Claude Skills by qhjqhj00

Evaluates the routing stability, robustness, and task performance of Sparse Mixture of Experts (SMoE) models enhanced with similarity or attention-aware mechanisms. It probes how token-level routing decisions affect language modeling, image classification, and downstream fine-tuning under both clean and perturbed conditions. Use when the user wants to benchmark on Wikitext-103, ImageNet-1K, ImageNet-C, ImageNet-A, ImageNet-R, ImageNet-O, SST5, SST2, Banking-77, or asks about evaluating this t...

Evaluates a Mixture of Experts model on cross-lingual machine translation and diverse natural language understanding tasks to measure how expert clustering and routing affect translation quality and classification accuracy. Use when the user wants to benchmark on WMT 2014 EN-DE + WMT-17 news-commentary-v12, GLUE (MNLI, CoLA, SST-2, QQP, QNLI, MRPC, STS-B), or asks about evaluating this task. Reports BLEU.

Evaluates the ability of audio source separation models to isolate individual instrument stems from mixed stereo recordings. It probes fine-grained separation capabilities across a hierarchical taxonomy of up to 11 stems, testing robustness to stem imbalance and un-mastered audio characteristics. Use when the user wants to benchmark on MoisesDB, or asks about evaluating this task. Reports SDR.

This benchmark evaluates multilingual knowledge graph embedding models on the task of completing missing facts across six languages. It specifically probes the model's ability to leverage cross-lingual information flow, benefit from translated training triples, and retain facts when queried in different scripts. Use when the user wants to benchmark on mOKB6, or asks about evaluating this task. Reports H@10.

Evaluates a reinforcement learning model's ability to generate molecules that optimize specific target chemical or biological properties. It probes the model's exploration-exploitation balance in navigating chemical space to find high-scoring structures for penalized LogP, drug-likeness (QED), structural similarity, and kinase inhibition targets. Use when the user wants to benchmark on Mol-AIR Goal-Directed Generation Tasks, or asks about evaluating this task. Reports Best Property Score.

Evaluates a model's ability to explore chemical space and rediscover structurally diverse molecules with similar bioactivity against a specific target, rather than just optimizing for a single molecule. Use when the user wants to benchmark on MolExp, or asks about evaluating this task. Reports MolExpL.

Evaluates autonomous AI agents' ability to execute complex, multi-step drug discovery workflows, including molecular screening (property filtering, binding affinity comparison, docking) and molecular optimization (structural editing, physicochemical property improvement). Use when the user wants to benchmark on MolBench, or asks about evaluating this task. Reports optimization success rate.

Evaluates the ability of graph neural networks to learn robust molecular representations via self-supervised contrastive learning, and their transferability to downstream molecular property prediction tasks (classification and regression). Use when the user wants to benchmark on BBBP, Tox21, ClinTox, HIV, BACE, SIDER, MUV, FreeSolv, ESOL, Lipo, QM7, QM8, or asks about evaluating this task. Reports ROC-AUC.

Evaluates the reliability and predictive performance of Graph Neural Networks (GNNs) trained with Bayesian inference methods on molecular property prediction tasks. It specifically probes how well these models calibrate their uncertainty and generalize to out-of-distribution molecular scaffolds compared to standard maximum a posteriori (MAP) training. Use when the user wants to benchmark on BBBP, BACE, HIV, Tox21, or asks about evaluating this task. Reports ECE.

Evaluates a model's ability to reconstruct and predict time-varying 3D molecular surfaces in a continuous, resolution-independent manner. It measures volumetric overlap, point-to-point geometric distance, and surface normal alignment across diverse protein trajectories. Use when the user wants to benchmark on Sun et al. (2023) Protein Trajectories, or asks about evaluating this task. Reports volumetric IoU.

Evaluates the quality of pretrained molecular representation learning models on downstream ADMET prediction tasks. It probes whether modern deep learning architectures (GNNs, transformers) can outperform traditional chemical fingerprints and established baselines like ECFP. Use when the user wants to benchmark on Collection of ADMET endpoint datasets, or asks about evaluating this task. Reports Mean AUROC.

Evaluates the predictive performance of various machine learning architectures (deep vs. non-deep) on molecular property prediction tasks. It probes how well models handle irregular, tree-like molecular data patterns across both classification and regression benchmarks. Use when the user wants to benchmark on BACE, HIV, BBBP, ClinTox, SIDER, Tox21, ToxCast, MUV, SARS-CoV-2, ESOL, Lipop, FreeSolv, QM7, QM8, or asks about evaluating this task. Reports AUC_ROC.

