Loading...
Loading...
Found 3,409 Skills
Use this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
Searches the web via Exa’s Search API and returns source URLs (optionally with highlights, full text, summaries, and subpages). Use when the user asks to “search with Exa”, “use Exa”, “find sources/URLs”, “do web research”, “retrieve webpage text”, “get highlights/summaries”, “filter by domain/date/category”, or needs fresh results (news, real-time lookups).
Used in Git development when you need to abandon current attempts and roll back to a historical commit. It automatically archives the current state to the archive/ branch and establishes bidirectional links (source and target) in ARCHIVE.md to ensure traceability of the development decision flow. Suitable for scenarios requiring safe rollback while retaining the context of failed attempts.
Use when writing or editing a system prompt for any LLM API or SDK (any code passing a `system=` / `system` role parameter, or a `.txt`/`.md` file holding such a prompt). Applies prompt-engineering and prompt-caching best practices.
A minimal teaching framework for understanding AI Agent architecture with core loop, fake LLM interface, and skill discovery system
Control web interfaces with natural language using Page Agent, a JavaScript in-page GUI agent for browser automation
Add persistent learning and self-improvement to AI agents using ACE framework
Local-first AI coding agent powered by llama.cpp with zero tokens costs, Docker sandboxing, 20 built-in tools, LSP/Roslyn intelligence, and MCP integration
Self-referential self-improving AI agents that optimize for any computable task using meta-learning and code generation
Visualize and manage Claude Code AI agents as pixel art characters in a VS Code extension office interface
Install and use World2Agent (W2A) sensors to give AI agents structured, real-time perception of the real world
Build and run durable background coding agents with workflow orchestration, isolated sandboxes, and GitHub integration on Vercel.