菜单
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | summarize |
| description | Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”). |
| homepage | https://summarize.sh |
| metadata | {"daemora":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/summarize","bins":["summarize"],"label":"Install summarize (brew)"}]}} |
Fast CLI to summarize URLs, local files, and YouTube links.
Use this skill immediately when the user asks any of:
yt-dlp needed)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
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.
Set the API key for your chosen provider:
OPENAI_API_KEYANTHROPIC_API_KEYXAI_API_KEYGEMINI_API_KEY (aliases: GOOGLE_GENERATIVE_AI_API_KEY, GOOGLE_API_KEY)Default model is google/gemini-3-flash-preview if none is set.
--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)Optional config file: ~/.summarize/config.json
{ "model": "openai/gpt-5.2" }
Optional services:
FIRECRAWL_API_KEY for blocked sitesAPIFY_API_TOKEN for YouTube fallbackUse this skill whenever the user wants to create rich, visually compelling documents, presentations, or PDFs — especially when they mention images, charts, design quality, or need professional output. Triggers include: "create a presentation", "make slides", "build a deck", "write a report with images", "generate a PDF brochure", "make a Word document with visuals", "create a pitch deck", "make a professional presentation on X topic", "generate slides about Y", "create a document with good design", "make a pptx", "make a docx", "make a pdf". This skill is essential for multi-format document creation (PPTX, DOCX, PDF) with real images sourced from the web. It is also the go-to skill for any presentation with more than 5 slides, any document requiring images or charts, and any request explicitly mentioning visual quality. Always prefer this skill over individual pptx/docx/pdf skills when images, design quality, or multi-format output is involved.
Generates professional, full-production video scripts from ANY idea, topic, or brief — across ALL industries, domains, and video styles. Covers tech, AI/LLM, gaming, real estate, fashion, food, healthcare, finance, spirituality, SaaS, sports, science, education, marketing, and more. Supports ALL styles: Cinematic/Documentary, Vlog/Talking Head, Faceless/AI Voiceover, News/Journalistic, Podcast/Interview, Motivational/Hype, Satirical/Comedy, ASMR/Calm. Supports ALL formats: YouTube long-form, Shorts/Reels/TikTok, corporate, training videos. Outputs a complete production package: hook, narration, scene directions, B-roll, captions, retention hooks, CTA, music mood, pacing, and SEO tags. Auto-detects length, style, and format from the idea. USE THIS SKILL whenever a user says anything like "write a script", "make a video", "YouTube script", "Short/Reel script", "video idea", "generate a video", "script for [topic]", or describes a topic and implies they want it turned into video content — even casually.
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks Daemora to add a note, list notes, search notes, or manage note folders.
Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
Capture frames or clips from RTSP/ONVIF cameras.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.