2.7K skills · sorted by relevance
Plan social selling on LinkedIn through profile improvements, relevant posts, personalized direct messages, and follow-ups. Build a clear path from audience engagement to sales conversations, with metrics to track which activities generate meetings.
Write, review, and refactor React and Next.js code using performance guidelines from Vercel Engineering. Prioritize improvements to data fetching, downloaded code size, server processing, and unnecessary rendering, with rule files providing explanations and code examples.
Write, review, test, and deploy Rust smart contracts on NEAR Protocol using near-sdk v5.x. Covers stored data, calls between contracts, security checks, upgrades, and gas optimization to reduce the computation costs of contract operations.
Guide a development task through requirements research, solution comparison, planning, implementation, optimization, and review. The workflow asks for approval at key stages and saves plans and completed task records in the project.
Write, review, and refactor React and Next.js code using Vercel's performance guidelines. Apply prioritized rules to reduce sequential data fetching, shrink downloaded code, improve server processing, and avoid unnecessary updates to the interface.
Provide other skills with tools for generating and editing images, analyzing image content, and improving text through external APIs. This foundation passes inputs to backend services without preprocessing and returns results as text or JSON.
Analyze token usage and AI costs in GitHub Agentic Workflows, identify expensive steps and budget or timeout failures, and develop prioritized improvements checked against the original workflow’s output quality.
Guides performance improvements when writing, reviewing, or refactoring React and Next.js applications. Prioritized rules cover data fetching, bundle size—the amount of code delivered to browsers—and rendering, with explanations and code examples.
Start the interactive Claude Octopus setup wizard to install and authenticate providers, configure RTK token optimization, choose a work mode, and complete onboarding. This skill directs configuration requests to the existing setup process.
Improve vllm-mlx performance through research, small experiments, and benchmarks on real models. The skill records results, keeps changes that improve measured performance, and carries successful work through implementation, testing, review, and pull request creation.
Audit the journey from a search result to a page’s intended action. Review titles, search intent, speed, readability, calls to action, and mobile usability to identify problems behind low click rates or weak conversions.
Choose a mathematical approach for a problem you do not yet know how to model. Guided questions clarify change, uncertainty, optimization goals, and required precision, leading to a recommended framework, starting equations, tools, and related skills.
Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.
Automates computational chemistry through Rowan's Python API, including molecular property prediction, structure optimization, and protein–ligand binding predictions. Submits cloud calculations, handles batches of molecules, tracks workflow status, and retrieves results without a local compute cluster.
Design and improve prompts and structured responses for AI applications. The skill also guides evaluation, retrieval augmented generation, which uses retrieved material to inform answers, and agent architecture, with references and scripts for production workflows.
Measure indicator calculation speed with BenchmarkDotNet, a benchmarking tool for .NET. Compare batch, incremental, and streaming implementations, detect slowdowns against saved results, and evaluate changes intended to reduce processing time and memory allocations.
Use pymoo in Python to optimize competing goals such as cost and performance under constraints. Find and visualize trade-off solutions, compare algorithms, and select candidates according to preferred priorities.
Choose a mathematical approach for a problem you do not yet know how to model. Guided questions clarify change, uncertainty, optimization goals, and required precision, leading to a recommended framework, starting equations, tools, and related skills.
Choose how to distribute tokens, the units a model processes, across MoE model experts during training. The guide compares alltoall, DeepEP, and HybridEP by GPU hardware, parallelism scale, memory needs, and optimization stage.
Improve MoE training throughput in Megatron Bridge. MoE models divide work among expert networks; this skill identifies memory, communication, and compute bottlenecks, guides controlled configuration comparisons, and validates speed alongside training health.
Generate small-molecule candidates from a starting structure, optimize supported molecular properties, and save results for validation. Local deployment also supports embeddings, numerical representations of molecules, and workflows that convert between molecular structures and learned internal representations.
Start a cuOpt REST server and build Python or curl clients to submit routing and optimization problems. Follow result polling, translate Python API field names into REST fields, and diagnose rejected requests.
Model and solve optimization problems with cuOpt through Python, C/C++, or the command line. Choose linear, mixed-integer, or quadratic methods based on the decisions involved, configure stopping limits, and investigate infeasible or unbounded results.
Turn written planning problems into mathematical optimization models. Separate fixed inputs, constraints, decisions, and objectives, then choose linear, mixed-integer, or quadratic formulations for tasks such as production planning, inventory management, and material allocation.