تشغيل أي مهارة في Manus بنقرة واحدة

obsidian-article-capture

النجوم٣

التفرعات٠

آخر تحديث٢٠ مارس ٢٠٢٦ في ٢٣:٤٧

Capture a web article from a URL into an Obsidian vault as an EMS Article entity note: fetch page, extract main body, create note via Obsidian CLI with article properties (`is`, `url`, `title`, `author`, `publisher`, `published`, `date`). Use when user says 'save this article', provides a URL to download, or wants the body saved as Markdown.

التثبيت

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

تشغيل في Manus

المصدر

Attamusc

Attamusc/dotfiles

فتح مستودع GitHub عرض مستودعات المنشئ

تنزيل

تشغيل في Manus

المهن ذات الصلةSOC

استنادا إلى تصنيف SOC المهني

مطوّرو الويبمهن الحاسوب والرياضيات·SOC 15-1254

مستكشف الملفات

3 ملفات

SKILL.md

readonly

name	obsidian-article-capture
description	Capture a web article from a URL into an Obsidian vault as an EMS Article entity note: fetch page, extract main body, create note via Obsidian CLI with article properties (`is`, `url`, `title`, `author`, `publisher`, `published`, `date`). Use when user says 'save this article', provides a URL to download, or wants the body saved as Markdown.

Obsidian Article Capture (EMS)

Capture a web article into your Obsidian vault as an EMS Article entity note.

When referencing vault files in responses, use wikilinks per [[utilities/Assistant Conventions]].

Prerequisite: Obsidian must be running (CLI commands require it). See the obsidian-cli skill for setup.

Workflow

Fetch
- Use functions.webfetch with format: markdown.
Extract
- Keep: title, lede, body paragraphs, meaningful lists, blockquotes.
- Drop: menus, share links, post navigation, "leave a reply", and comments.
Pick a path
- Default: atlas/notes/<Title> - <Author or Publisher>.md.
- Sanitize filename: remove /\:*?"<>|, collapse whitespace.
- If a note already exists for the same URL, update it instead of creating a duplicate.
Ensure EMS wiring exists
- entity-schemas.json includes an Article entry (required: is, in, date, url; propertyValues.is = atlas/entities/article).
- atlas/entities/article.md exists (stub OK; matches other entity notes).

Create the note via CLI

# Create the note with body content (no frontmatter — CLI handles properties)
obsidian create path="atlas/notes/<Title> - <Author>.md" content="<body>"

Set properties via CLI

obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=is value="[[atlas/entities/article]]"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=in value="[[atlas/collections/Web Articles.base]]" type=list
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=date value="<YYYY-MM-DD>" type=date
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=url value="<url>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=title value="<title>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=author value="<author>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=publisher value="<publisher>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=published value="<date>" type=date
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=status value="unread"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=saved_via value="webfetch"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=canonical_source value="<url>" type=list

Skip optional properties (author, publisher, published) if the data is not available.
date is always today's date (capture date). published is the article's original publication date.

Format body
- Start with # <Title>.
- Preserve blockquotes as > blocks.
- Add ## Source at the end with the URL.

Property Schema

Property	Type	Required	Description
`is`	link	yes	`[[atlas/entities/article]]`
`in`	list	yes	`[[atlas/collections/Web Articles.base]]`
`date`	date	yes	Capture date (today)
`url`	text	yes	Source URL
`title`	text	yes	Article title
`author`	text	no	Author name
`publisher`	text	no	Publisher/site name
`published`	date	no	Original publication date
`status`	text	no	Default: `unread`
`saved_via`	text	no	Default: `webfetch`
`canonical_source`	list	no	Canonical URL(s)

Guardrails

Do not include comments unless asked.
Do not overwrite existing properties; only add missing fields.
If the note already exists (check with obsidian read), update properties with property:set rather than recreating.

