Expert at building Odoo XML views: Form, List, Kanban, Search, Calendar, and Graph. Generates correct XML for Odoo 14-17 with proper visibility syntax.

Step-by-step Odoo version upgrade advisor: pre-upgrade checklist, community vs enterprise upgrade path, OCA module compatibility, and post-upgrade validation.

Expert guide for Odoo Purchase: RFQ → PO → Receipt → Vendor Bill workflow, purchase agreements, vendor price lists, and 3-way matching.

Expert guide for Odoo Project and Timesheets: task stages, billable time tracking, timesheet approval, budget alerts, and invoicing from timesheets.

Automate Monday.com work management including boards, items, columns, groups, subitems, and updates via Rube MCP (Composio). Always search tools first for current schemas.

Implement, refactor, review, or explain `@base-ui/react` in React applications. Use when working with Base UI components or utilities.

Generate high-fidelity, functional Next.js mockup screens for Oracle Forms modernization from one or more module evidence folders and linked screenshots. Use when asked to preserve legacy fields, tabs, grids, section organization, and business behavior while applying minimal web modernization; combine separate Maintain/Retrieve-style forms into a unified search, filter, add, edit, and delete experience; or extend a target Next.js application while matching its existing Reference / Products / Maintain Products visual and interaction conventions.

Curate an Oracle Forms modernization feature by reconciling extracted Oracle evidence, linked screenshots, a running target mockup, its Next.js implementation, existing canonical requirements, and accepted target architecture. Use when a target mockup must be converted or incrementally enriched into a review-ready feature requirement package plus an evidence-backed server-side implementation specification covering UI-to-data mappings, LOVs, validations, detailed decision rows for Delete, Add, Edit, and other operations, Oracle-constraint-to-application-message translations, transactions, tab dependencies, APIs, errors, security, and acceptance scenarios without inventing unsupported physical mappings.

Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.

Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific context to generate more accurate, contextually-aware prompts.

Render the authenticated user's billing history in Next.js — listing transactions via the Paddle Node SDK, the mandatory customer-id filter, pagination via `.next()`/`.hasMore`, status filtering, and formatting raw transaction totals (lowest-unit conversion + Intl.NumberFormat, with the zero-decimal currency special case for JPY/KRW/CLP).

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation. Use when repeated file processing is slow and results should be cached and invalidated by content rather than path.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.

Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff.

GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode

Use when a PR or feature needs both specification and code-quality review