olivomarco

Generate a PowerPoint (.pptx) presentation using python-pptx and the shared pptx_utils.py module. Use this skill whenever the user asks to create a PowerPoint file, generate a .pptx, export slides to PPTX, or wants a downloadable presentation file. Also use when the user says "generate pptx", "make a PowerPoint", "export to pptx", or "I need a .pptx file".

Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.

Build demo guides with companion scripts for live technical demonstrations. Use this skill when the user asks to create demos, walkthroughs, hands-on labs, or demo packages for customer sessions. Also use when the user says "create a demo", "build a walkthrough", "demo guide", or "companion scripts".

Build What-The-Hack-style hackathon events with progressively harder challenges, coach materials, and dev containers. Use this skill when the user asks to create hackathons, challenge-based labs, or hands-on workshops for customers and partners.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.

Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication

Shared hard rules enforced across all squad agents

How to write comprehensive architectural proposals that drive alignment before code is written

Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22

Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces

Coordinating work across multiple Squad instances

How to coordinate with squads on different machines using git as transport

Microsoft Style Guide + Squad-specific documentation patterns

Capture the current session's state into a clean, copy-pasteable handoff block so work can continue in a fresh session. Use when the user wants to hand off, continue elsewhere, start a new session, or uses any 'handoff' / 'continue session' trigger phrases.

Ingest YouTube transcripts from a single video or an entire playlist and produce a detailed, structured summary of what was said. Use when the user shares a YouTube URL (video or playlist) and wants a transcript, notes, key takeaways, or a summary. Triggers include 'summarize this YouTube video', 'transcribe this playlist', 'what does this video say', or any youtube.com / youtu.be link.

Roast the user about their own repository — a witty, savage-but-affectionate code review of the codebase's questionable choices. ONLY highlight really questionable choices, do not roast just for the sake of roasting. ONLY run when the user explicitly asks to be roasted, e.g. "roast me", "roast this repo", "roast my code", "destroy me", "be brutally honest about my repo". Never trigger automatically or infer this from unrelated requests. Technology-agnostic.

Audit a codebase for duplication and inconsistency (DRY violations) and propose concrete consolidation into shared components, helpers, and utilities. Use when asked to "find duplication", "DRY this up", "check consistency", "deduplicate code", or "find repeated patterns". Technology-agnostic.

Review the existing functionality of an application for correctness, broken flows, missing states, and bugs. Use when asked to "do a functional review", "check the app works correctly", "find broken flows", "review functionality", or "audit user flows". Technology-agnostic.

Review an application as a product and recommend the most impactful next features and functional improvements to build. Use when asked "what should I build next", "suggest new features", "next feature opportunities", "product improvement ideas", or "what's missing". Technology-agnostic.

Analyze a codebase for refactoring opportunities that improve maintainability, readability, and reduce technical debt, then produce a prioritized plan. Use when asked to "find refactoring opportunities", "identify code smells", "reduce tech debt", or "suggest refactors". Technology-agnostic.

Audit a codebase for security vulnerabilities and produce a prioritized remediation plan. Use when asked to "run a security review", "audit for vulnerabilities", "check OWASP Top 10", "find security issues", or "do a security audit". Technology-agnostic.

Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, optimize prompt, improve prompt, optimize agent instructions, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, agent monitoring, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Write student and coach challenge content for What The Hack repositories in a beginner-friendly, coachable format.

Makes AI-generated content sound genuinely human — not just cleaned up, but alive. Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee. Triggers: 'this sounds like AI', 'make it more human', 'add personality', 'it feels generic', 'sounds robotic', 'fix AI writing', 'inject our voice'. NOT for initial content creation (use content-production). NOT for SEO optimization (use content-production Mode 3).