Skip to content

sumitaich1998/jarvisvr / skills/research/summarize-source

summarize-source

Verified

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.

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

  1. Acquire the content. Provided text → use directly. A URL → web_search (or fetch via provider) to obtain the page text.
  2. Extract structure: a one-line thesis, 3–5 key points, and any numbers / dates / names worth keeping.
  3. Compose the summary. Lead with the thesis; bullet the points; preserve source attribution. Stay faithful — never add claims the source doesn't make.
  4. Render a panel with sections, or show_document to open the original alongside.
  5. 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.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall