repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources16d ago| #1 | --- |
| #2 | name: summarize |
| #3 | description: Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”). |
| #4 | homepage: https://summarize.sh |
| #5 | metadata: {"clawdbot":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/summarize","bins":["summarize"],"label":"Install summarize (brew)"}]}} |
| #6 | --- |
| #7 | |
| #8 | # Summarize |
| #9 | |
| #10 | Fast CLI to summarize URLs, local files, and YouTube links. |
| #11 | |
| #12 | ## When to use (trigger phrases) |
| #13 | |
| #14 | Use this skill immediately when the user asks any of: |
| #15 | - “use summarize.sh” |
| #16 | - “what’s this link/video about?” |
| #17 | - “summarize this URL/article” |
| #18 | - “transcribe this YouTube/video” (best-effort transcript extraction; no `yt-dlp` needed) |
| #19 | |
| #20 | ## Quick start |
| #21 | |
| #22 | ```bash |
| #23 | summarize "https://example.com" --model google/gemini-3-flash-preview |
| #24 | summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview |
| #25 | summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto |
| #26 | ``` |
| #27 | |
| #28 | ## YouTube: summary vs transcript |
| #29 | |
| #30 | Best-effort transcript (URLs only): |
| #31 | |
| #32 | ```bash |
| #33 | summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract-only |
| #34 | ``` |
| #35 | |
| #36 | If the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand. |
| #37 | |
| #38 | ## Model + keys |
| #39 | |
| #40 | Set the API key for your chosen provider: |
| #41 | - OpenAI: `OPENAI_API_KEY` |
| #42 | - Anthropic: `ANTHROPIC_API_KEY` |
| #43 | - xAI: `XAI_API_KEY` |
| #44 | - Google: `GEMINI_API_KEY` (aliases: `GOOGLE_GENERATIVE_AI_API_KEY`, `GOOGLE_API_KEY`) |
| #45 | |
| #46 | Default model is `google/gemini-3-flash-preview` if none is set. |
| #47 | |
| #48 | ## Useful flags |
| #49 | |
| #50 | - `--length short|medium|long|xl|xxl|<chars>` |
| #51 | - `--max-output-tokens <count>` |
| #52 | - `--extract-only` (URLs only) |
| #53 | - `--json` (machine readable) |
| #54 | - `--firecrawl auto|off|always` (fallback extraction) |
| #55 | - `--youtube auto` (Apify fallback if `APIFY_API_TOKEN` set) |
| #56 | |
| #57 | ## Config |
| #58 | |
| #59 | Optional config file: `~/.summarize/config.json` |
| #60 | |
| #61 | ```json |
| #62 | { "model": "openai/gpt-5.2" } |
| #63 | ``` |
| #64 | |
| #65 | Optional services: |
| #66 | - `FIRECRAWL_API_KEY` for blocked sites |
| #67 | - `APIFY_API_TOKEN` for YouTube fallback |
| #68 |