphSkill
- code-review-skillSkill
- coding-standardsSkill
- deep-researchSkill
- doc-coauthoringSkill
- fact-checkSkill
- humanizerSkill
- Literature OverviewSkill
- Literature ResearchSkill
- literature-reviewSkill
- Literature SearchSkill
- annotated-bibliographySkill
- evidence-synthesisSkill
- paper-comparisonSkill
- paper-readerSkill
- quality-assessmentSkill
- research-gapsSkill
- systematic-screeningSkill
- ml-paper-writingSkill
- office-academic-skillSkill
- paper-analysis-assistantSkill
- paper-analystSkill
- paper-deep-readerSkill
- paper-reading-zhSkill
- paper-prioritizerSkill
- PDF Processing ProSkill
- pdf-processorSkill
- recursive-decompositionSkill
- research-coordinatorSkill
- research-trendsSkill
- research-writing-skillSkill
- review-generatorSkill
- scientific-toolkit-skillSkill
- semantic-scholarSkill
- wos-parserSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.