Summarize source

Skill sumitaich1998/jarvisvr/skills/research/summarize-source

An AI agentic operating system for mixed reality on the Meta Quest 3 — your own J.A.R.V.I.S. Multi-agent orchestration, multimodal perception (sight/hearing/gaze), 42 holographic widgets, 20 LLM providers.

Install

npx -y skills add sumitaich1998/jarvisvr --skill summarize-source

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Condense a single source — a URL, article, document, or pasted text — into key points the user can read at a glance. Use for "summarize this", "TL;DR", "give me the key points", or as a summarizer sub-agent merging one of several sources. Triggers: summarize, tldr, key points, gist, condense, brief me on this, what's the takeaway.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 575 tokens by cl100k_base, as published. Nobody here has run it

Summarize Source

Produce a faithful, compact summary of one source and present it as a sectioned panel (or open the original in a document_viewer). This is also the unit of work for a summarizer sub-agent in a fan-out (protocol §9.2 handoff).

Steps

Acquire the content. Provided text → use directly. A URL → web_search (or fetch via provider) to obtain the page text.
Extract structure: a one-line thesis, 3–5 key points, and any numbers / dates / names worth keeping.
Compose the summary. Lead with the thesis; bullet the points; preserve source attribution. Stay faithful — never add claims the source doesn't make.
Render a panel with sections, or show_document to open the original alongside.
Speak a 1-sentence TL;DR; offer the full panel for detail.

Output

panel (show_panel, props per registry.json):

{ "widget_type": "panel",
  "props": { "title": "Summary — Quest 4 review",
             "body": "Strong display gains, same comfort tradeoffs.",
             "sections": [
               { "heading": "Key points", "text": "1) Brighter pancake lenses 2) Better passthrough 3) Heavier" },
               { "heading": "Source", "text": "TechNews, 2026" } ],
             "scrollable": true } }

Spoken TL;DR:

{ "text": "TL;DR: a meaningful display upgrade, but comfort is unchanged.", "final": true }

As a sub-agent (fan-out)

When merging several sources, each summarizer sub-agent (a1.1, a1.2, …) summarizes one source and returns its {thesis, points, source}; the parent research-agent reconciles overlaps and dedupes before handing to result-synthesis / present-data.

Edge cases

Paywalled / unreachable URL → summarize the snippet you have and flag that it's partial; never invent the body.
Very long doc → summarize hierarchically (per-section, then overall) and open it in document_viewer with page_count set.
Conflicting claims within the source → present them as the source's open question, don't resolve silently.
Code/tabular content → use code_viewer / data_table instead of prose.

Gives 0 of the 12 instructions most note taking skills give in 575 tokens

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-06

include a visual element on every slidein 44 of 686, across 13 files
use wikilinks for internal vault linksin 35 of 686, across 11 files
commit to a single visual motif across every slidein 34 of 686, across 9 files
read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
keep 0.5 inch minimum marginsin 30 of 686, across 7 files
use subagents to visually inspect rendered slidesin 30 of 686, across 6 files
re-verify affected slides after every fixin 27 of 686, across 5 files
run content QA checks before declaring successin 26 of 686, across 3 files
Use Markdown links for external URLs onlyin 26 of 686, across 10 files
pick a bold topic specific color palettein 24 of 686, across 2 files
read editing guide before editing existing presentationsin 23 of 686, across 1 file
use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

acquire the source content
extract a one-line thesis
bullet the extracted key points
preserve source attribution
summarize the available snippet for unreachable URLs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.