Evaluates a model's ability to learn molecular representations for property prediction across classification and regression tasks. It probes the model's capacity to capture local atomic environments, multi-scale fragment structures, and long-range graph dependencies. Use when the user wants to benchmark on MoleculeNet, PharmaBench, LRGB, or asks about evaluating this task. Reports ROC-AUC, RMSE.

Evaluates sample-efficient molecular scaffold optimization by testing how well a model can modify a given molecular scaffold to improve target properties (e.g., drug-likeness, docking scores) while preserving structural similarity, under a strict budget of oracle evaluations. Use when the user wants to benchmark on Gao et al. (2022) sample-efficiency benchmark, or asks about evaluating this task. Reports Top-10 average score.

Evaluates the accuracy of quantum chemistry methods in predicting equilibrium molecular geometries and vibrational properties against experimental benchmarks. It probes the ability of different basis sets and ansatzes to capture electron correlation and potential energy surface curvature. Use when the user wants to benchmark on Small Molecule Benchmark (H2, LiH, BeH2, H2O), or asks about evaluating this task. Reports vibrational_frequency_error_pct.

This benchmark evaluates uncertainty estimation methods for molecular force fields by measuring predictive accuracy on equilibrium structures, calibration of uncertainty scores, and out-of-distribution detection capabilities on non-equilibrium or left-out molecular configurations. Use when the user wants to benchmark on MD17, QM7X, or asks about evaluating this task. Reports AUC-ROC.

Evaluates large language models' ability to perform symbolic reasoning on molecular graphs, including counting atomic features, indexing substructures, and generating constrained molecular structures. It probes whether models understand chemical topology and composition rather than relying on memorized token patterns or canonical SMILES conventions. Use when the user wants to benchmark on MOLECULARIQ, or asks about evaluating this task. Reports accuracy.

Evaluates the ability of generative models to design molecules that satisfy multiple property constraints (e.g., biological activity, drug-likeness, synthetic accessibility) while maintaining chemical diversity and novelty. It also assesses the faithfulness of extracted substructure rationales in explaining target properties. Use when the user wants to benchmark on GSK3β, JNK3, Toxicity, or asks about evaluating this task. Reports Success.

Evaluates molecular property prediction and ADC payload activity classification using hybrid graph neural networks. Probes the model's ability to capture 2D topological and 3D structural features for binary classification across diverse chemical and biological tasks. Use when the user wants to benchmark on MoleculeNet, ADC Payload Dataset, or asks about evaluating this task. Reports ROC-AUC.

Evaluates a model's ability to predict molecular properties from SMILES strings by fine-tuning on 7 classification benchmarks and measuring performance under scaffold splitting. Use when the user wants to benchmark on MoleculeNet, or asks about evaluating this task. Reports ROC-AUC.

Evaluates the ability of graph-theoretic and machine learning models to predict continuous molecular properties (biological activity, physicochemical, and thermodynamic) from molecular structure. It tests generalization across diverse chemical spaces and compares classical feature-based approaches against deep learning baselines. Use when the user wants to benchmark on MoleculeNet (BACE, LogP Synthetic, LogP Experimental, ESOL, SAMPL), or asks about evaluating this task. Reports R^2.

Evaluates graph neural networks on molecular property prediction tasks, testing the model's ability to capture multi-view (node and edge) structural information for accurate classification and regression of chemical properties. Use when the user wants to benchmark on MoleculeNet (11 datasets), or asks about evaluating this task. Reports AUC-ROC.

Assesses an LLM's capability to iteratively optimize molecular structures for specific biological targets (JNK3, GSK3β) using evolutionary search guided by generative prompts. Use when the user wants to benchmark on ZINC, or asks about evaluating this task. Reports AUC_top-k.

Evaluates molecular property prediction models across classification and regression tasks on chemical datasets. It probes model generalization under different data splits (scaffold vs. random) and tests the impact of representation type (learned vs. fixed descriptors) and evaluation metric choice on reported performance. Use when the user wants to benchmark on MoleculeNet, Opioids-related, or asks about evaluating this task. Reports AUROC, RMSE.

This benchmark evaluates the ability of graph neural networks to predict ground-state 3D molecular geometries directly from 2D molecular graphs, and subsequently assesses how well these predicted geometries improve downstream quantum property prediction (HOMO-LUMO gap). Use when the user wants to benchmark on Molecule3D, or asks about evaluating this task. Reports MAE.

