Browse reusable Agent Skills, each with a clear purpose and practical guidance.
This skill should be used when the user asks to "convert a notebook to marimo", "migrate a Jupyter notebook to marimo", "rewrite a notebook in marimo", or wants to modernize an existing .ipynb file into a high-quality marimo .py notebook.
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black background, teal/sky/magenta/amber neon accents, glassmorphism panels, aurora gradient atmosphere) — opened in a browser, full-screened, shared. For the warm, printed, serif look use openkb-deck-editorial instead. Does NOT apply to generating skills (`openkb skill new`), research reports, or scrolling long-form documents.
Work with Deepnote project files (.deepnote). Use when creating, editing, or understanding .deepnote files — YAML-based notebook projects containing Python code, SQL queries, markdown, visualizations, and input widgets. Covers file structure, block types, database integrations, snapshots, and CLI usage.
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.
Dataset annotation management — COCO labels, sequences, export, and Kaggle upload
AI-assisted dataset annotation with COCO export — bbox, SAM2, DINOv3 methods
Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio
Ingest a raw source document into the wiki. Reads the source, extracts key information, creates or updates wiki pages, maintains cross-references, and logs the operation. Use when the user adds a new source or says 'ingest this'.
Sync Xpra Markdown release notes from docs/CHANGELOG.md into packaging/rpm/xpra.spec and packaging/debian/xpra/changelog. Use when asked to copy a release entry into RPM or Debian package changelog formats, strip Markdown URLs while preserving descriptions, update release dates and package changelog datetimes, or replace TODO placeholders for an Xpra release.