Аналитик мобильных игр: анализ успешных игр (от $1M/месяц), выделение работающих механик, ревью решений гейм-дизайнеров, прогнозирование метрик.
Builds and ships a Swift/SwiftUI iOS app to the App Store from a natural language idea. Handles all phases autonomously: trend research (X + TikTok + App Store) → SDD spec → Xcode…
Use when designing or auditing the evaluation of a MobiSys submission — building real-device testbeds, instrumenting energy and thermal behavior, measuring latency and frame-rate…
Use when auditing a MobiSys submission for HotCRP readiness — the paper-registration prerequisite, the single December UTC deadline, the 12-page double-column body including…
Use when planning a MobiSys project timeline backward from the single early-December paper deadline through registration, two-round review with an early-reject cut, the rebuttal,…
Use when when you have a trained multitask model that accepts multiple input modalities (e.g., 1D NMR spectra in different nuclei or complementary analytical techniques) and you…
Use whenever the task involves auditing, validating, reviewing, stress-testing, challenging, or assessing the readiness of a model, notebook, backtest, experiment, scoring system,…
Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a winner, reasoning, and…
Validate, gap-fill, and curate genome-scale metabolic models using memote for quality scores and COBRApy for manual curation.
Standardize the reporting of model metrics to ensure statistical rigor and business relevance.
Managing ML experiments, metrics, parameters, and artifacts using MLflow, Weights & Biases, and best practices for reproducible ML experiments and model versioning.
Use when you have a pre-trained GNN model for CCS prediction and need to verify that it generalizes to test data that was held out during training.
Use when a deep learning model for molecular structure prediction (e.g., NMR2Struct) has been trained and evaluated on a limited molecular size range (e.
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (ma — from…
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (ma — from…
Implement automated machine learning model performance monitoring, statistical data drift (KS-test, PSI, Wasserstein distance), concept drift detection, and prediction quality…
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both…
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, inter — from…
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency — from majiayu000/claude-skill-registry
Validate neuronal dynamics implementations against analytic solutions, limiting cases, nullcline predictions, or known statistical identities, and add focused tests in the…
Geführte Prozedur für die Modell-Erstinbetriebnahme der KI-Wache — Silent Mode (Datensammlung) → CVAT-Labeling → Colab-Training → best.pt → Analyse-Modus → Fehlalarm-Nachtraining.
Use when you have a fitted linear model (lmFit object) from microarray, RNA-seq, qPCR, or proteomics data and need to test for differential expression across genes while…
Use when targeting 《现代经济探讨》(Modern Economic Research — 江苏省社会科学院主管主办的综合性经济理论月刊, 1982 年创刊, 匿名审稿、不收版面费) or deciding whether a Chinese econ/management manuscript fits this venue.
Use when targeting 《现代金融研究》(Modern Financial Research — 中国工商银行与中国现代金融学会主办、2024 年由《金融论坛》改为现名、不收任何费用、仅邮箱投稿) or deciding whether a Chinese finance manuscript fits this venue.
Curate, review, or repair ai-gene-review ModuleReview YAML documents under modules/, including pathway/module boundary setting, parts and variant modeling, annoton-level molecular…
Deterministic validity / synthesizability / drug-likeness gate over GENERATED molecules with karyon — reject invalid, unsynthesizable, or out-of-range candidates with named…
Use to convert references to the current Cell Press numbered style used by Molecular Cell — superscript numbers in order of first appearance, a reference list numbered in that…
Use to build Molecular Cell's data and code deposition plan and the Data and Code Availability statement inside STAR Methods Resource Availability — approved repositories (GEO,…
Use to finalize Molecular Cell display items — column-width sizing, minimum fonts, RGB, show-the-data with defined error bars/n/replicate type, gel/blot and structural-figure…
Use when triaging a study before any writing — stress-tests whether it clears Molecular Cell's bar (a deep molecular mechanism proven by orthogonal approaches with physiological…
Use to lock the single-mechanism arc before drafting — converts a set of correct experiments into one Molecular Cell story that runs molecular question → the mechanism →…
Use to produce the three signature Cell Press front-matter artifacts for Molecular Cell — Highlights (3–4 bullets, each ≤85 characters), the eTOC/In Brief blurb (~50 words,…
Use to build Molecular Cell's mandatory STAR Methods — the Key Resources Table, the Resource Availability subsections, Experimental Model and Subject Details, Method Details, and…
Use as the final preflight before submitting to Molecular Cell — a complete checklist across mechanism, single-mechanism arc, length budget, figures, STAR Methods, data…
Use to write Molecular Cell's Summary — a single unstructured paragraph (~150 words; re-check on the official site) that conveys the molecular question, the mechanism, and its…
Use when deciding which molcell-* sub-skill to invoke next, or when sequencing a manuscript from mechanism-fit test through reviewer rebuttal for Molecular Cell (Mol.
