Obsidian 与 Zotero 文献整理指南
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "obsidian-zotero-guide":https://skillpi.com/zh/skills/deepskill-134e82edb6daf4637f318e0af90d3c49335238d96a8b1785f0defabb79569564。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/writing/citation/obsidian-zotero-guide/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/writing/citation/obsidian-zotero-guide --skill obsidian-zotero-guide来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
面向用 Zotero 管理参考文献、用 Obsidian 整理研究笔记的使用者。指南介绍如何统一引用键、在写作时插入引文,并把 PDF 高亮与批注导入文献笔记。需要配置 Obsidian 社区插件和 Zotero 的 Better BibTeX。批量导入前可先用单篇文献检查引用与附件的保存位置。
文件浏览
---
name: obsidian-zotero-guide
description: "Insert citations and notes from Zotero into Obsidian knowledge bases"
version: 1.0.0
author: wentor-community
source: https://github.com/mgmeyers/obsidian-zotero-integration
metadata:
openclaw:
category: "writing"
subcategory: "citation"
emoji: "🔗"
keywords:
- obsidian
- zotero
- citation-management
- note-taking
- knowledge-base
- bibliography
---
# Obsidian-Zotero Guide
A skill for integrating Zotero reference management with Obsidian note-taking to create a seamless academic knowledge management workflow. Based on the obsidian-zotero-integration plugin (2K stars), this skill guides the agent through setting up, configuring, and optimizing the bridge between your reference library and your personal knowledge base.
## Overview
Academic researchers accumulate hundreds or thousands of papers over a career, each containing insights that need to be connected, synthesized, and retrieved when writing new work. Zotero excels at organizing references and PDFs, while Obsidian excels at creating interlinked notes and building knowledge graphs. This integration bridges the two, allowing annotations made in Zotero to flow into Obsidian as linked notes, and enabling citation insertion directly from the Obsidian editor.
The result is a unified research workflow where reading, annotating, note-taking, and writing happen in a connected ecosystem rather than in isolated tools.
## Setup and Configuration
**Prerequisites**
- Zotero 6 or 7 with the Better BibTeX plugin installed
- Obsidian with community plugins enabled
- A designated vault folder for literature notes (e.g., `references/` or `literature/`)
**Installation Steps**
- Install the Zotero Integration plugin from the Obsidian community plugins browser
- Configure the Zotero data directory path in the plugin settings
- Set up the Better BibTeX citation key format (recommended: `authYear` or `authYearTitle`)
- Define the literature note template (see Template Configuration below)
- Test the connection by inserting a citation from a known Zotero entry
**Template Configuration**
- Create a template file that defines the structure of imported literature notes
- Include frontmatter fields: citekey, authors, year, journal, DOI, tags
- Include body sections: abstract, key findings, methodology notes, personal comments
- Use Nunjucks template syntax for dynamic field insertion
- Configure annotation extraction to pull highlights and comments from PDFs
## Citation Workflow
The primary citation workflow during writing:
**Inserting Citations**
- Use the command palette or hotkey to open the Zotero citation picker
- Search by author, title, year, or tag to find the desired reference
- Insert the citation in the desired format (pandoc, LaTeX, plain text)
- The plugin creates a backlink to the corresponding literature note
- Multiple citation formats can be configured for different output targets
**Managing Literature Notes**
- Each imported Zotero entry generates a literature note in Obsidian
- Notes are named by citation key for consistent linking
- Tags from Zotero are imported as Obsidian tags for cross-referencing
- PDF annotations (highlights, comments) are extracted into structured sections
- Notes are automatically updated when Zotero metadata changes
**Building Connections**
- Link literature notes to topic notes, project notes, and concept notes
- Use Obsidian's graph view to visualize connections between references
- Create MOC (Map of Content) notes that curate papers by theme
- Track reading status with custom frontmatter fields (unread, reading, read, reviewed)
- Use dataview queries to generate dynamic reading lists and bibliographies
## Annotation Extraction
One of the most powerful features is extracting PDF annotations:
**Highlight Extraction**
- Color-coded highlights can be mapped to different note sections
- Yellow highlights for key findings, blue for methodology, green for quotes
- Each highlight includes the page number and surrounding context
- Highlights are formatted as blockquotes with source attribution
- Batch extraction processes all annotations from a paper at once
**Comment Extraction**
- Marginal comments from Zotero's PDF reader are imported alongside highlights
- Comments are distinguished from highlights with different formatting
- Time-stamped comments preserve the reading chronology
- Comments can be tagged for follow-up actions (verify, discuss, replicate)
**Image Extraction**
- Area annotations (image selections) from PDFs can be extracted
- Extracted images are saved to a designated assets folder
- Image annotations include captions from the Zotero comment field
- Useful for capturing key figures, tables, and equations from papers
## Advanced Workflows
**Systematic Review Support**
- Import entire Zotero collections as literature note sets
- Use Obsidian dataview to create screening matrices
- Track inclusion/exclusion decisions with frontmatter fields
- Generate evidence tables from structured literature notes
- Export curated collections back to Zotero for bibliography generation
**Collaborative Research**
- Share Obsidian vaults via Git for team-based literature reviews
- Merge literature notes from multiple team members
- Use consistent templates to ensure compatible note structures
- Track who added which annotations and comments
**Writing Integration**
- Use pandoc with citeproc to render citations in final documents
- Export bibliography in any CSL-supported format
- Generate reference lists directly from cited literature notes
- Support for footnote, author-date, and numeric citation styles
## Integration with Research-Claw
This skill enhances the Research-Claw reference management capabilities:
- Automate literature note creation from newly added Zotero entries
- Generate synthesis notes combining insights from multiple papers
- Suggest connections between newly imported papers and existing notes
- Help maintain consistent tagging and categorization across the library
- Assist with writing literature review sections from interlinked notes
## Best Practices
- Establish a consistent citation key format before importing any references
- Create templates before importing to avoid reformatting existing notes
- Use a dedicated folder for literature notes separate from personal notes
- Regularly sync Zotero and re-extract annotations after additional reading
- Back up the Obsidian vault before bulk import operations
- Keep literature note templates versioned to track structural changes over time
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
1.0.0
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
解决学术研究人员在 Obsidian 与 Zotero 之间同步引用和笔记的核心痛点
评分依据
description 清晰准确描述核心功能
评分依据
文档结构完整,包含从基础设置到高级工作流的清晰章节划分
评分依据
基于真实存在的 obsidian-zotero-integration 插件(GitHub 2K stars),工具来源可靠
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- github.com
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。