Skills Plugins MCP Prompt Model 博客 我的中心

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=agricidaniel-claude-obsidian-skills-obsidian-markdown-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name obsidian-markdown description Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations. Obsidian Flavored Markdown Use this as a compact fallback for Obsidian-specific syntax. Prefer a separately installed kepano/obsidian-skills obsidian-markdown skill when available, then current Obsidian Help , for detailed or version-sensitive questions. Resolve the installed product root from this skill's own location, not from the vault or current working directory: PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian CORE= " $PRODUCT_ROOT /scripts/claude-obsidian.py" test -f " $CORE " Answer syntax questions read-only. If the user requests a vault edit, draft the complete note, read operation-transactions.md , and build one claude-obsidian.transaction.v1 bundle with operation_type: markdown and only wiki/ targets. Inspect it, then set APPROVAL_SHA256 to the returned approval_sha256 after review and apply it through the same vault-bound plan. A canonical page create or removal includes an active index or MOC update in that bundle; update the overview only when its stable high-level synthesis changed: python3 " $CORE " transaction inspect " $BUNDLE " --vault " $VAULT " python3 " $CORE " transaction apply " $BUNDLE " --vault " $VAULT " \ --approved-plan-sha256 " $APPROVAL_SHA256 " Never write a note directly. Properties Use flat YAML properties and YYYY-MM-DD dates. Quote wikilinks inside YAML. --- type: concept title: "Contextual Retrieval" created: 2026-07-11 updated: 2026-07-11 status: developing tags: - retrieval - ai/knowledge aliases: - Context-aware retrieval related: - "[[Retrieval]]" sources: - "[[Anthropic Contextual Retrieval]]" --- Do not nest objects in generated wiki properties. Use block lists rather than inline YAML arrays. Quote numeric-only tag values, for example - "2026" , so YAML parsers preserve them as tags instead of numbers. Keep unknown existing properties unless the requested edit changes them. Wikilinks and embeds [[Note Name]] [[Note Name|Display text]] [[Note Name#Heading]] [[Note Name#^block-id]] [[Folder/Note Name]] This paragraph is addressable. ^evidence-block ![[Note Name#Summary]] ![[diagram.png|480]] ![[paper.pdf#page=3]] Match the target filename exactly. Use a vault-relative folder path when a basename is ambiguous. Use standard Markdown links for external URLs; use wikilinks for this vault's notes. Callouts > [!note] > Supporting context. > [!warning] Review required > This claim has contradictory evidence. > [!question]- Open question > What evidence would resolve this? - starts collapsed and + starts expanded. Common built-in types include note , abstract , info , todo , tip , success , question , warning , failure , danger , bug , example , and quote . Preserve custom vault callout types rather than rewriting them. Other Obsidian syntax #inline-tag #nested/tag ==Highlighted text== Visible text %%hidden comment%% Inline math: $E = mc^2$ $$ \int _0^1 x^2\,dx = \frac{1}{3} $$ ```mermaid flowchart LR Source --> Claim ``` Standard CommonMark/GFM headings, lists, tasks, tables, code fences, and footnotes remain valid. Avoid HTML when native Markdown is sufficient. Validate a drafted note Parse the YAML boundary and keep property types consistent. Verify every internal target, heading, and block reference that can be checked locally; never fabricate a target to make a link look complete. Keep evidence wording distinct from inference and preserve source locators. Ensure code fences and callout quoting are balanced. Run deterministic wiki lint after a requested mutation and report remaining findings without silently repairing them. For source-cited pages, also follow provenance.md . Report the transaction operation ID and exact changed paths after an applied edit.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。