Menu
[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build PowerPoint (.pptx) slide decks in a Nord-themed house style — Nord palette with a dark theme (default) and a light theme, Consolas mono figures, kicker + title + standfirst anatomy, white-on-dark cards with coloured accent bars, green takeaway banners, facilitation-grade speaker notes. Use this skill whenever the user asks for a deck, slides, a presentation, an onboarding session, an inspiration session, a workshop deck, a kickoff deck, or any .pptx output.
Design and implement governance controls for tool-using and multi-agent AI systems, including policy enforcement, approval gates, audit trails, trust scoring, rate limits, and safe tool execution.
Assess tool-using and multi-agent AI systems against OWASP ASI-style controls, mapping evidence to prompt injection, tool governance, agency, escalation, trust boundaries, audit, identity, policy integrity, supply chain, and behavioural monitoring risks.
Guide users to review and install the external ai-ready skill from its upstream repository. Use when the user asks to install or try John Papa's ai-ready skill.
Beginner-friendly interactive tutorial for GitHub Copilot CLI concepts, slash commands, permissions, file context, planning, and custom instructions.
Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external data — and scores outputs with evaluators instead of assertions. Use when adding evals to a Python AI app.
| name | imbalanced-classification |
| description | [TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables. |
| version | 1.0.0 |
| tags | ["data-science",["TODO"]] |
| metadata | {"skill-author":"Marie-Lynne Block"} |
[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.
[TODO] List concrete user intents and trigger phrases that should activate this skill.
Input: User asks for help in imbalanced-classification. Expected output: A reproducible, validated workflow using the skill's core tools.
