summarize git:20261009.8eb2fa0A

Immutable. This exact content never changes and is served at /api/v1/blob/9b9125ab4ae5a6ab.

---
name: summarize
description: Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
metadata: {"bubbles":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/summarize","bins":["summarize"],"label":"Install summarize (brew)"}]}}
---

# Summarize

Project website: https://summarize.sh

Fast CLI to summarize URLs, local files, and YouTube links.

This optional CLI is not the default summarization engine. Codex can summarize
retrieved text itself. Prefer `--extract-only` for supported URLs; invoking an
external model or paid extraction service requires explicit user intent and may
use separate API credits, not the Codex subscription. Do not silently fall back
to another paid provider when native retrieval fails.

## 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

```bash
summarize "https://example.com" --model google/gemini-3-flash-preview
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto
```

## YouTube: summary vs transcript

Best-effort transcript (URLs only):

```bash
summarize "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