Agent skills for Claude Code

Stands up one navigable feature the same way every time — a fixed lib/features/<feature>/presentation/ folder (dumb View + one 1:1…

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.

Scala conventions for this codebase: coding style, project layout, and tooling preferences.

Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values'…

Scans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed.

Use when the user asks to initialize or bootstrap the complete project documentation/conventions set, set up project conventions…

Transcribe a web article from a URL into a local markdown file with YAML frontmatter (title, author, date, source URL, word count).

Suggest WCAG 2.1 / Section 508 corrected captions for a YouTube video.

How to build scenes — entry, dialogue, pacing, transitions.

Transitional intro cards between video scenes.

Use when adding or editing a 3D scene in a BRICKS app with the Scene3D brick — product viewers, showcases, menus with 3D flair, ambient…

Use when making a Scene3D brick interactive — spin/inspect product viewers, click-to-explore demos, kiosk attract loops, or simple 3D…

Guide SceneKit game implementation, repair, and maintenance.

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology.

Use when adding or auditing Schema.org structured data for AI extraction and rich results.

Build data-entry forms with Zod → JSON Schema → JSON Forms (jsonforms.io), custom Tailwind/token renderers, and typed submit wiring.

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database.

Apply the ScholarEval framework to systematically evaluate scholarly and research work.

Translates academic papers and research markdown files while preserving LaTeX formulas, code blocks, and image references.

knows.academy currently indexes only 2026 papers (mostly arXiv). For older or non-2026 papers (Transformer 2017, BERT 2018, classics…

Guides manuscript content allocation across main text, appendix, supplementary materials, and multimedia for Scientia Sinica Informationis…