Loading...
Loading...
Found 1,573 Skills
Interactive planning and execution for complex tasks. Use when user asks to use or invoke planner skill.
Systematic code analysis with evidence collection
Writes marketing copy for landing pages, emails, and social media posts. Use when creating promotional content, sales copy, or brand messaging.
Biome formatting, import style, strict TypeScript, naming (including React file names), or generated files.
Patterns and conventions for creating a good PR
Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.
Motto: Style counts. Context matters. Story trumps numbers.
Beads (bd) distributed git-backed issue tracker for AI agents: hash-based IDs, dependency graphs, worktrees, molecules, sync, GitLab/Linear/Jira. Keywords: bd, beads, issue tracker, git-backed, dependencies, molecules, worktree, sync, AI agents.
Store, transform, and deliver optimized images with Cloudflare Images. Covers image upload (API, Worker, Direct Creator Upload), variants, transformations (URL and Workers), bindings, Polish, signed URLs, formats (AVIF, WebP), R2 integration, watermarks. Keywords: Cloudflare Images, image transformations, variants, /cdn-cgi/image/, imagedelivery.net, Polish, AVIF, WebP, signed URLs, Direct Creator Upload, Images binding, R2, watermark.
Build serverless applications on Cloudflare Workers. Covers runtime APIs, handlers (fetch, scheduled, queue, email), bindings (KV, R2, D1, Durable Objects, Queues, AI, Vectorize), wrangler.toml configuration, local development with Miniflare, static assets, compatibility flags, testing with Vitest. Keywords: Cloudflare Workers, serverless, edge computing, Wrangler, fetch handler, scheduled handler, bindings, KV, R2, D1, Durable Objects, Workers AI, Miniflare, wrangler.toml, compatibility_date.
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
How to design formats that succeed — simplicity, community, timing