Use when targeting Molecular Biology and Evolution (MBE) or deciding whether a molecular evolution manuscript fits this venue.
分子生物学设计与验证范畴路由。用于 PCR/qPCR 引物探针、CRISPR sgRNA pegRNA donor、限制性酶切和克隆图谱、质粒注释、RNA 二级结构和结构探针等实验设计任务，选择具体 skill 并生成可执行交接物。
Use when after a trained CNN model has generated molecular embeddings for query spectra, and you need to retrieve the most likely candidate molecules from a reference database.
Use when you have a curated dataset of small molecules with SMILES, optional 3D coordinates, adduct information, and experimentally measured CCS values (in Ångströms or similar…
Use when targeting Molecular Cell (Mol Cell) or deciding whether a molecular-biology manuscript fits this Cell Press venue.
Use when a task needs the judgment of a Molecular and Cellular Biologist — quantifying gene expression change from qPCR (ΔΔCt/Pfaffl), validating a Western blot for quantitative…
Use when you have raw molecular structures in SMILES or SDF format and need to prepare molecular descriptors as input to a descriptor-based classifier (e.g., BitterPredic — from…
Use when you have SMILES strings or 2D molecular structures of N-Me derived unsaturated sterol lipids (or other C=C-containing molecules) and need to generate 3D conformational…
Use when you have 1D ¹H and/or ¹³C NMR spectra (as preprocessed numerical arrays or peak lists) from an unknown organic molecule with ≤19 heavy atoms, and you need to recover its…
Use when when setting up a ViMMS chemical sampling environment and you need to restrict the chemical search space to a specific m/z range (e.g., 100–1000) and MS level (e.g., MS1…
Use when you have raw molecular datasets (e.g., METLIN-CCS, CCSBase) with SMILES strings, 3D coordinates, adduct information, and ground-truth collision cross section labels, and…
Use when you have raw molecular structures in SMILES or SDF format and need to prepare them as input for BitterPredict.m or similar descriptor-based classifiers.
Use when when you have a query mass spectrum and a set of candidate molecular structures (as SMILES or 2D/3D coordinates), and you need to prepare them for cross-view similarity…
Use when when you have validated SMILES strings or canonical molecule objects from RDKit and need to convert them into the fixed-size numerical tensor format expected by a deep…
Use when you have a collection of chemical structures (SMILES, InChI, SDF, or mol formats) and need to train or apply a machine learning model for retention time prediction or…
OneScience 小分子生成与药物设计模型 skill。用于 MolSculptor 的 SMILES/分子图、autoencoder、latent diffusion、分子优化、reward、DSDP/docking 相关 case、训练和推理任务。
Use when after SMILES standardization when you have a table of translated SMILES strings (e.g., interim/tables/1_translated/structure/smiles.tsv.
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and product — from…
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and product — from…
Use when targeting Molecular Ecology (Mol Ecol) or deciding whether a manuscript applying molecular approaches to ecological, evolutionary, or conservation questions fits this…
Use when you have downloaded and extracted a GNPS archive (from METABOLOMICS-SNETS,
Use when you have untargeted metabolomics peak intensity data and spectral groupings (Molecular Families or Mass2Motifs) but lack confident chemical annotations or want to avoid…
Use when you have loaded a collection of molecular fingerprint vectors (e.g., from biosynfoni fingerprints deposited in Zenodo) and need to assess their statistical properties…
Use when you have natural product molecules (or compounds from natural product-like databases such as COCONUT or ZINC) in structural format (SMILES, InChI, or SDF file) and need a…