Agent skills for Cursor

Deploy applications and websites to Vercel.

Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents.

W&B: log ML experiments, sweeps, model registry, dashboards.

Build and maintain a persistent, compounding knowledge base as interlinked markdown files (Karpathy's LLM Wiki pattern): ingest sources…

Always use when any visual/UI/UX task is required.

Portable OKF knowledge bundle for coding-agent memory and LLM wikis — start a wiki, ingest a source, query project knowledge with…

Draft a knowledge base article from a resolved issue or common question.

Maintaining the story knowledge base: creating, updating, and organizing wiki-style reference pages in kb/.

A retrieval and Q&A assistant for local knowledge base directories, combining grep, Read, pdfplumber, and pandas by file type for progressiv

Use when positioning a KDD submission against the data-mining lineage (prior KDD volumes, ICDM, SDM, WSDM, CIKM, WWW) and the ML…

Use when auditing a KDD submission for readiness in either cycle, covering Research vs ADS track declaration, OpenReview profile…

Use when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the…

Use when revising a KDD paper into the venue's register, where the first page names a data regime, a mechanism, and scale evidence…

Every KDP Niche Finder bucket as a local research database — rank niches across buckets Trigger phrases: `find a kdp niche`, `rank kdp…

Use when implementing or debugging ANY network request, API call, or data fetching.

Preserves or recovers the reasoning behind a codebase — architectural decisions, rejected alternatives, workarounds, incident learnings…

Fetches and analyzes Amazon product historical data including pricing, BSR trends, Buy Box history, and review growth via Keepa API.

Deploys compiled firmware to embedded target boards using Keil MDK's native debugger and Flash algorithms.

Browser automation via Playwright CLI — UI testing, form filling, screenshots, scraping.

Kenjo integration via Apideck's HRIS unified API — same methods work across every connector in HRIS, switch by changing `serviceId`.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.