rpi5/openclaw/plugins/summarize/skills/summarize/SKILL.md
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
npx skillsauth add nsimonfr/nic-os summarizeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 fallbackdatabases
Query today's Immich "on this day" memories and print a summary picoclaw can relay. Use when the user asks about Immich memories, on-this-day, or a recap of past photos from today's date.
documentation
Promote items from Wiki/Inbox into curated Wiki/Pages, merging or creating as Wiki/Schema dictates
development
Audit the LLM Wiki for orphans, broken links, duplicates, and stale facts; write a report page
documentation
Drop a URL or pasted note into the LLM Wiki Inbox in AFFiNE