skilld
All skills
steipete avatar

/summarize

@5867207
by Peter Steinbergersteipete/clawdis391k stars
82,234

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

Ask your Agent

Use this Skill: https://skilld.dev/gh/steipete/clawdis/summarize

This session only. Nothing lands on disk.

SKILL.md

≈28 tokens always: the name and description. ≈390 when used: this file.

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"
summarize "/path/to/file.pdf"
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto

YouTube: summary vs transcript

Best-effort transcript (URLs only):

summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract

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 auto; config may choose the provider/model.

Useful flags

  • --length short|medium|long|xl|xxl|<chars>
  • --max-output-tokens <count>
  • --extract (print extracted content, no LLM summary)
  • --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

Source: SKILL.md on GitHub

Third-party checks

2 warnings16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill integrates a command-line tool for summarizing various content sources such as websites, videos, and local documents. It relies on an external software dependency from a third-party repository and creates a potential surface for indirect prompt injection from the content it processes.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 2 issues

  • Runlayer7mo

    1/1 file flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 5867207. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 1 hour ago.

Activeupdated 5 months ago

Capability

homepage
https://summarize.sh
Other metadata
metadata
{
  "openclaw": {
    "emoji": "🧾",
    "requires": {
      "bins": [
        "summarize"
      ]
    },
    "install": [
      {
        "id": "brew",
        "kind": "brew",
        "formula": "steipete/tap/summarize",
        "bins": [
          "summarize"
        ],
        "label": "Install summarize (brew)"
      }
    ]
  }
}

Topics

  • CLI
  • summarize
  • transcribe
  • youtube
  • pdf
  • url
  • openai
  • anthropic
  • content-extraction

README badge

README badge for steipete/clawdis/summarize

What it does

Wraps a CLI tool that summarizes or transcribes URLs, YouTube videos, PDFs, and local files using OpenAI, Anthropic, xAI, or Google APIs. Supports transcript extraction, configurable summary length, and optional Firecrawl/Apify fallbacks for blocked or YouTube content.

Generated from the current SKILL.md.

Frequently asked

What input formats does this skill support?
URLs, local files (including PDFs), YouTube links, and video/podcast transcripts. YouTube transcript extraction is best-effort and does not require yt-dlp.
Which LLM providers does this skill work with?
OpenAI, Anthropic, xAI, and Google Gemini. Set the corresponding API key (OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, or GEMINI_API_KEY) and optionally configure the model in ~/.summarize/config.json.
Can I get a transcript instead of a summary?
Yes, use the --extract flag to print extracted content without LLM summarization. For YouTube URLs specifically, use --youtube auto --extract for best-effort transcript extraction.
What do I do if the skill can't extract content from a website?
Set FIRECRAWL_API_KEY to enable the Firecrawl fallback (--firecrawl auto|off|always). For YouTube, you can also set APIFY_API_TOKEN for an Apify fallback.

Generated from the current SKILL.md. These answers refresh after source changes.