Total 55,549 skills, AI & Machine Learning has 9240 skills
Showing 12 of 9240 skills
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
Run team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.
Run a coding agent in an autonomous loop via a /ralph command, gated by a preflight check that every CLI is installed, linked, and authenticated. Use when driving long-running autonomous development from a wide, outcome-focused prompt.
Temu 全球站电商广告 Ads API，经 LinkFox 网关转发 Partner Global Ads / 广告投放 相关 bg/temu 接口（广告计划、广告组、创意、报表、预算出价等，接口将按 Partner 文档逐条接入）。当用户提到 Temu Global 广告、Ads、广告投放、广告计划、广告组、创意、出价、预算、广告报表、ad campaign、product-inventory 广告 时触发。商品管理用 linkfox-temu-manage-product-global；促销用 linkfox-temu-promotion-global；订单用 linkfox-temu-order-global。
Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication. Use when a user asks to analyze code or coding threads for recurring work, find a published loop, interview them to turn a goal into a bounded loop, review a loop for weak checks or unsafe authority, execute a loop with an evidence receipt, learn from completed runs, save or reuse a project loop, or validate and submit a loop to Loop Library.
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.
Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers TypedDict usage, exemplar YAML updates, and forbidden default patterns.
Used when an Agent needs to control OpenTeam via the local openteamcli: create AI group chats, add temporary roles, publish tasks, wait for replies, read results, or continue existing group chats.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
Structured framework for verifying numerical parity of HF<->MCore weight conversions. References existing tools and the add-model-support skill.