agent-skills

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts. Keywords: which agent, best agent for this, delegate to expert, agent capability mapping.

Evaluate and improve AI-generated output with explicit rubrics, reflection loops, and stop conditions. Use when building self-critique workflows, evaluator-optimizer pipelines, or acceptance gates for code, docs, analysis, or plans.

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Supports detect-only audits, edit-in-place file cleanup, voice and context profiles, and an iterate-to-convergence pass.

Azure deployment for web apps — Static Web Apps, App Service, Blob Storage, Bicep/ARM, GitHub Actions CI/CD. Use when deploying Next.js/Vite to Azure or configuring Azure resources for full-stack apps.

Interactive idea refinement using Socratic method to develop fully-formed designs

Manage breaking API changes, migration guides, deprecation notices, and semver versioning. Use when introducing breaking changes, writing migration paths, updating changelogs, or releasing major versions.

Design philosophy docs and canvas-based visual creation. Use when articulating design principles, crafting multi-page design documents, or exploring aesthetic philosophy with intentional design thinking.

Choose and compare cloud design patterns for distributed systems. Use when reviewing architecture, selecting workload patterns, or mapping reliability, performance, messaging, security, and migration concerns to concrete design options.

Synchronize and verify code examples in documentation. Use when function signatures change, API interfaces update, imports shift, or documentation snippets become outdated and need correction.

two-stage review (spec compliance first, then code quality), refactoring, and quality improvement. Use when reviewing code, eliminating code smells, reducing technical debt, refactoring methods, running self-critique loops, or improving maintainability and readability.

Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a course,' 'explain this codebase interactively,' 'teach this code,' 'interactive tutorial from code,' 'codebase walkthrough,' 'learn from this codebase,' or 'make a course from this project.' This skill produces a stunning, self-contained HTML file with scroll-based navigation, animated visualizations, embedded quizzes, and code-with-plain-English side-by-side translations.

Python research assistant with Context7 MCP. Use for Python library research, evaluating packages, enforcing strict Python coding standards, or fetching up-to-date library docs via Context7.

Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?

Validate GCI competition predictions and notebook outputs against expected schema, metric, and submission constraints.

Replace arbitrary timeouts with condition polling for reliable async tests

Scope the real change surface before editing. Use when planning a feature, bugfix, refactor, or review and you need a concrete map of likely touch points, dependencies, tests, and nearby risks.

Refresh a safe, concise map of this GCI World 2026 workspace before deeper course, assignment, or dataset work.

xUnit testing patterns and data-driven test guidance. Use when writing or reviewing .NET unit tests.

Discover, validate, and invoke .agent.md custom agents. Use when finding agent files in the local Claude or VS Code Insiders directories, checking frontmatter, verifying disable-model-invocation, or determining agentName for runSubagent calls.

NVIDIA DeepStream SDK development guidance for Python pyservicemaker pipelines, video analytics, TensorRT integration, and streaming inference workflows.

NVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pipelines with export, TensorRT build, and benchmark steps.

Validate at every layer data passes through to make bugs impossible

Spec-driven development lifecycle — EARS requirements, technical design docs, implementation tracking, and contribution guidelines. Use when planning features, defining requirements, or managing project lifecycle.

Git operations, shell scripting, CI/CD pipelines, and terminal automation. Use for conventional commits, PowerShell/Bash scripting, configuring GitHub Actions, or automating development tooling workflows.

Use multiple Claude agents to investigate and fix independent problems concurrently

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Inspect PDFs, DOCX, PPTX, and XLSX files for share-readiness, metadata, links, comments, and hidden content.

Create structured docs from scratch — PRDs, technical specs, design docs, decision records, knowledge bases. Use when drafting documentation, writing proposals, defining requirements, or planning features.

Automate doc generation with JSDoc/TSDoc, linters, and pre-commit hooks. Use when setting up markdownlint, configuring doc linting pipelines, integrating JSDoc/TSDoc, or building automated documentation workflows.

Templates and structural patterns for API docs, feature docs, config guides, and REST endpoint documentation. Use when structuring docs, applying Markdown templates, or standardizing doc formats.

Documentation quality standards and writing principles. Use when establishing formatting rules, reviewing doc quality metrics, creating writing guidelines, or enforcing consistent documentation style across a project.

Validate documentation before merging - check completeness, broken links, code example accuracy, and factual correctness. Use when reviewing docs for quality gates or running pre-merge doc validation.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Covers polished document output, tracked changes, comments, image updates, XML-level repairs, and safe conversion workflows.

Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution structure, async patterns, dependency injection, or testability.

Use only when the user explicitly requests strict code-cell-only output for a Jupyter or undergraduate data-science task, or when an ITX2007 assignment requires that format. Do not activate for ordinary data analysis or explanation requests.

Use for explicit undergraduate data-science teaching, assignment guidance, concept clarification, method selection, or output interpretation. Do not activate merely because a task contains data or Python code.

Generate .excalidraw diagrams from natural language. Use when creating flowcharts, mind maps, system architecture diagrams, sequence diagrams, ER diagrams, network diagrams, or any visual process visualization.

Excel (.xlsx) manipulation via MCP server. Use for creating workbooks, formatting cells, writing formulas, building charts, pivot tables, data analysis, or any task involving Excel spreadsheets.

Execute detailed plans in batches with review checkpoints