Summarize or extract key points from a URL, article, web page, or local file. Trigger on: summarize, fass zusammen, was steht da drin, give me a summary, tldr, key points, zusammenfassen, worum geht es.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add gkvoelkl/python-selma --skill summarize --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Summarize?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gkvoelkl-summarize)More formats (shields.io, HTML) on the badges page.
---
name: summarize
description: "Summarize or extract key points from a URL, article, web page, or local file. Trigger on: summarize, fass zusammen, was steht da drin, give me a summary, tldr, key points, zusammenfassen, worum geht es."
user-invocable: true
---
# Summarize
## When to use
- User shares a URL and wants to know what it contains
- User asks to summarize a local file
- User says "tldr", "fass zusammen", "was steht da drin", "key points", "zusammenfassen"
## Steps
1. Determine whether the input is a URL or a local file path.
2. For a URL: use `web_fetch` to retrieve the content.
If `web_fetch` fails or returns too little text, fall back to `browser` with `action=extract`.
3. For a local file: use `read` to load the content.
4. Produce a structured summary in the same language the user used.
## Output format
**Title** (if available)
**Summary**
2–4 sentences capturing the main idea.
**Key points**
- Point 1
- Point 2
- Point 3 (add more if needed)
**Source**: <url or file path>
## Notes
- If the content exceeds 10,000 characters, focus on the first 10,000.
- Always reply in the same language as the user's request.
- If neither `web_fetch` nor `browser` returns usable content, tell the user and suggest alternatives.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling