Loading...
Loading...
Found 2,800 Skills
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Dispatch, reconcile, and upsert group webhook pushes after tasks reach terminal states. Use to trigger by TaskID/GroupID, run one-shot backfill by date for pending/failed, and write webhook plans into WEBHOOK_BITABLE_URL (JSON/JSONL).
Expert-level aerospace systems, flight management, maintenance tracking, aviation safety, and aerospace software
Comprehensive guide to Spark Structured Streaming for production workloads. Use when building streaming pipelines, implementing real-time data processing, handling stateful operations, or optimizing streaming performance.
Personalized brainstorming agent that generates sellable utility ideas (CLI, TUI, GUI, agent tools) tailored to the user's stack and niche, with persistent memory of past suggestions. Triggered by: /spark.
Use when building, modifying, or debugging NetSuite UIF SPA components. Provides API/type lookup for `@uif-js/core` and `@uif-js/component` (constructors, methods, props, enums, hooks, and component options).
Lists TrueFoundry workspaces and clusters. Provides workspace FQNs for deployment, cluster connectivity status, available GPU types, and base domains.
Work inside the current cmux workspace and terminal. Use for cmux workspace, current workspace, caller surface, panes, surfaces, socket targeting, and non-interfering cmux automation.
Set up, review, debug, or validate Orca per-workspace environment recipes — on-demand, disposable runtimes (cloud sandboxes, VMs, or local) created fresh for each workspace. Covers first-time setup (provider prerequisites, the reusable base snapshot, the coding-agent auth snapshot, credentials, and state), not just the per-workspace lifecycle scripts. Use to stand up per-workspace environments, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure.
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
Validate project space structure, boilerplate docs, and consistency with ideas/
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.