PaperclipOrg
Claude Agent Skill · by Steipete

Summarize

A solid CLI that pulls text from URLs, PDFs, and YouTube videos, then feeds them to your choice of LLM for summarization. Handles the annoying extraction work s

Install
Terminal · npx
$npx skills add https://github.com/steipete/clawdis --skill summarize
Works with Paperclip

How Summarize fits into a Paperclip company.

Summarize drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md87 lines
Expand
---name: summarizedescription: Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).homepage: https://summarize.shmetadata:  {    "openclaw":      {        "emoji": "🧾",        "requires": { "bins": ["summarize"] },        "install":          [            {              "id": "brew",              "kind": "brew",              "formula": "steipete/tap/summarize",              "bins": ["summarize"],              "label": "Install summarize (brew)",            },          ],      },  }--- # Summarize Fast CLI to summarize URLs, local files, and YouTube links. ## When to use (trigger phrases) Use this skill immediately when the user asks any of: - “use summarize.sh”- “what’s this link/video about?”- “summarize this URL/article”- “transcribe this YouTube/video” (best-effort transcript extraction; no `yt-dlp` needed) ## Quick start ```bashsummarize "https://example.com" --model google/gemini-3-flash-previewsummarize "/path/to/file.pdf" --model google/gemini-3-flash-previewsummarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto``` ## YouTube: summary vs transcript Best-effort transcript (URLs only): ```bashsummarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract-only``` If the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand. ## Model + keys Set the API key for your chosen provider: - OpenAI: `OPENAI_API_KEY`- Anthropic: `ANTHROPIC_API_KEY`- xAI: `XAI_API_KEY`- Google: `GEMINI_API_KEY` (aliases: `GOOGLE_GENERATIVE_AI_API_KEY`, `GOOGLE_API_KEY`) Default model is `google/gemini-3-flash-preview` if none is set. ## Useful flags - `--length short|medium|long|xl|xxl|<chars>`- `--max-output-tokens <count>`- `--extract-only` (URLs only)- `--json` (machine readable)- `--firecrawl auto|off|always` (fallback extraction)- `--youtube auto` (Apify fallback if `APIFY_API_TOKEN` set) ## Config Optional config file: `~/.summarize/config.json` ```json{ "model": "openai/gpt-5.2" }``` Optional services: - `FIRECRAWL_API_KEY` for blocked sites- `APIFY_API_TOKEN` for YouTube fallback