practicalswan/agent-skills

1

using-git-worktrees Create isolated git worktrees with smart directory selection and safety verification

practicalswan/agent-skills

19

2

infostealer-malware-detector Detects and removes infostealer malware (credential stealers, data exfiltrators) via full-system file search, cryptog…

practicalswan/agent-skills

18

3

pdf Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual che…

practicalswan/agent-skills

18

4

nextjs-development Next.js 16.2.4 with TypeScript — App Router, Server Components, use cache directive, Turbopack dev, Server Actions, I…

practicalswan/agent-skills

17

5

xlsx Use this skill any time a spreadsheet file is the primary input or output. Covers reading, editing, cleaning, modelin…

practicalswan/agent-skills

15

6

agent-task-mapping Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to …

practicalswan/agent-skills

14

7

nemo-retriever NVIDIA NeMo Retriever deployment and usage guidance for local retrieval services, corpus ingestion, and grounded ques…

practicalswan/agent-skills

14

8

security-review AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, underst…

practicalswan/agent-skills

14

9

jupyter-notebook Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tu…

practicalswan/agent-skills

13

10

agentic-eval Evaluate and improve AI-generated output with explicit rubrics, reflection loops, and stop conditions. Use when build…

practicalswan/agent-skills

12

11

avoid-ai-writing Audit and rewrite content to remove AI writing patterns (\"AI-isms\"). Supports detect-only audits, edit-in-place fil…

practicalswan/agent-skills

12

12

cloud-design-patterns Choose and compare cloud design patterns for distributed systems. Use when reviewing architecture, selecting workload…

practicalswan/agent-skills

12

13

codebase-to-course Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-techni…

practicalswan/agent-skills

12

14

context-map Scope the real change surface before editing. Use when planning a feature, bugfix, refactor, or review and you need a…

practicalswan/agent-skills

12

15

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

practicalswan/agent-skills

12

16

defense-in-depth Validate at every layer data passes through to make bugs impossible

practicalswan/agent-skills

12

17

dotnet-best-practices Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution st…

practicalswan/agent-skills

12

18

imagegen Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, t…

practicalswan/agent-skills

12

19

java-docs Java Javadoc best practices. Use when adding or reviewing documentation for Java types, methods, packages, and public…

practicalswan/agent-skills

12

20

java-junit JUnit 5 testing patterns and parameterized-test guidance. Use when writing or reviewing Java unit tests.

practicalswan/agent-skills

12

21

mcp-builder Build high-quality MCP servers with strong tool design, structured outputs, clear error handling, and realistic evalu…

practicalswan/agent-skills

12

22

playwright Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screensh…

practicalswan/agent-skills

12

23

secret-scanning Configure GitHub secret scanning and push protection, triage secret alerts, and run local pre-commit secret audits. U…

practicalswan/agent-skills

12

24

spreadsheet-formula-helper Write and debug spreadsheet formulas (Excel/Google Sheets), pivot tables, and array formulas; translate between diale…

practicalswan/agent-skills

12

25

web-dev-explainer Trigger when the user asks for explanations of web development concepts, code breakdowns, or learning guidance.

practicalswan/agent-skills

12

26

accelerated-computing-cudf Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…

practicalswan/agent-skills

11

27

deepstream-dev NVIDIA DeepStream SDK development guidance for Python pyservicemaker pipelines, video analytics, TensorRT integration…

practicalswan/agent-skills

11

28

deepstream-import-vision-model NVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pi…

practicalswan/agent-skills

11

29

rag-blueprint NVIDIA RAG Blueprint deployment, configuration, troubleshooting, and shutdown guidance for Docker, Helm, and library-…

practicalswan/agent-skills

11

30

rag-eval NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, …

practicalswan/agent-skills

11

31

rag-perf NVIDIA RAG Blueprint performance-tuning guidance for profiling retrieval stacks, comparing bottlenecks, and validatin…

practicalswan/agent-skills

11

32

research Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Us…

practicalswan/agent-skills

11

33

security-best-practices Perform language and framework specific security best-practice reviews and suggest improvements.

practicalswan/agent-skills

11

34

stitch-react-components Convert Stitch HTML and screenshots into modular Vite/React/TypeScript components, or sync existing components to upd…

practicalswan/agent-skills

11

35

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

practicalswan/agent-skills

10

36

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

practicalswan/agent-skills

10

37

condition-based-waiting Replace arbitrary timeouts with condition polling for reliable async tests

practicalswan/agent-skills

10

38

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

practicalswan/agent-skills

10

39

doc Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fide…

practicalswan/agent-skills

10

40

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

practicalswan/agent-skills

10

41

ds-notebook-strict-code Use only when the user explicitly requests strict code-cell-only output for a Jupyter or undergraduate data-science t…

practicalswan/agent-skills

10

42

ds-teaching-assistant Use for explicit undergraduate data-science teaching, assignment guidance, concept clarification, method selection, o…

practicalswan/agent-skills

10

43

figma Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Fig…

practicalswan/agent-skills

10

44

figma-implement-design Translate Figma designs into production-ready application code with 1:1 visual fidelity. Use for Figma URLs, node IDs…

practicalswan/agent-skills

10

45

final-assignment-citation-review Review final-assignment materials for requirements, citations, AI-use disclosure, and data-analysis completeness.

practicalswan/agent-skills

10

46

gardening-skills-wiki Maintain skills wiki health - check links, naming, cross-references, and coverage

practicalswan/agent-skills

10

47

homework-notebook-review Review homework notebooks for completeness, reproducibility, safe execution, and academic-integrity boundaries.

practicalswan/agent-skills

10

48

inversion-exercise Flip core assumptions to reveal hidden constraints and alternative approaches - \"what if the opposite were true?

practicalswan/agent-skills

10

49

meta-pattern-recognition Spot patterns appearing in 3+ domains to find universal principles

practicalswan/agent-skills

10

50

notebook-execution-safety Review Jupyter notebooks for side effects, dependencies, and safe execution strategy before running or editing them.

practicalswan/agent-skills

10