411 skills · sorted by relevance
Choose automatic layouts for diagrams made of connected nodes. Match algorithms and tools to the graph structure, then plan connector routes, overlap handling, and stable placement so readers can follow relationships and edits remain predictable.
Capture and analyze iOS memory snapshots to find objects that remain allocated unexpectedly. Trace the references keeping them alive, identify a targeted fix, and compare the same app flow before and after to document evidence.
Design image-led pages with large photographs, visible grid guides, and carefully positioned text and buttons. Coordinate typography, transparent cards, shading, and subtle motion so the image remains prominent while supporting information stays readable.
Build and tune enemy behavior for action games, including targeting, movement, attacks, retreats, and boss phases. Organize decisions into explicit states, make attacks readable to players, and check behavior with repeatable tests and browser encounters.
Create Three.js game effects that clearly communicate attacks, hits, damage, and status changes. Define each effect’s purpose and lifetime, limit resource use, and test overlapping effects, repeated triggers, low-quality settings, and reduced-motion alternatives.
Create SVG illustrations centered on one physical object, with white faces, teal sides, dark outlines, and hard shadows. Use this consistent, people-free style for onboarding steps, empty states, feature cards, and product imagery.
Turn reference images into prompts for AI image generation by describing composition, lighting, colors, and materials. Receive a main prompt and a negative prompt that specifies unwanted features, tailored to the image’s visual medium.
Analyze relationships between people, objects, or papers as networks in Python. Use NetworkX to find shortest paths, identify important nodes and communities, visualize connections, exchange graph data, and generate sample networks for testing.
Search ten academic databases for papers, preprints, author publications, and citation links. Look up specific papers by DOI, a paper identifier, and find abstracts, available full text, or openly accessible PDF links.
Draft or revise introductions for economics papers using a clear sequence: motivation, research question, empirical approach, findings, and contribution to existing literature. A checklist helps identify vague claims, missing results, misplaced literature discussion, and excessive length.
Estimate how an intervention affects outcomes using Bayesian causal analysis. The workflow confirms causal assumptions with the user, selects a suitable method, checks whether findings withstand challenges, and reports effects with uncertainty and limitations.
Assess how a pull request affects documentation, classify the required updates, and coordinate writing, technical verification, and editorial review. The result is an advisory comment with proposed changes for affected pages or document structure.
Find academic papers, citation links, and openly available full text using suitable sources among ten literature APIs. Results include search parameters, identifiers, and access dates so readers can repeat the lookup and understand gaps in coverage.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
Build PyTorch machine learning workflows for molecules, proteins, and biomedical relationships. Get guidance on datasets, model selection, training, and evaluation for property prediction, protein modeling, molecule generation, and planning synthesis routes from target molecules.
Draft and revise scientific manuscript prose from research notes and results. Organize sections, write abstracts and figure captions, integrate citations, and refine terminology and clarity while following study reporting guidelines and journal requirements.
Analyze relationships between people, objects, or places using Python networks. Build connection diagrams, find shortest paths, identify important nodes and closely connected groups, visualize network structure, and save the resulting data and measurements.
Process datasets that exceed available memory and run Python computations across multiple cores or machines. The skill guides large table and array operations, multi-file cleaning and aggregation, custom task dependencies, and execution settings for parallel workflows.
Tune Megatron Bridge training for MoE models, which route tokens to specialized experts, by overlapping expert communication with computation. Check dispatcher requirements, avoid conflicting settings, and compare steady training performance while changing one overlap setting at a time.
Configure and validate sequence packing, which combines training examples into token sequences, and long-context training in Megatron-Bridge. Compare offline, in-batch, and Energon online approaches while checking batch sizes, parallelism requirements, and model compatibility.
Diagnose GPU out-of-memory errors during Megatron Bridge training and choose memory reduction settings. Covers fragmentation, LoRA input storage, recomputation, parallelism changes, and CPU offloading, explaining compatibility limits and potential tradeoffs between memory use and training throughput.
Build, query, and inspect the project knowledge graph in .planning/graphs/
The English summary is being prepared. Showing the original description.
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are available. Activates when the user asks about code structure, wants to find where a feature lives, or needs to understand how code is organised.
The English summary is being prepared. Showing the original description.
Apply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates Lift_To_Graph mappings and composes Graph_Render_View, Graph_Fold_By_Property, Extract_Node_*, Enrich_Node_*, and Enrich_Graph_* calls. Accepts a supplied query or limited basic natural-language source request; it is not a general natural-language-to-KQL/IRQL skill. WHEN: Lift_To_Graph, Graph_Render_View, Graph_Fold_By_Property, IRQL graph enrichment, graph mapping for existing query results, icon-decorated graph, fold graph nodes. Use azure-kusto-graph for native make-graph analysis, graph-match, shortest paths, components, or persistent graphs.
The English summary is being prepared. Showing the original description.