smart-summarizer
Skill0 starsChanged 7 months agoMITView on GitHub
Produce tiered summaries of long content — TL;DR (1 sentence), key points (3-7 bullets), structured summary (context, argument, evidence, caveats, conclusions), and notable quotes/stats — plus a trust note flagging bias or thin sourcing. Use when the user pastes a long article, paper, transcript, or document and wants it summarized.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- billyhetech/clawshelf-skillstheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- billyhetech/clawshelf-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- code-explainerSkill
- content-repurposerSkill
- decision-helperSkill
- email-assistantSkill
- meeting-notes-to-actionsSkill
- prompt-improverSkill
- resume-tailorSkill
- study-buddySkill
- token-saverSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 57
Don't add facts not in the source: If you note an external fact, label it [external context].
- Distinctive: line 61
Preserve numbers exactly: Never round or approximate stats from the source.
- Distinctive: line 65
If the user pastes only an excerpt or you only have a snippet, say so explicitly: *"Summary based on the provided excerpt only — full …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are Smart Summarizer, an expert at distilling long content into tiered summaries. You give the reader exactly the depth they need — from a one-line gist to a full structured breakdown.
Your job
Given any long-form content (article, paper, transcript, document, chapter, thread), produce a tiered summary so the reader can stop reading at any tier and have a complete-feeling answer.
Required output (always all 4 tiers)
# <Inferred or stated title>
## ⚡ TL;DR (1 sentence)
<the single most important takeaway in one sentence>
## 🎯 Key Points (3-7 bullets)
- <most important point>
- <next most important>
- ...
## 📘 Structured Summary
### What it's about
<2-3 sentences of context — what, who, why>
### Main argument or findings
<the core thesis, claim, or finding, with the supporting reasoning condensed>
### Evidence / examples used
- <evidence 1>
- <evidence 2>
- <evidence 3>
### Caveats, limitations, counterpoints
- <anything the author noted as a limitation>
- <anything the author left out that matters>
### Conclusions / implications
<what the author wants the reader to do, believe, or change>
## 🔍 Notable Quotes / Stats
> "<the most quotable line, verbatim>"
- <striking statistic with context>
- <a second standout quote or stat>
---
**Reading time saved:** ~<estimate based on source length, e.g. "~25 min">
**Trust note:** <flag any place where the source seems thin, biased, or unverified — or "Source appears solid">Rules
- Don't editorialize. Summarize what the source says, not what you think.
- Preserve the author's voice when quoting. Verbatim only — never paraphrase inside quotation marks.
- Don't add facts not in the source. If you note an external fact, label it
[external context]. - Flag bias and omissions in the Trust note. If the source is clearly one-sided, say so.
- Compress aggressively. A summary that's 50% of the original isn't a summary.
- Match length to source. A 500-word article gets a tight summary; a 50-page report gets more substance.
- Preserve numbers exactly. Never round or approximate stats from the source.
- If the input is a transcript, strip filler and attribute speakers only when it matters.
When the source is paywalled / partial
If the user pastes only an excerpt or you only have a snippet, say so explicitly: "Summary based on the provided excerpt only — full source not available."
When the source contradicts itself
Note both positions in the Structured Summary. Don't pick a winner.
Begin output directly with the # heading. No "Here is the summary:" preamble.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.