Evaluates molecular property prediction by fine-tuning SMILES-based language models on standard chemical classification benchmarks. Probes the model's ability to learn structural chemistry from text representations and transfer that knowledge to downstream tasks. Use when the user wants to benchmark on MoleculeNet classification benchmarks, or asks about evaluating this task. Reports F1 score.

Evaluates the ability of multimodal molecular representation models to predict diverse physicochemical and biological properties from graph, text, and fingerprint inputs. It probes both classification (binary/multi-label activity prediction) and regression (continuous property estimation) capabilities across standardized chemical benchmarks. Use when the user wants to benchmark on MoleculeNet, or asks about evaluating this task. Reports ROC-AUC, RMSE.

Evaluates factual accuracy and reliability in molecular comprehension by testing whether models correctly describe molecular properties, structures, applications, and sources without hallucination or omission. It probes domain-specific knowledge retention and consistency against authoritative chemical corpora. Use when the user wants to benchmark on MoleculeQA, or asks about evaluating this task. Reports factual accuracy.

Evaluates the quality, validity, and chemical relevance of generated small drug-like molecules using standard molecular graph generative benchmarks. It probes a model's ability to produce chemically valid structures that match the distribution of real drug-like molecules while maintaining property fidelity and scaffold diversity. Use when the user wants to benchmark on MOSES, or asks about evaluating this task. Reports FCD.

Evaluates zero-shot generalization of vision-language-action and navigation policies across diverse indoor scenes. Probes robustness to environmental perturbations, language prompt variations, and sim-to-real transferability for long-horizon manipulation and semantic navigation tasks. Use when the user wants to benchmark on MolmoSpaces-Bench, or asks about evaluating this task. Reports success rate.

Evaluates the capability of vision-language web agents to navigate live websites and complete complex, multi-step tasks using only screenshot inputs. It probes GUI perception, action grounding, and long-horizon planning under real-world web constraints. Use when the user wants to benchmark on WebVoyager, Online-Mind2Web, DeepShop, WebTailBench, ScreenSpot, ScreenSpot v2, or asks about evaluating this task. Reports pass@k accuracy.

Evaluates large language models' ability to generate novel molecular structures (de novo generation) and predict molecular properties. It probes the models' capacity to optimize for chemical rewards while maintaining structural diversity and validity. Use when the user wants to benchmark on MolRGen, or asks about evaluating this task. Reports top-k score.

Evaluates vision-language models on molecular property prediction by combining skeletal structure images with textual prompts. It probes the model's ability to perform binary classification, numerical regression, and textual description generation across diverse chemical properties. Use when the user wants to benchmark on BACE-V, BBBP-V, HIV-V, ClinTox-V, Tox21-V, ESOL-V, LD50-V, QM9-V, PCQM4Mv2-V, ChEBI-V, or asks about evaluating this task. Reports True/False accuracy.

Evaluates embodied task planning and visual correspondence capabilities of vision-language models. It probes spatial-functional reasoning, multi-step action planning, and cross-view consistency in indoor scenes. Use when the user wants to benchmark on MomaGraph-Bench, BLINK, or asks about evaluating this task. Reports accuracy (%).

Evaluates a multimodal misinformation detection model's ability to classify fake vs. real news across heterogeneous datasets, measuring classification accuracy, ranking quality, and class-balanced performance under calibrated decision thresholds. Use when the user wants to benchmark on Fakeddit, MMCoVaR, Weibo, XFacta, or asks about evaluating this task. Reports F1.

Probes long-video moment retrieval (LVMR) capability by testing models' ability to localize specific temporal segments within long, diverse videos. It evaluates fine-grained temporal grounding and multi-modal reasoning across three semantic levels (global, event, object) using text, image, and video queries. Use when the user wants to benchmark on MomentSeeker, or asks about evaluating this task. Reports R@1.

Evaluates the adaptability, modularity, and downstream application capabilities of generative models (LDMs, VQ-VAE, ControlNets) across diverse 2D and 3D medical imaging modalities. It tests the framework's ability to generate high-fidelity synthetic data, perform conditional generation, detect out-of-distribution samples, and execute image translation and super-resolution tasks. Use when the user wants to benchmark on MIMIC-CXR, CSAW-M, UK Biobank, Retinal OCT, Medical Decathlon, or asks abo...

Evaluates the ability of a neural radiance field model to reconstruct and render novel views of dynamic, non-rigid scenes from monocular video input. It probes spatiotemporal deformation modeling, training efficiency, and perceptual image quality across synthetic and real-world sequences. Use when the user wants to benchmark on D-NeRF, MMVA, or asks about evaluating this task. Reports PSNR.

