Skip to main content
skill CX Codex

zotero-obsidian-bridge — Claude Code skill

Moves Zotero-based literature notes into a project knowledge base with traceable evidence. Use it when paper notes, synthesis, and writing outputs need a fixed structure.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Galaxy-Dawn/claude-scholar --skill zotero-obsidian-bridge -a claude-code
Open on GitHub

What zotero-obsidian-bridge does

This skill defines a path from Zotero to project-local notes: Sources/Papers/, then Knowledge/, Writing/, and Maps/literature.canvas. Each paper gets one canonical note under Sources/Papers/. After substantial ingestion, it updates _system/registry.md, 02-Index.md, and the current Daily/ entry.

Core papers and reusable claims need an Evidence Record with source details, source type, method, limitation, project relevance, and claim strength. Literature synthesis placed in Knowledge/ must link directly to supporting paper notes. That is a reason to inspect source records: abstract-only items and webpage placeholders cannot support durable claims.

Before material reaches Knowledge/ or Writing/, the skill applies the Claim Promotion Gate. Every promoted claim must point to an Evidence Record ID, use a sufficiently strong source type, and retain wording appropriate for a later report, manuscript, or rebuttal.

What it helps with

  • create canonical paper notes in Sources/Papers/
  • link literature synthesis to supporting sources
  • record evidence for reusable claims
  • keep abstract-only notes out of durable claims
  • update project indexes after literature ingestion

Example prompts for the agent

  • “Use zotero-obsidian-bridge to turn these Zotero papers into notes under Sources/Papers/.”
  • “Create a Knowledge/ synthesis for these papers and link each claim to its Evidence Record.”
  • “Check whether the claims intended for Writing/ pass the Claim Promotion Gate.”

How to install zotero-obsidian-bridge

1Skills CLI (Vercel)

npx skills add Galaxy-Dawn/claude-scholar --skill zotero-obsidian-bridge -a claude-code

2Manually: put the files in place

~/.claude/skills/zotero-obsidian-bridge/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/zotero-obsidian-bridge/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about zotero-obsidian-bridge

How do I install zotero-obsidian-bridge in Claude Code?

Run npx skills add Galaxy-Dawn/claude-scholar --skill zotero-obsidian-bridge -a claude-code, then run npx skills add Galaxy-Dawn/claude-scholar --skill zotero-obsidian-bridge -a claude-code again. The skill file is located at ~/.claude/skills/zotero-obsidian-bridge/SKILL.md.

What does zotero-obsidian-bridge do?

It structures Zotero literature notes inside a project and requires evidence links for promoted claims. It also directs synthesis to Knowledge/, writing material to Writing/, and the derived graph to Maps/literature.canvas.

Which sources cannot support durable claims?

Abstract-only items and webpage placeholders cannot support durable claims. A promoted claim needs an Evidence Record ID and a source type strong enough for that claim.

Source text

SKILL.md · MIT
---
name: zotero-obsidian-bridge
description: Use this skill when Zotero is the literature source of truth and the project KB should receive source notes under Sources/Papers plus project-linked synthesis in Knowledge and Writing.
version: 0.3.0
---

# Zotero Obsidian Bridge

Use this skill when papers live in Zotero and the project KB should receive project-local notes.

Default flow:

```text
Zotero -> Sources/Papers -> Knowledge -> Writing -> Maps/literature.canvas
```

Rules:
- one canonical paper note per paper under `Sources/Papers/`
- literature synthesis goes to `Knowledge/`
- writing-oriented outputs go to `Writing/`
- `Maps/literature.canvas` is the default derived graph artifact
- update `_system/registry.md`, `02-Index.md`, and today's `Daily/` after substantial ingestion

## Evidence extraction requirement

Core papers and papers with reusable claims should include an evidence record. Abstract-only or placeholder notes may stay in `To-Read` until there is enough evidence to extract a reusable claim.

```md
## Evidence Record

Evidence ID:
Source:
Source type: full paper | preprint | dataset | experiment artifact | project note | abstract-only | webpage placeholder
Supports:
Contradicts:
Method / dataset / metric:
Limitation:
Project relevance:
Claim strength: speculative | observed | supported | strong
```

Use `../research-ideation/references/research-contract.md` as the shared contract for Evidence Records and claim strength definitions.

Before synthesis lands in `Knowledge/` or `Writing/`, apply the shared Claim Promotion Gate:
- every promoted claim must point back to an Evidence Record ID,
- source type must be strong enough for the claim,
- abstract-only and webpage-placeholder items cannot support durable claims,
- allowed wording and forbidden stronger wording must be preserved when the claim may later enter a report, manuscript, or rebuttal.

When synthesis lands in `Knowledge/`, link the supporting paper notes explicitly. Do not promote literature synthesis that cannot point back to source notes.

© Galaxy-Dawn · MIT · Galaxy-Dawn/claude-scholar

Similar skills

Everything for Science and research →

From the same set29

review-response Sorts reviewer comments into classes and drafts a structured rebuttal anchored to artifacts in the paper. Useful when a conference deadline is close. CX Codex +1 555installs results-analysis Turns ML experiment artifacts into a strict analysis bundle: statistics, real figures, report. Built for checking significance, not for writing prose. CX Codex +1 542installs ui-ux-pro-max Turns a vague "make it look good" into a concrete design system: palette, typography, component rules and stack-aware notes. CX Codex +1 506installs results-report Turns a finished experiment into a structured report: what was tested, what holds up, what to do next. Runs after the results-analysis skill. CX Codex +1 490installs skill-quality-reviewer Audits local skills across description quality, structure, and writing style. Generates weighted letter grades and prioritized remediation plans before sharing. CX Codex +1 457installs ml-paper-writing Turns a research repo into a draft paper for NeurIPS, ICML, ICLR, ACL, AAAI or COLM. Citations get fetched and verified through APIs instead of written from memory. CX Codex +1 457installs publication-chart-skill Converts research data into publication-ready scientific figures and tables using pubfig and pubtab. Helps select chart types and exports clean LaTeX. CX Codex +1 411installs daily-paper-generator A skill that searches arXiv and bioRxiv for recent papers on a topic and writes bilingual reviews of the ones it picks. CX Codex +1 410installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor