Total 55,747 skills, AI & Machine Learning has 9268 skills
Showing 12 of 9268 skills
Apply Complex Adaptive Systems theory to analyze phenomena exhibiting emergence, self-organization, co-evolution, and edge-of-chaos dynamics. Use this skill when the user needs to understand why a system behaves unpredictably despite known components, model agent-based interactions that produce emergent outcomes, analyze fitness landscapes, or when they ask 'why does this system behave in ways no one designed', 'how do local interactions create global patterns', or 'why do small changes sometimes cause massive system shifts'.
Implement matrix factorization to decompose user-item interaction matrices into latent factor representations. Use this skill when the user needs scalable collaborative filtering, latent feature discovery, or dimensionality reduction for recommendation — even if they say 'SVD recommendations', 'latent factors', or 'factorize the rating matrix'.
AscendC Operator Precision Evaluation. Generate a comprehensive precision test case set (≥30 cases) for the compiled and installed operator, run the tests and generate a precision verification report. Keywords: precision test, precision evaluation, precision report, accuracy, error analysis. After execution, YOU MUST display the overview, failure summary and key findings in the current conversation, and must not only attach the report path.
Deep Performance Optimization Skill for Triton Operators on Ascend NPU, dedicated to achieving the Triton operator performance improvement required by users. Core technologies include but are not limited to Unified Buffer (UB) capacity planning, multi-Tokens parallel processing, MTE/Vector pipeline parallelism, mask optimization, etc. This Skill must be triggered when the user mentions the following: performance optimization of Vector-type Triton operators on Ascend NPU.
AscendC Operator Design Completion - Assist users in completing operator architecture design, interface definition, and performance planning. Use this skill when users mention operator design, operator development, tiling strategy, memory planning, AscendC kernel design, two-level tiling, inter-core splitting, or intra-core splitting.
Map migration-relevant Megatron changes onto the official MindSpeed repository by resolving branch alignment, locating affected subsystems, and identifying concrete adaptation points. Use when Codex has structured Megatron change events and needs to decide whether MindSpeed already covers them, which MindSpeed files are likely affected, and whether patch generation is safe.
Create Docker containers for Huawei Ascend NPU development with proper device mappings and volume mounts. Use when setting up Ascend development environments in Docker, running CANN applications in containers, or creating isolated NPU development workspaces. Supports privileged mode (default), basic mode, and full mode with profiling/logging. Auto-detects available NPU devices.
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full inference pipeline (preprocessing + model + postprocessing) to run end-to-end on NPU. Workflow 5 verifies precision between ONNX and OM outputs. Workflow 6 generates a reproducible README. Supports any standard PyTorch/ONNX model. Use when converting, testing, or deploying models on Ascend AI processors.
Accepts Triton operator implementations, automatically invokes Torch small operator implementations (CPU or NPU) for precision comparison, and generates precision reports. It is used when users need to verify the correctness and precision of Triton operator implementations, compare precision with PyTorch implementations, and generate standardized precision reports.
Canonical pointer to Armani Ferrante’s X (Twitter) post at status id 1411589629384355840 for primary-source citation in Solana/Anchor/Coral-adjacent discussions. Use when the user cites this exact URL or needs a stable bookmark alongside sealevel-attacks-solana—not as a substitute for opening the post for verbatim text, thread context, or current Anchor documentation.
Maps observable MEV searcher behavior and infrastructure from public bundles, blocks, and traces—EVM builder/relay patterns, Solana Jito bundles, strategy fingerprints, profit consolidation paths, and concentration metrics. Use when the user asks for MEV bot analysis, searcher clustering, bundle/builder mapping, private-order-flow research questions, or ecosystem centralization studies—not for running competitive bots, mempool manipulation, or harassing operators.
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.