zotero-obsidian-bridge
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 "zotero-obsidian-bridge":https://skillpi.com/zh/skills/deepskill-7305ff9277bd9cf3e561b829c1939a74aae9ee728e67fc017889ea8adb2dfd9c。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/33-Galaxy-Dawn-claude-scholar/skills/zotero-obsidian-bridge/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/33-Galaxy-Dawn-claude-scholar/skills/zotero-obsidian-bridge --skill zotero-obsidian-bridge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
本条目面向文献与学术工具场景,提供“zotero-obsidian-bridge”技能的目录入口。公开标签:learning、Zotero、Obsidian、文献管理。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
---
name: zotero-obsidian-bridge
description: Use this skill when papers are collected in Zotero but the user wants detailed reading notes, project-linked literature synthesis, collection-wide paper-note coverage checks, and a connected knowledge map inside the bound Obsidian project knowledge base.
version: 0.2.0
---
# Zotero Obsidian Bridge
Bridge **Zotero as the literature source of truth** with **Obsidian as the durable project knowledge base**.
Use this skill when the user wants to:
- collect and organize papers in Zotero,
- read papers from Zotero MCP,
- create or update one detailed paper note per paper under Obsidian `Papers/`,
- synthesize those notes into `Knowledge/` notes,
- verify that a whole Zotero collection has complete canonical note coverage,
- visualize the literature structure as a default Obsidian canvas.
## Core stance
- Zotero owns **collection, metadata, attachments, PDF full text, annotations**.
- Obsidian owns **durable reading notes, project-facing literature knowledge, cross-note links, synthesis**.
- Prefer **one canonical paper note per paper**.
- Prefer **filesystem-first Obsidian notes**; do not require Obsidian MCP.
- Use this as an **explicit, agent-first skill** for Zotero ingestion.
- Prefer **`Papers/` + `Knowledge/`** as the default bridge targets.
- Prefer **`Maps/literature.canvas`** as the default graph artifact.
- Prefer a strong review schema inside each canonical paper note:
- `Claim`
- `Method`
- `Evidence`
- `Limitation`
- `Direct relevance to repo`
- `Relation to other papers`
- Treat some Zotero `webpage` items as valid literature sources when they still expose useful metadata, attachment text, or fulltext.
## Default workflow
1. Resolve the current project via `$obsidian-project-memory`.
- If the repo is already bound, use the existing vault.
- If it looks like a research repo but is not bound, bootstrap it first.
2. Read Zotero items from the target collection/query.
- If the user asked for a full collection pass, prefer full coverage over a small representative subset.
- If the transport path through MCP is failing but a local `zotero-mcp` source checkout or Python environment is available, use that local fallback to read metadata/fulltext instead of stopping the workflow.
3. For each paper:
- get metadata,
- get full text when available,
- get annotations/notes when helpful,
- create or update the canonical paper note in `Papers/`.
4. Add project-facing structure to each paper note:
- claim,
- research question,
- method,
- evidence,
- strengths,
- limitation,
- direct relevance to repo,
- relation to other papers,
- links to related papers and the best matching `Knowledge/` notes.
5. Synthesize the batch into durable `Knowledge/` notes such as:
- `Knowledge/Literature-Overview.md`
- `Knowledge/Method-Families.md`
- `Knowledge/Research-Gaps.md`
only when the synthesis is stable enough to deserve a canonical note.
6. If the request is collection-scoped, update a durable inventory note that records:
- collection size,
- item triage,
- item -> canonical note mapping,
- current coverage count such as `16 / 16`.
- use the canonical inventory path `Knowledge/Zotero-Collection-{collection-slug}-Inventory.md`.
7. Refresh `Maps/literature.canvas`.
- Prefer semantic filtering and edge thinning.
- Prefer argument-map structure (`paper + claim + method + gap`) over dense all-to-all paper links.
- If needed, keep a second lightweight display canvas such as `Maps/literature-main.canvas`.
8. If the user also wants writing deliverables, update:
- `Writing/literature-review.md`
- `Writing/comparison-matrix.md`
9. Update today's `Daily/` note and repo-local project memory.
10. Run a deterministic verification pass after batch ingestion or schema refactors.
## Default outputs
- `Papers/*.md` - one detailed reading note per paper
- `Knowledge/*.md` - durable literature synthesis notes when the batch yields stable knowledge
- `Knowledge/Zotero-Collection-{collection-slug}-Inventory.md` - when the source is a concrete Zotero collection and coverage tracking matters
- `Maps/literature.canvas` - default visual literature graph
- `Maps/literature-main.canvas` - optional lightweight presentation graph after semantic filtering
- `Writing/literature-review.md` - when the user asks for synthesis
- `Writing/comparison-matrix.md` - when cross-paper comparison is useful
## Safety rules
- Do not dump raw full text into Obsidian.
- Do not create a new note if the canonical paper note already exists.
- Do not create `Concepts/` or `Datasets/` trees by default.
- Do not treat `Experiments/`, `Results/`, or `Writing/` as the default bridge target during Zotero ingestion.
- Do not force every relationship into a new note; use frontmatter fields, sections, wikilinks, and `linked_knowledge` first.
- If a relationship is uncertain, record it in the note body or `Daily/` instead of manufacturing durable structure.
- Do not stop at a representative subset if the user explicitly asked to check **all** papers in a collection.
- Do not leave schema drift unresolved across notes in the same collection after a batch pass.
## References
Load only what is needed:
- `references/WORKFLOW.md` - end-to-end Zotero -> Obsidian procedure
- `references/PAPER-NOTE-SCHEMA.md` - detailed paper note fields and sections
- `references/COLLECTION-INVENTORY-SCHEMA.md` - canonical inventory note naming and mapping contract
- `references/LOCAL-ZOTERO-FALLBACK.md` - local fallback runbook when MCP transport fails
- `examples/example-collection-inventory.md` - example inventory note
- `scripts/verify_paper_notes.py` - deterministic schema, zotero-key, and inventory consistency check
- `../obsidian-literature-workflow/references/PAPER-NOTE-SCHEMA.md` - shared note schema
- `../obsidian-literature-workflow/references/CANVAS-WORKFLOW.md` - default literature canvas refresh rules
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
0.2.0
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
解决学术研究中从 Zotero 文献收集到 Obsidian 知识管理的完整闭环需求
评分依据
触发词精准完整,明确描述使用场景和边界条件
评分依据
文档结构清晰,包含完整的 workflow、outputs、safety rules 和 references
评分依据
工具来源明确,参数正确,覆盖主要异常情况
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。
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。