Add retries and timeouts to Python service calls, with increasing and randomized waits between attempts. Use examples to distinguish temporary failures from permanent errors, limit retry duration, and record retries in logs.
Evaluate whether a fine-tuned model is ready for release by checking training data, general capability loss, comparisons with the base model, and staged production rollout. Produces an evidence-based promotion or rejection report with one prioritized remedy when rejected.
Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.
Identify software protections that hinder inspection, such as debugger detection and obfuscation that makes code harder to understand. Support authorized binary analysis and CTF security challenges with protection findings, bypass strategies, reports, and analysis scripts.
Move Python application settings out of code and into environment variables. Use pydantic-settings to check value types and required fields at startup, organize development and production settings, and keep secrets out of version control.
Set up Python projects with uv, manage required packages, and create isolated environments for each project. Covers Python versions, dependency updates, migration from existing tools, and lockfiles that record package versions for repeatable installations.
Tune vector indexes, which organize data for similarity searches, to balance speed, memory use, and missed matches. Choose index types, adjust HNSW settings, and assess compression options using benchmarks with real queries.
Explains how PluginEval combines structural checks and experimental model assessments into quality scores. Helps interpret low scores, identify improvement areas, set marketplace thresholds, and explain what evaluation badges actually represent.
Create or repair a JSON specification for an editable PowerPoint deck. Define exact object positions, sizes, styles, and layering, alongside reading order and image descriptions, so the build process follows an explicitly authored layout.
Turn Python code into installable libraries or command-line tools. The skill guides project structure, package metadata, dependency settings, building wheel and source archives, and publishing releases to PyPI or private package repositories.
Choose a model training method and configuration from paired response preferences or individual positive and negative ratings. Covers DPO, ORPO, KTO, and SimPO, including pair construction, repeated training rounds, and troubleshooting learning settings.
Help secure payment systems using PCI DSS, the payment card data security standard. Covers encryption, log masking, access controls, and tokenization, which replaces card details with substitute values to reduce direct handling of sensitive data.
Export an approved fine-tuned model into a format suited to its hardware and runtime. Choose weight packaging and quantization, which reduces numerical precision, then compare outputs before and after export to check for regressions.
Build Helm charts, reusable packages for deploying Kubernetes applications. Organize templates, manage configuration values for different environments, document settings, and validate charts before packaging or installation, with guidance for troubleshooting deployment and dependency problems.
Draft employment contracts, job offer letters, employee handbooks, and HR policies. The skill helps organize consistent employment documents around worker classifications and local requirements, with templates intended for customization and review by qualified legal counsel.
Manage complex Git histories with guidance for reorganizing commits, copying selected changes between branches, and finding bug-introducing commits. It also covers working on multiple branches at once and recovering lost commits through Git's reference history.
Design and improve Unity games that process large numbers of entities. Learn ECS, an approach that separates data from behavior, and apply Jobs and Burst patterns to organize parallel processing and address CPU performance bottlenecks.
Guides Kubernetes security configuration with network restrictions, Pod execution rules, and role-based access control. Use its configuration examples to separate workloads, limit permissions, and enforce deployment requirements across a cluster.
Build a consistent interface foundation with Tailwind CSS v4 using shared design values and reusable components. Covers responsive layouts, dark mode, accessibility, and component variations to help standardize UI patterns across a codebase.
Set up and organize an Nx monorepo, a shared repository for multiple applications and libraries. Define dependency boundaries, configure build caching, and use affected commands to focus CI tasks on projects impacted by changes.
Set up machine learning training and inference on NVIDIA DGX Spark. Get guidance on choosing containers and packages, resolving CUDA compatibility errors, and checking that PyTorch can access the GPU before starting a workload.
Write and maintain Architecture Decision Records (ADRs), documents explaining important technical choices. Capture the context, options, decision, and consequences, then organize records and track their status so teams can revisit the reasoning.
Build and maintain a Markdown knowledge store with source links for individual claims. Use Git checks to detect changes in the code a page describes, and archive outdated pages while preserving their history.
Build Next.js applications with App Router patterns for page structure, data fetching, caching, and progressive page loading. Covers server and browser component responsibilities, route design, Server Actions, and migration from Pages Router.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)