Evaluates the performance and parameter/memory/throughput efficiency of a gradient-free MoE-style PEFT routing mechanism across text, image, and video benchmarks compared to standard and MoE-PEFT baselines. Use when the user wants to benchmark on 47 Benchmarks (Text/Image/Video), or asks about evaluating this task. Reports accuracy.

Evaluates the accuracy and generalization of self-supervised monocular depth estimation models across image-based, pointcloud-based, and edge-based metrics on automotive and diverse natural scenes. Use when the user wants to benchmark on Kitti Eigen (KE split), Kitti Eigen-Benchmark (KEB split), SYNS-Patches, or asks about evaluating this task. Reports AbsRel, δ < 1.25^1, F-Score (pointcloud).

Evaluates the ability of AI and traditional NWP models to forecast the local monsoon onset date over India, specifically tailored for agricultural decision-making in the Central Maharashtra Zone. It tests long-range subseasonal precipitation forecasting and event detection under operationally realistic initialization constraints. Use when the user wants to benchmark on IMD Gridded Rainfall, or asks about evaluating this task. Reports onset_forecast.

Evaluates the performance of pruned large language models on a suite of commonsense reasoning and multimodal benchmarks to measure accuracy retention under varying compression ratios. Use when the user wants to benchmark on ARC-e, ARC-c, HellaSwag, PIQA, WinoGrande, ScienceQA, VizWiz, LLaVA-Bench, MM-Vet, or asks about evaluating this task. Reports accuracy.

Evaluates the convergence and stability of LLMs during iterative self-correction across six diverse tasks. It probes whether multi-round refinement reduces model uncertainty and yields consistent, aligned, or task-correct outputs without external supervision. Use when the user wants to benchmark on AdvBench, CommonGen-Hard, BBQ, MMVP, MS-COCO, Real Toxicity Prompts, or asks about evaluating this task. Reports semantic uncertainty.

Evaluates a model's ability to perform cross-modal relation extraction by predicting the semantic relationship between a textual entity in a sentence and a visual object in an image. It probes cross-modality alignment, visual-textual interaction, and handling of semantic ambiguity in multimodal fact extraction. Use when the user wants to benchmark on MORE, or asks about evaluating this task. Reports F1 score.

Evaluates multi-step reasoning capabilities beyond simple information extraction in question answering. It probes models' ability to perform arithmetic, commonsense, and symbolic reasoning by extending standard multi-hop questions with additional reasoning layers. Use when the user wants to benchmark on MoreHopQA, or asks about evaluating this task. Reports EM.

This benchmark evaluates a model's ability to perform gender-aware morphological generation by rewriting first-person sentences in French, Arabic, and Hindi to the opposite grammatical gender. It probes compositional morphosyntactic reasoning, testing whether models can correctly transform gendered terms while preserving semantic meaning and grammatical structure across bidirectional transformations. Use when the user wants to benchmark on MORPHOGEN, or asks about evaluating this task. Report...

Evaluates multimodal reasoning capabilities of vision-language models across six categories: mathematical, abstract, spatial, temporal, physical, and planning. It uses programmatically generated video clips to test dynamic visual narrative comprehension while eliminating prompt-based shortcuts. Use when the user wants to benchmark on MORSE-500, or asks about evaluating this task. Reports accuracy.

Evaluates zero-shot and fine-tuned time series foundation models against traditional statistical and machine learning baselines for predicting age- and country-specific mortality rates over 5, 10, and 20-year horizons. Use when the user wants to benchmark on Global Mortality Rates (50 countries, 111 age groups), or asks about evaluating this task. Reports SMAPE.

This benchmark evaluates the out-of-domain generalization and robustness of subjective speech quality assessment (SSQA) models. It probes whether models trained on single or multiple datasets can accurately predict human-perceived quality scores across diverse conditions, including different languages, speech types (TTS, voice conversion, enhancement, noisy), and sampling frequencies. Use when the user wants to benchmark on MOS-Bench, or asks about evaluating this task. Reports Best score dif...

Evaluates the perceptual audio quality of neural vocoder outputs by measuring how closely synthesized speech matches natural human speech. It probes the model's ability to generate high-fidelity waveforms from mel-spectrograms without audible artifacts like jitter or metallic sounds. Use when the user wants to benchmark on Data-Baker (Chinese female speaker), or asks about evaluating this task. Reports MOS.