المزيد من هذا المستودع

نفس المستودع

write-like-me

Attamusc/dotfiles

Write messages, comments, PR reviews, Slack posts, and other prose in Sean's voice. Use when drafting anything that will be sent under Sean's name — code review comments, postmortem feedback, Slack messages, GitHub comments, coaching notes, design feedback, strategic takes. Triggers: 'write like me', 'in my voice', 'draft a comment for me', 'sound like me', 'sharpen this', 'this still sounds like AI'.

2026-07-093

code-review

Attamusc/dotfiles

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

2026-07-093

implement

Attamusc/dotfiles

Implement a piece of work based on a spec or set of tickets.

2026-07-093

wayfinder

Attamusc/dotfiles

Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets, and resolve them one at a time until the way to the destination is clear.

2026-07-093

triage

Attamusc/dotfiles

Move todos through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs. Maps to pi's built-in todo tool; see ../todo-tracker.md for the full tracker → tool mapping.

2026-07-093

to-spec

Attamusc/dotfiles

Turn the current conversation into a spec and publish it as a todo — no interview, just synthesis of what you've already discussed.

2026-07-093

name	obsidian-article-capture
description	Capture a web article from a URL into an Obsidian vault as an EMS Article entity note: fetch page, extract main body, create note via Obsidian CLI with article properties (`is`, `url`, `title`, `author`, `publisher`, `published`, `date`). Use when user says 'save this article', provides a URL to download, or wants the body saved as Markdown.

Obsidian Article Capture (EMS)

Capture a web article into your Obsidian vault as an EMS Article entity note.

When referencing vault files in responses, use wikilinks per [[utilities/Assistant Conventions]].

Prerequisite: Obsidian must be running (CLI commands require it). See the obsidian-cli skill for setup.

Workflow

Fetch
- Use functions.webfetch with format: markdown.
Extract
- Keep: title, lede, body paragraphs, meaningful lists, blockquotes.
- Drop: menus, share links, post navigation, "leave a reply", and comments.
Pick a path
- Default: atlas/notes/<Title> - <Author or Publisher>.md.
- Sanitize filename: remove /\:*?"<>|, collapse whitespace.
- If a note already exists for the same URL, update it instead of creating a duplicate.
Ensure EMS wiring exists
- entity-schemas.json includes an Article entry (required: is, in, date, url; propertyValues.is = atlas/entities/article).
- atlas/entities/article.md exists (stub OK; matches other entity notes).

Create the note via CLI

# Create the note with body content (no frontmatter — CLI handles properties)
obsidian create path="atlas/notes/<Title> - <Author>.md" content="<body>"

Set properties via CLI

obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=is value="[[atlas/entities/article]]"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=in value="[[atlas/collections/Web Articles.base]]" type=list
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=date value="<YYYY-MM-DD>" type=date
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=url value="<url>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=title value="<title>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=author value="<author>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=publisher value="<publisher>"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=published value="<date>" type=date
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=status value="unread"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=saved_via value="webfetch"
obsidian property:set path="atlas/notes/<Title> - <Author>.md" name=canonical_source value="<url>" type=list

Skip optional properties (author, publisher, published) if the data is not available.
date is always today's date (capture date). published is the article's original publication date.

Format body
- Start with # <Title>.
- Preserve blockquotes as > blocks.
- Add ## Source at the end with the URL.

Property Schema

Property	Type	Required	Description
`is`	link	yes	`[[atlas/entities/article]]`
`in`	list	yes	`[[atlas/collections/Web Articles.base]]`
`date`	date	yes	Capture date (today)
`url`	text	yes	Source URL
`title`	text	yes	Article title
`author`	text	no	Author name
`publisher`	text	no	Publisher/site name
`published`	date	no	Original publication date
`status`	text	no	Default: `unread`
`saved_via`	text	no	Default: `webfetch`
`canonical_source`	list	no	Canonical URL(s)

Guardrails

Do not include comments unless asked.
Do not overwrite existing properties; only add missing fields.
If the note already exists (check with obsidian read), update properties with property:set rather than recreating.