Machine learning

Chess improvement coach for the operator's 300→1500 chess.com goal.

Smart Copilot PR-review watchdog (multi-repo) that reads review state + timestamps, checks merge conflicts first, and lets an LLM decide…

Build a trustworthy eval for an LLM app, prompt, or pi skill inside the current repo, then hillclimb against it one change at a time with a held-out test split.

Push the LLM to reconsider, refine, and improve its recent output.

Generate professional engineering documentation from KiCad projects — Hardware Design Descriptions (HDD), CE Technical Files, Interface Control Documents…

Turn one exported PC Rate Management (RTM) ratebook XML into an analysis set a human or an LLM can read (JSON for the book, its rate tables and calc routines…

Evaluates a named skill by running its artifact checks and optionally invoking the skill against fixture inputs.

【视频网格图生成工具】把一个视频按时间间隔或按镜头边界抽帧,拼成一张带序号+时间戳标注的网格总览图 (grid_overview.jpg),便于一次性喂给多模态模型做全片理解、视觉一致性、物理异常等评测。当用户要求生成视频全片概览图/总览拼图/shot 网格图/grid overview/拼帧图,或要给 LLM…

Trigger Jenkins CI builds for Composable Kernel pull requests or branches with optional parameter overrides.

Compute three measures of semantic diversity on a parquet of texts — word-level DSI (BERT layers 6+7, Beaty/Patterson 2022 recipe), sentence-level mean…

Connectivity, chat, JSON & streaming regression tests for all enabled cloud LLM providers

LLM & VLM evaluation suite for home security AI applications

Use this skill for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI…

Use this skill when working with Hugging Face Datasets: loading local or Hub datasets, defining Features schemas, processing/streaming datasets, converting…

Use this skill for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers…

Use when working with ESPnet speech AI toolkit: installation, ESPnet2 recipes and training, pretrained inference/model zoo, ESPnet3 stage workflows, and…

Use to run a regression eval suite over an LLM application — fixed test cases with deterministic graders (exact match, JSON schema, regex, embedding…

ローカルの SQLite/CSV を BQMLite (bonsai/bqmlite-go) で学習・予測する。BigQuery も MLフレームワークも使わず、決定的(deterministic)に mean / linear_regression / logistic_regression を実行し、結果と…

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model…

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

Use AdalFlow to build, debug, evaluate, optimize, trace, and operate LLM task pipelines, RAG systems, agents, tools, and structured-output workflows.

AgentScope repo skill for building agents, provider connectors, RAG and memory workflows, service deployments, and local or sandboxed workspaces.