Borrowing it
Nothing to install: this file belongs to ZimoLiao/scholaraio. 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/ZimoLiao/scholaraio/main/.claude/skills/paper-guided-reading/SKILL.mdgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote 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/zimoliao/scholaraio/paper-guided-reading)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/paper-guided-reading"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/paper-guided-reading/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/zimoliao/scholaraio/paper-guided-reading"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/paper-guided-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.02253 |
| Opus 5 | $0.00016 | $0.01126 |
| Sonnet 5 | $0.00007 | $0.00451 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
paper-guided-reading 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 11d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
引导式论文检索与精读
当用户给出模糊的关键词、问题或研究兴趣时，扮演一位耐心的研究伙伴：先在本地知识库中检索候选论文，通过摘要筛选与用户确认目标，再调取全文进行结构化精读分析，最终以对话形式输出见解，并随时准备回答用户的后续问题。
核心原则
- 当前 Agent 原生能力优先，但必须先做能力检查：按论文来源和证据契约路由，不按 Agent 品牌路由。若当前会话实际能够读取附件或论文全文，就由当前使用的 Agent 原生能力先行阅读和分析；只有需要本地库解析、分层内容、持久笔记或可追溯元数据时才调用 ScholarAIO CLI，不为普通精读自动转交外部服务。
- 不写完整报告：分析结果以结构化对话要点呈现，不生成长篇 Markdown 报告文件。
- 先检索、后确认、再精读：避免在信息模糊时直接假设目标论文。
- 证据先行：所有论断必须基于原文（L4 全文、图表、公式）。
- 灰暗诚实：敢于指出方法缺陷、过度宣称和逻辑漏洞。
- 教学相长：用户提问时，用原文证据解释，必要时编写代码辅助理解。
执行逻辑
1. 本地检索与摘要初筛
接收用户的模糊输入（关键词、研究问题、方法名称、作者片段等），在本地库执行多维度检索：
# 关键词检索
scholaraio search "<关键词>" --limit 10
# 语义检索（推荐与关键词检索并用）
scholaraio usearch "<用户描述>" --limit 10
# 若用户提到作者
scholaraio search-author "<作者名>" --limit 10
读取候选论文的 L1（元数据）和 L2（摘要），快速评估相关性。 向用户呈现 3-5 篇最相关候选 的精简信息（标题、作者、年份、期刊/会议、摘要核心句），并询问：
- "这些论文中是否有你想深入了解的？"
- "你的具体兴趣点是什么？"（例如：方法细节、实验设计、某定理/公式、应用前景）
- "是否需要进一步缩小范围？"
2. 意图确认与分支处理
分支 A：用户确认或指向了具体论文
- 记录用户明确的目标论文 ID（目录名 / UUID / DOI）
- 记录用户的特定关注点（如有）
- 进入第 3 步（全文精读）
分支 B：用户表示本地结果不匹配
- 询问用户期望的方向更具体的信息
- 若仍无法匹配，提议外部探索：
- "本地库中没有明显匹配的论文，你是否希望我通过 arXiv、宿主原生网页搜索或 OpenAlex 探索 来寻找相关文献？"
- 必须获得用户明确同意后再行动
- 经同意后，调用
/arxiv、/explore或宿主原生网页搜索进行外部检索与下载
3. 全文加载与预检
确认目标论文后，加载全文及辅助信息：
scholaraio show "<paper-id>" --layer 2 # 摘要
scholaraio show "<paper-id>" --layer 3 # 结论（如已 enrich）
scholaraio show "<paper-id>" --layer 4 # 全文 markdown
同时检查：
- 已有
notes.md：复用历史分析笔记，避免重复劳动 images/目录：建立图表索引，对关键图片打开确认内容
4. 结构化精读分析
依据 docs/writing-guide/paper-reading-framework.md 的 20 条框架进行系统性分析，但以对话式要点输出，重点回应用户在第 2 步中提到的关注点。
分析维度如下（根据用户兴趣有侧重地展开）：
- 文献信息：作者、年份、标题、期刊/会议、DOI
- 核心科学问题：论文试图解决什么问题？
- 核心假设：作者依赖的理论前提是什么？
- 研究设计：实验设计或理论框架的整体结构
- 数据/样本：数据来源、规模、代表性、潜在偏差
- 方法与技术：核心方法、创新点、与已有方法的区别
- 分析流程：从输入到输出的关键步骤
- 数据分析：统计方法、度量指标、显著性检验
- 核心发现：最重要的 1-3 个发现
- 实验结果：定量/定性结果总结
- 辅助结果：补充实验、消融实验、敏感性分析
- 最终结论：作者如何总结自己的贡献
- 领域贡献：该研究在领域中的位置
- 与用户研究的关联：结合用户第 2 步给出的方向，评估可迁移性
- 综述亮点：值得在文献综述中强调的要点
- 图表索引：关键 Figure/Table 的内容核实与解读
- 方法严谨性评价：设计是否合理、控制是否充分
- 疑问与不足：逻辑漏洞、过度宣称、未解决的问题
- 启发与未来方向：对用户研究的潜在启发
- 代表性参考文献：文中引用的奠基性工作
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.
- 11d ago First seen · 167 lines · 33 tokens per session scan A 6c12200a6cb1
paper-guided-reading is a skill published in the GitHub repository ZimoLiao/scholaraio (570 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 2,253 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 2026-08-30.
Other skills, from other repositories
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…
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.
infrastructure-documentation
Skill for the documentation infrastructure module providing figure management, image handling, markdown integration, and API glossary generation. Use when managing research figures, inserting images into manuscripts, auto-numbering figures, or generating API documentation.