Latest Agent Skills

Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Evaluates text-to-speech systems by measuring distributional distance between synthetic and real speech across five factors, producing a scalar score without subjective MOS ratings.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Audits medical LLM benchmarks across five lifecycle phases using 46 medically tailored criteria to assess clinical relevance, data integrity, safety-critical capabilities, validity, and governance.

Scores generated image captions against reference captions and source images using the Polos metric, which is trained to align with human judgments and probes hallucination robustness and open-vocabulary evaluation.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Evaluates computational throughput and real-time efficiency of embedded CPU and GPU platforms by measuring peak FLOPS via a matrix rotation kernel and assessing inference latency and power consumption on a robotic vision pipeline.

Computes CIDEr and related metrics to score how well generated image descriptions align with human consensus, using reference sentences and triplet annotations.

Computes the AUROC metric using torchmetrics, handling binary, multiclass, and multilabel tasks with configurable thresholds and averaging.

Performs geospatial vector data analysis with GeoPandas, including reading/writing shapefiles, GeoJSON, GeoPackage, and PostGIS, geometric operations, spatial joins, overlays, coordinate transformations, and map visualization.

Train quantum circuits with automatic differentiation and build hybrid quantum-classical models using PennyLane, including VQE, QAOA, and integration with PyTorch, JAX, and TensorFlow.

Generates pixel art SVG illustrations for READMEs, docs, or slides, with character templates, chat bubbles, and scene composition guidance.

Evaluates the throughput and resource allocation efficiency of RIS-aided mobile edge computing systems by measuring the total computation task bits successfully completed under varying network conditions.

Evaluates the trade-off between file size reduction and image fidelity when encoding radio astronomy data using JPEG2000, benchmarking both lossless and lossy compression modes to determine the compression ratio at which visual artifacts first appear.

Evaluates automated metrics and vision-language models on identifying granular errors in detailed image descriptions and ranking paired descriptions against human judgments, using macro F1, pairwise accuracy, Spearman rank ρ, and Kendall's τ.

Quantifies the minimum accuracy gap needed between two models for a sampled micro-benchmark to reliably preserve their ranking, using the MDAD metric from Yauney et al. (2025).

Computes the HARE Score, an entity- and relation-centric metric for evaluating machine-generated histopathology reports against ground truth, using GatorTronS+SapBERT embeddings and relation F1.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

Evaluates the faithfulness of abstractive summaries by generating questions from summary sentences and verifying if the answers can be extracted from the source document, reporting Pearson and Spearman correlations with human judgments.

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.

Evaluates a containerized framework for deploying distributed big data workloads, measuring execution time and cloud cost scaling from four to eight nodes.

Create, analyze, and visualize complex networks and graphs in Python, covering graph construction, algorithms, generators, I/O, and visualization.

Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a.

Measures the trade-off between computation time and energy consumption in mobile edge computing by computing a weighted sum of the two objectives, given system configuration parameters and per-user task characteristics.

Quantifies audio source separation quality by computing the signal-to-distortion ratio (SDR) between ground-truth and estimated stems, with per-stem and record-level averaging.

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

Computes bibliometric indices for AI/NLP conferences, including QQE, average/median citations, and citation inequality, from annual publication and citation data.

Evaluates the naturalness, speaker similarity, and real-time synthesis speed of a Mandarin speech cloning system across diverse practical application scenarios.

Measures distributional similarity between original GAN-generated images and their semantically manipulated counterparts using the Fréchet Inception Distance (FID) metric.

Compute the Equal Error Rate (EER) metric using torchmetrics for binary, multiclass, or multilabel classification tasks, with reference signatures and usage examples.

Validates the Emotional Attitude Score (EAS) metric by measuring its consistency with human judgment on word-level sentiment polarity, using the AmbGIMT dataset and pairwise score comparisons.

Evaluates machine learning classifiers on their ability to distinguish signal from background in particle physics simulations, measuring how well algorithms rank signal events above background ones using the AUC metric.

Self-hosted observability platform for LLM applications, providing tracing, evaluation, datasets, experiments, and real-time monitoring to debug and improve AI systems.

Answers questions about a code repository by analyzing source files and citing evidence with linked citations.

Read, write, and manipulate DICOM medical imaging files, including pixel data extraction, metadata editing, anonymization, format conversion, and compression handling.

Provides guides for creating diagrams and visualizations using Mermaid, Excalidraw, PlantUML, TikZ, and other tools, covering flowcharts, architecture diagrams, and scientific illustrations.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and built-in statistical estimation.

Creates interactive Plotly visualizations in Python, covering Express and Graph Objects for scatter, line, bar, heatmap, 3D, and geographic charts, plus subplots, styling, and HTML export.

Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features.

Connects AI assistants to the Hugging Face Hub via MCP server tools to search models, datasets, Spaces, and papers, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools.

Query the Cancer Dependency Map (DepMap) for CRISPR gene dependency scores, drug sensitivity data, and gene effect profiles to identify cancer-specific vulnerabilities, synthetic lethal interactions, and validate oncology drug targets.

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Track ML experiments, manage the model registry with versioning, deploy models, and reproduce experiments using MLflow's framework-agnostic platform.

Solve single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including Pareto front analysis, constraint handling, and benchmarking on standard test problems.

Simulate open and closed quantum systems with QuTiP, covering master equations, Lindblad dynamics, decoherence, and quantum optics.

Creates, edits, and analyzes PowerPoint presentations by converting to markdown, unpacking raw XML, and applying design principles for new slides.

Explains machine learning model predictions using SHAP values, covering feature importance, visualization plots, model debugging, bias analysis, and production deployment.

Performs time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using the aeon toolkit.

Manage persistent terminal sessions, windows, and panes with tmux, including scripting multi-pane layouts and automating commands from bash.

Fetches any X/Twitter post as structured JSON via the ADHX API, including full article content, author info, and engagement metrics, without scraping or a browser.

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

Query, filter, transform, and aggregate JSON data using jq, with practical patterns for shell pipelines and integration with CLI tools.

Provides expert guidance on modern Julia 1.10+ development, covering performance optimization, multiple dispatch, testing, and production-ready practices.

Gerencia contas do Instagram via Graph API: publica fotos, vídeos, reels, stories e carrosséis, agenda posts, responde comentários e DMs, coleta métricas, pesquisa hashtags e cria templates de conteúdo.

Handle errors as values using fp-ts Either and TaskEither, replacing try/catch with predictable, type-safe error handling patterns.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, producing a prioritized report with severity ratings and concrete fixes.

Converts text to speech and speech to text using fal.ai audio models.