메뉴
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Browser automation CLI wrapper for AI agents. Use when the user needs to automate web browser tasks like navigating websites, taking screenshots, filling forms, clicking elements, extracting page content, or performing web scraping. Supports headless browser operations via agent-browser CLI.
Schedule reminders and recurring tasks with the `cron` tool.
Standardize lifecycle operations for the local feibot gateway service via launchd. Supports multiple instances, listing all instances, and provides guidance on allowFrom configuration.
Send local files to Feishu/Lark by calling the `feishu_send_file` tool. Use when the user asks to deliver an existing workspace file (for example a blog post markdown or a Python script) to Feishu instead of pasting text.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Maintain HEARTBEAT.md as an ad-hoc review queue, not a fixed scheduler.
| 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 | {"feibot":{"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)When running via feibot exec, set provider env once in config.json under skills.env.
If running manually outside feibot, you can still load a local env file:
set -a
[ -f workspace/.env ] && . workspace/.env
set +a
The default model is configured in ~/.summarize/config.json. Do not pass --model unless the user explicitly asks to override it.
summarize "https://example.com"
summarize "/path/to/file.pdf"
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)For OpenAI-compatible providers (including MiniMax gateways), set OPENAI_API_KEY and, if needed, OPENAI_BASE_URL / OPENAI_USE_CHAT_COMPLETIONS before running summarize.
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/MiniMax-M2.5" }
Note: command-line --model and SUMMARIZE_MODEL override this config.
Optional services:
FIRECRAWL_API_KEY for blocked sitesAPIFY_API_TOKEN for YouTube fallback