CI/CD

Converts natural language compliance requirements into executable policies (OPA Rego, AWS Config Rules, Sentinel, Terraform). Standardizes governance by making it part of the build process.

Solidity smart contract development with Foundry. Covers writing, testing, security, deployment, and upgrades. Triggers on .sol files, contract, pragma solidity, forge.

Spot patterns appearing in 3+ domains to find universal principles. Use when noticing the same pattern across 3+ different domains or experiencing déjà vu in problem-solving.

Expert assistant for managing AI prompts, features, and configuration in the KR92 Bible Voice AI system. Use when creating AI prompts, configuring AI features, managing prompt versions, setting up AI bindings, or working with AI pricing and models.

Code review for Paweł Lipowczan portfolio project (React+Vite+Tailwind SPA). Use when user wants to review code changes, pull requests, commits, or modifications in portfolio project. Verifies architecture compliance, SEO standards, accessibility (WCAG 2.1 AA), performance (Core Web Vitals), blog system (markdown frontmatter, OG images), prerendering setup, and edge cases. References docs/{PRD.md,SRS.md,TODO.md,blog/BLOG_WORKFLOW.md}. Focuses on bugs, edge cases, and conditions causing errors after deployment.

Deep technical assistant for projects that combine Neural Quantum States (FFNN and Transformer-based) with Sample-based Quantum Diagonalization (SQD). Trigger this skill whenever the task involves: (1) designing or analyzing NQS architectures for quantum chemistry, (2) connecting classical samplers to qiskit-addon-sqd, (3) studying sample-efficiency, bias, and variance in few-sample regimes (e.g. 12–14-bit H2).

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Codex should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

This skill should be used when the user works with Jujutsu (jj) version control, asks to "commit with jj", "rebase in jj", "use revsets", "create bookmarks", "push to git with jj", "split commits", "squash changes", "edit history", or mentions jj-specific concepts like changes, revsets, bookmarks, operation log, or anonymous branches.

Ensure code follows DDD architecture and DAL separation principles.LOAD THIS SKILL WHEN: Creating new feature/module | User says "新功能", "新模組", "架構", "DDD", "scaffold" | checking architecture compliance | reviewing domain design.CAPABILITIES: Generate DDD folder structure, check dependency direction, validate DAL separation, scaffold Entities/ValueObjects/Repositories.

Create marketing content optimized for both human readers and LLM discovery (GEO/AEO). Use when the user needs to write or improve marketing materials including landing page copy, tweet threads, launch emails, blog posts, or feature announcements. Automatically analyzes the user's codebase to understand product features and value propositions. Applies casual, direct brand voice and Generative Engine Optimization principles to maximize visibility in AI search results.

Scaffold, structure, and deploy the Physical AI textbook in Docusaurus with book-aware content and RAG-ready exports. Use when creating or updating the Docusaurus site, adding chapters, configuring sidebar, or deploying to GitHub Pages/Vercel.

Deploys public-facing apps that handle their own authentication (like Jellyfin, game servers) without Authelia forward auth

Document user-facing features in a codebase. Use when asked to document features, explain what software does, or generate feature docs. Identifies features (not technical layers), then produces numbered markdown files per feature. Works with any language.

Generate executive-grade proposals for 360 Social Impact Studios' innovation transformation services. Creates customized proposals with proper GenIP attribution, cultural considerations, and strategic positioning across Innovation Assessment, Business Design, and Leadership & Culture tracks.

Run PHPUnit tests and fix failures using intelligent agent delegation. Use when user requests to:- Run tests (full suite, specific path, or single file)- Fix failing tests- Analyze test failures- Check test coverageDelegates to runner agent (haiku) for execution and fixer agent (sonnet) for fixes.Automatically cycles between run and fix until tests pass or human intervention needed.

Autonomously explore unfamiliar codebases using Miller's code intelligence. Use semantic search, symbol navigation, and call path tracing to understand architecture without reading entire files. Activates when user asks to understand, explore, or learn about a codebase.

Analyze production incidents and generate prioritized triage checklists

Multi-agent and MCP pipeline security with 5-layer defense architecture. Use when building MCP servers, multi-agent systems, or any pipeline that handles user input to prevent prompt injection and ensure proper authorization.

Enterprise CLI tool architecture with multi-language patterns, UX/DX optimization, and production deployment strategies

Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating real-time voice agents that need to transfer control between specialized agents, implement supervisor escalation, or build complex conversational systems.