179 skills · sorted by relevance
Create charts and dashboards with a consistent approach to chart selection, color validation, labels, and interaction. Includes a palette checker and accessibility rules for readable visualizations in both light and dark modes.
Create a title animation where glass shards emerge through fog, assemble into a headline, and fly past the camera. Adjust the text, shard count, rotation, timing, and fog in a reusable HyperFrames video block.
Build and evaluate single-agent reinforcement learning experiments, where an agent learns actions from rewards. Use Stable Baselines3 to choose algorithms, create environments, monitor training, and save models with the normalization data needed for consistent evaluation.
Predict spatial gene expression from H&E-stained tissue images using DeepSpot-M. Query a released panel of about 19,000 genes and combine predictions from small image tiles into slide-wide maps for research analysis.
Deploy decoy credentials, documents, and URLs with Canarytokens to detect suspicious access. Guides token generation, placement, alert testing, and inventory tracking, with email or webhook notifications when someone interacts with a planted token.
Turn supplied data into a newspaper-style chart with a takeaway headline, annotations, and source notes. Create line, bar, or range-band charts, which show an interval around a central line, with staggered animation in a single HTML file.
Create developer tutorial slides with a GitHub-style dark background, purple and blue lighting effects, and three-color gradient headings. Coordinate code colors, centered layouts, and highlighted blocks within a 16:9 presentation.
Decide whether geographic data needs a map, then choose suitable background maps, visual forms, and implementation tools. Plan overlapping markers, zoom behavior, and mobile interactions so the map supports the intended analysis or product task.
Create clear, accurate charts for dashboards, data exploration, and reports. Choose chart types that fit the message, refine labels and scales, use accessible colors, and add context and annotations to help readers understand the findings.
Configure UnoCSS and style interfaces with utility classes, small reusable styling instructions. Use project settings to define custom rules, shortcuts, themes, and presets for features such as icons, typography, and attribute-based styling.
Use Boltz-2 to predict structures of complexes containing proteins, DNA, RNA, and small molecules. Obtain structure files and confidence scores to assess designed binders, with optional predictions of binding strength between a protein and a small molecule.
Plan interviews and focus groups for qualitative research, which explores people’s experiences and views. Develop question guides, follow-up prompts, discussion plans, transcription conventions, and participant review procedures suited to the study.
Build reinforcement learning experiments, where agents learn actions from rewards, using Stable Baselines3. Get guidance on choosing algorithms, creating Gymnasium environments, training and evaluating agents, monitoring progress, and saving models for later use.
数据可视化的判断层 SSOT——画任何图表、dashboard、看板之前先加载它，不是画完之后。管"该不该这么画"：这张图想让读者得出什么结论、用均值还是中位数、能不能聚合、堆叠还是折线、能不能上双轴、配色与颜色数量、同一实体跨图是否同色同位、表格该留几列。介质无关：HTML 报告页、React/Vue dashboard、PPT 原生图表、matplotlib/plotly/ECharts/D3、渲染成 PNG 的图，一律适用。Use when 动手画图之前，或评审既有图表（"这几张图有什么问题"、"图例为什么不一致"）。Not for 报告页的排版/组件/交互（用 report-with-html:report-with-html）或 PPT 原生图表的实现与渲染陷阱（用 deck-creator:deck-creator）。
The English summary is being prepared. Showing the original description.
Handles BED-format genomic intervals (BED3 through BED12, narrowPeak/broadPeak) and the coordinate-system substrate the whole interval category rests on, with bedtools (CLI) and pybedtools/pyranges/pandas (Python). Covers the 0-based half-open vs 1-based-closed convention boundary and the start-1/end-unchanged conversion, the silent failures (chrom-name mismatch, CRLF, lexicographic-vs-version sort under -sorted), genome/chrom.sizes generation, sorting contracts, BED12 block invariants, validation, makewindows, cross-assembly liftover (liftOver/CrossMap), and BED<->VCF/BAM/FASTA conversion. Use when reading, creating, validating, sorting, lifting between genome builds, or converting interval files, preparing inputs for bedtools/tabix/bigBed, or debugging an off-by-one or empty-overlap result.
The English summary is being prepared. Showing the original description.
Build Sankey, alluvial, river, and CONSORT-style flow diagrams to visualize cohort transitions, cell-state changes, or pipeline filtering using ggalluvial, networkD3, plotly, and consort. Use when showing how entities move between categories across timepoints (cell states, drug response classes, patient flow through a trial) or filtering pipelines (variants filtered through QC stages).
The English summary is being prepared. Showing the original description.
Designs PROTACs, molecular glues, and bivalent degraders with explicit handling of E3 ligase choice (VHL, CRBN, IAP, MDM2, KEAP1), linker design (length, composition, rigidity), ternary complex prediction (PRosettaC, DeepTernary, AlphaFold3), cooperativity (alpha), DC50 / Dmax characterization, hook effect, and prediction-experiment reconciliation. Use when designing targeted protein degraders, planning linker SAR, predicting ternary complex stability, or building generative degrader workflows.
The English summary is being prepared. Showing the original description.
Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.
The English summary is being prepared. Showing the original description.
Use when turning a dense sculpt, scan, ZBrush export or AI-generated mesh into animation-ready or game-ready topology in Maya without a mouse ("clean up this AI mesh", "retopo this character", Quad Draw, Retopologize), testing it deforms before rigging (bad elbow or wrist bend, lids popping through the eyes), or unwrapping UVs, cutting seams, setting texel density, mip-safe padding, UDIMs, lightmap UVs, stacking mirrored shells, or preparing a low poly and cage for baking. Keywords: edge flow, eye and mouth loops, Unfold3D, bake prep.
The English summary is being prepared. Showing the original description.
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host is bound to the source env, provisions a new **Platform Host** (recommended, idempotent) or a **Custom Host** via the BAP env-create API with the `D365_ProjectHost` template, or guides the user through PPAC install / `New custom host` (manual fallbacks). Polls lifecycle operations, verifies the host responds to Pipelines API calls, writes a host-check artifact other ALM skills consume. Use when asked to: "set up pipelines host", "ensure pipelines host", "no pipelines host", "install pipelines", "create pipelines host", "provision platform host", "provision custom host". Also invoked transparently by /power-pages:setup-pipeline when its host discovery step finds nothing.
The English summary is being prepared. Showing the original description.
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models
The English summary is being prepared. Showing the original description.
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline injection.
The English summary is being prepared. Showing the original description.
Route DRL-Pytorch reinforcement-learning workflows for standalone PyTorch Q-learning, DQN-family, PPO, DDPG, TD3, SAC, Atari DQN, and Actor-Sharer-Learner scripts.
The English summary is being prepared. Showing the original description.
Guide ROS/Gazebo Velodyne mobile-robot navigation with the DRL-robot-navigation TD3 implementation, including simulator setup, environment contracts, bounded training, checkpoints, and policy evaluation.
The English summary is being prepared. Showing the original description.