mcpField
S
summarize

summarize

github.com/nkchivasProductivity0125 installsUpdated 36w ago
Repository

About summarize

summarize is a CLI for summarizing URLs, local files, and YouTube links, with best-effort transcript extraction for videos. It supports configurable models, output lengths, machine-readable JSON, and optional extraction fallbacks.

Key features

  1. 01Summarize URLs and local files
  2. 02Summarize YouTube links
  3. 03Extract available video transcripts
  4. 04Choose model and output length
  5. 05Return machine-readable JSON
  6. 06Configure extraction fallbacks

Use cases

  1. 01Summarizing an article URL
  2. 02Summarizing a local PDF
  3. 03Getting a YouTube video overview
  4. 04Extracting a video transcript

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nkchivas/openclaw-skill-summarize --skill summarize

After installing, type/summarizein Claude Code to confirm it loaded.

Bundled filespackage.json

Details

From the project README

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

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):

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

{ "model": "openai/gpt-5.2" }

Optional services:

  • FIRECRAWL_API_KEY for blocked sites
  • APIFY_API_TOKEN for YouTube fallback

Comments

Markdown supported