跳到主要内容
知仓学习社ZHICANG

obsidian-literature-workflow

Use this skill when the user keeps paper notes inside an Obsidian project knowledge base and wants filesystem-first literature review, explicit agen…

不碰外部(只输出文字)无严重或高危命中brycewang-stanford/Auto-Empirical-Research-Skills

它会碰到什么

扫了多少6 个文本文件,40 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Obsidian Literature Workflow

Handle the literature sub-workflow inside the filesystem-first Obsidian project knowledge base.

Role in the workflow

This is a supporting skill under obsidian-project-memory.

Use it when the user says things like:

  • “My papers are in Obsidian”
  • “Read papers from Zotero and create notes in the vault”
  • “Review the notes under Papers/
  • “Generate literature knowledge notes from this project vault”
  • “Connect paper notes to project knowledge”
  • “Show me the literature structure as a map/graph”
  • “Check whether all papers already have detailed notes”

Assumptions

  • The project is already bound through .claude/project-memory/registry.yaml, or can be imported with obsidian-project-bootstrap
  • Durable paper notes live under Papers/ inside Research/{project-slug}/
  • Obsidian note writing is done through the filesystem; no Obsidian MCP is required
  • Zotero may still be used as the source of metadata/full text; use $zotero-obsidian-bridge when the source corpus is in Zotero

Default workflow

  1. Read bound project memory and locate the vault root.
  2. If the source papers are in Zotero, explicitly use $zotero-obsidian-bridge to pull them into canonical Papers/*.md notes.
  3. Scan Papers/ and adjacent synthesis notes using filesystem tools.
  4. Normalize note metadata and structure using $obsidian-markdown.
  • Prefer the standardized review schema:
  • Claim
  • Method
  • Evidence
  • Limitation
  • Direct relevance to repo
  • Relation to other papers
  1. Query narrowly first:
  • read the relevant paper notes,
  • then the linked Knowledge/ notes,
  • and only then open Writing/ if the user asked for a review or comparison deliverable.
  1. Prefer updating existing paper notes and literature synthesis notes over creating sibling notes.
  2. Default literature synthesis should land in Knowledge/, not Experiments/ or Results/:
  • update Knowledge/Literature-Overview.md
  • update Knowledge/Method-Families.md
  • update Knowledge/Research-Gaps.md

when the synthesis is stable enough to deserve canonical notes.

  1. If the source is a named collection and the user cares about completeness, maintain a collection inventory note with explicit coverage mapping.
  2. Refresh Maps/literature.canvas after major paper-note changes or batch note creation.
  • Prefer argument-map structure over dense all-to-all links.
  • Prefer semantic filtering and edge thinning.
  • Create Maps/literature-main.canvas only when a lightweight presentation graph is needed.
  1. Update the daily note and project memory with what changed.

Default outputs

  • Papers/ remains first-class: one durable paper note per paper whenever possible
  • Knowledge/ holds durable literature synthesis notes
  • Maps/literature.canvas is the default visual graph surface
  • literature work should usually produce at least one of:
  • new or updated paper notes,
  • new or updated knowledge notes,
  • literature-canvas refresh,
  • optional writing synthesis when requested

Default stance

Do not assume by default:

  • Concepts/
  • Datasets/
  • .base views

The literature workflow may create Maps/literature.canvas by default. Other artifacts still require explicit justification.

References

Load only what is needed:

  • references/PAPER-NOTE-SCHEMA.md - detailed paper-note frontmatter and sections
  • references/CANVAS-WORKFLOW.md - how and when to refresh Maps/literature.canvas

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。