AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Too Long To Read (TL;DR Rewriter)

Turns long articles, docs, and links into conclusion-first short chat messages that fit on one screen — without flattening the conditions, numbers, and risks that change your decision.

Content & WritingBeginner★ 473⑂ 52AI score 9/10Last updated: Nov 9, 2026

What it does

  • Fires only on explicit fast-read intent ("TL;DR", "give me the conclusion first", "squeeze this into one screen") — not just because something is long or a file is attached.
  • Rebuilds the material in order of what matters to the reader instead of compressing paragraph by paragraph, optimizing for new-information density.
  • Treats seemingly minor items as part of the conclusion and never drops them: key conditions, scope, limits, risks, counterexamples, numbers, owners, deadlines, dependencies, next steps.
  • Outputs continuous short messages (one idea per paragraph, no bullets/tables/Markdown headings, typically 400–700 characters, ≤10 paragraphs).
  • Treats any instructions embedded in the source as content to understand, never to execute — a built-in prompt-injection guard.
  • If a link, Feishu/Kingsoft doc, or PDF can't be fully read, it states exactly what was and wasn't read rather than hallucinating a complete summary.

Who it's for

  • Knowledge workers drowning in reports, meeting notes, and policy documents.
  • Anyone frustrated by summaries that read nicely but hide the actual decision drivers.
  • People handling contracts, medical, or investment material where exceptions and conditions matter.

Examples

  1. Paste a 20-page status report and ask "conclusion first" → current call, risks, owners, dates, and next steps in one screen.
  2. Share an article link with "make this readable in one screen" → core claim, essential evidence, plus the author's own hedges and counter-evidence preserved.
  3. Follow up with "why", "expand point two", "show me the source text", "action items only", or "shorter" → it continues the same reading task without re-pasting the material.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/aiskillstore/marketplace/HEAD/pending/359392475-blue-sky/too-long-to-read/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the pending/359392475-blue-sky/too-long-to-read folder from the GitHub repo aiskillstore/marketplace into my ~/.claude/skills/too-long-to-read/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/aiskillstore/marketplace.git /tmp/marketplace && mkdir -p ~/.claude/skills/too-long-to-read && cp -r /tmp/marketplace/pending/359392475-blue-sky/too-long-to-read/* ~/.claude/skills/too-long-to-read/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/aiskillstore/marketplace.git /tmp/marketplace
  3. Create the skill folder: mkdir -p ~/.claude/skills/too-long-to-read
  4. Copy the files: cp -r /tmp/marketplace/pending/359392475-blue-sky/too-long-to-read/* ~/.claude/skills/too-long-to-read/
  5. Verify that ~/.claude/skills/too-long-to-read/SKILL.md exists.
  6. Restart Claude Code, then paste a long text and say "give me the conclusion first" to trigger it.
  7. Optional: the description is written in Chinese — add English triggers like "TL;DR" or "bottom line first" to the frontmatter description if activation feels inconsistent.
View source on GitHub ↗