Obsidian资料整理

SKILL效率
效率 未标注权限 许可证不明确
安装这个技能

Maintain Obsidian vault core-file notes, topic synthesis notes, folder indexes, and graph links. Use when working in an Obsidian vault or document/code workspace and creating, editing, moving, deleting, scanning, summarizing, or organizing files that may need `.core.md`, `专题综合.core.md`, `资料索引.md`, or `核心文件索引.md`.

一句话选型结论

按资料字段整理

Obsidian资料整理是效率类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类效率 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_55161a2d/obsidian-core-notes
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

效率
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_55161a2d仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验未标注上游最后核验时间 · 数据更新 1791736898
正文体量5.6 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
整理待办与日程

把零散任务收进清单,排出优先级。

批量处理重复任务

把固定动作做成模板,重复执行。

把流程写成清单

把口头流程整理成可复用的步骤。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在效率场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
Obsidian资料整理当前 未标注权限 未标注 未标注 未标注 有
Nano PDF 文档 联网访问 ClawHub 市场 424.9 万 OpenClaw 有
自动更新程序 浏览器控制 ClawHub 市场 296.4 万 OpenClaw 有
Gemini 助手 联网访问 ClawHub 市场 254.7 万 OpenClaw 有
word DOCX 文档 联网访问 ClawHub 市场 239.6 万 OpenClaw 有
Excel XLSX 前端 联网访问 ClawHub 市场 227.0 万 OpenClaw 有

SKILL.md 全文

5.6 KB
模型实际读到的说明书原文,来自技能仓库

Obsidian Core Notes

Keep source files, generated .core.md notes, topic-level 专题综合.core.md notes, and Obsidian relationship indexes synchronized.

Workflow

  1. Confirm the vault/workspace root. Use the current working directory unless the user names another root.
  2. Before writing, run a scan when scope is broad:
    bash python <skill-dir>/scripts/obsidian_core_notes.py scan --root <vault-root> --json
  3. Decide the note type before writing:
    - File sidecar: one generated .core.md for a non-Markdown business source attachment.
    - Folder index: 资料索引.md for navigation and direct source lists.
    - Topic synthesis: 专题综合.core.md only for high-value folders that can support V3-like synthesis.
  4. Before revising source Markdown, folder indexes, or topic synthesis notes, apply the vault document-governance fields from 个人/公司相关个人资料/个人知识库实现路径/文档分类分级与技能取信准则.md.
  5. For create/edit/move/rename/delete operations, update the matching .core.md note and nearest 资料索引.md in the same turn.
  6. For bulk refreshes, run:
    bash python <skill-dir>/scripts/obsidian_core_notes.py refresh --root <vault-root>
    refresh creates lightweight sidecars and indexes; it does not replace human/LLM synthesis for 专题综合.core.md.
  7. For broad topic work, screen candidates before writing:
    bash python <skill-dir>/scripts/obsidian_core_notes.py topic-candidates --root <vault-root> --json
  8. Validate after any bulk operation:
    bash python <skill-dir>/scripts/obsidian_core_notes.py validate --root <vault-root>
  9. Clean generated notes only when explicitly requested:
    bash python <skill-dir>/scripts/obsidian_core_notes.py clean-generated --root <vault-root>

Rules

  • Treat non-Markdown business source files as attachments and generate distinct sidecar notes named <source filename>.core.md.
  • Do not generate .core.md sidecars for code, config, scripts, tests, runtime output, trained model output, parser output, checkpoints, vendor bundles, or generated result folders. Existing Markdown project documents such as README or planning notes may be referenced directly.
  • Reference existing Markdown core files directly; do not duplicate them.
  • Put folder navigation in 资料索引.md; put the workspace entrypoint in 核心文件索引.md.
  • Generated .core.md sidecars must use doc_role: source, doc_authority: supporting, and doc_rule: wiki-doc-governance-v1.
  • Generated 资料索引.md and 核心文件索引.md must use doc_role: common, doc_authority: preferred, and doc_rule: wiki-doc-governance-v1.
  • Deep 专题综合.core.md notes that carry durable judgments should use doc_role: result; lightweight source maps may use doc_role: common. Preserve existing higher-authority values unless the user asks to reclassify.
  • If modifying an original Markdown source file, do not overwrite result files with process/source/evidence content. Prefer adding provenance links such as related_process, related_result, or validation.
  • Do not make every folder look deeply summarized. Most 专题综合.core.md files should remain lightweight source maps unless the folder passes topic-synthesis screening.
  • V3-like topic synthesis must include source provenance, version/history cues, core judgments, content map, reusable patterns/templates/components, actions, and open questions.
  • When a user asks for aggressive cleanup, back up overwritten/deleted generated notes outside the vault before deletion.
  • Use only generated markers for safe overwrite or deletion:
  • <!-- CORE_FILE_NOTE_V1 -->
  • <!-- CORE_FOLDER_INDEX_V1 -->
  • <!-- CORE_WORKSPACE_INDEX_V1 -->
  • Never delete hand-written Markdown notes unless the user explicitly asks.
  • Exclude dependencies, caches, logs, build output, code/config files, model artifacts, training output, parser output, static vendor bundles, generated result folders, and temporary Office lock files.

References

  • Read references/core-file-rules.md before changing core-file classification.
  • Read references/obsidian-linking.md before changing note names, tags, markers, or relationship link conventions.
  • Read references/topic-synthesis-core-notes.md before screening folders for V3-like 专题综合.core.md notes or rewriting many topic notes.

Scripts

  • scripts/obsidian_core_notes.py scan: count core candidates and summarize scope.
  • scripts/obsidian_core_notes.py refresh: create or update .core.md, 资料索引.md, and 核心文件索引.md.
  • scripts/obsidian_core_notes.py topic-candidates: rank folders whose direct sources may justify V3-like 专题综合.core.md.
  • scripts/obsidian_core_notes.py validate: verify generated marker counts and common corruption patterns.
  • scripts/obsidian_core_notes.py clean-generated: remove files with generated markers; use --noise-only for code/model/output cleanup.

Common Pitfall

If the user wants "像 V3 一样的专题综合", do not stop after refresh. refresh is a graph-maintenance pass; it can produce version/source statistics, but the V3-style note is a curated synthesis pass over selected folders.

常见问题

5 问
答案由本站依据条目字段整理
Obsidian资料整理怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_55161a2d/obsidian-core-notes。安装方式为未标注。装完刷新技能列表或重开客户端。

Obsidian资料整理支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

Obsidian资料整理权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

Obsidian资料整理收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

Obsidian资料整理用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 未标注。