omerakben

Creates Next.js 16 API routes with auth, validation, and tenant scoping. Use when creating API endpoints.

Implements AI tools for Canvas generation and updates. Use when creating GenUI tools for code generation, document editing, or Canvas interactions.

Develops Canvas code execution features with Pyodide/iframe sandboxing. Use when working on Python/JS execution, package management, or sandbox security.

Creates and extends Canvas UI components with Monaco editor, split views, and educational context. Use when building Canvas panel, editor, or preview features.

Foundational Canvas type definitions and language support patterns. Use when working with Canvas types, schemas, or language configuration.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Creates educational UI components following learning science principles. Use for classroom, student, or teacher interfaces.

Use when creating or modifying email templates for Elon AI - welcome emails, role changes, notifications, teacher digests, or QR code invitations. This project uses HTML string templates, NOT React Email components.

AHA single door: full cycle + memory + resume/debrief/promote for fuzzy agentic asks.

Rewrites a loose prompt as a standalone prompt for a context-free agent with role, constraints, output schema, and worked example. Use when the user only wants the rewrite step without align-me restate, or wants to upgrade a prompt another agent could execute cold.

Restates a task in the agent's own words, surfaces implicit assumptions and open questions, reports confidence and execution status, and optionally rewrites the task as a standalone prompt. Use before any non-trivial task, when the user says "align me", wants to confirm shared understanding before acting, or wants to upgrade a fuzzy prompt for a context-free agent.

Generates 3-5 ranked clarifying questions where each answer changes the approach, before acting on a fuzzy task. Use when the user has a vague ask, says "ask me", wants clarifying questions instead of guessing, or needs leverage-ranked multiple-choice questions before planning or execution.

Steelmans then adversarially reviews a draft with 3 specific strengths, 3 failures with concrete fixes, and the single highest-leverage change. Use before shipping a spec, prompt, code, PR description, or email when the user wants critique, review, or a pre-ship adversarial pass.

Post-execution retrospective on an agent run. Compares what the handoff packet predicted against what actually happened — surfaces broken assumptions, unexpected failures, and one concrete change for the next run. Use after an agent completes a task, when the user says "debrief", "retro", "what went wrong", or wants to capture learnings before the next handoff.

Use to think through a feature's design, requirements, and trade-offs before building — advisory exploration, not an enforced gate.

Use to plan a RED-first TDD ordering for a behavior change — advisory test-ordering guidance, not an enforced gate.

Use to verify spec, reference code, and library docs before writing code — advisory guidance on the 3-source discipline, not an enforced gate.

Drive the code-oz agentic SDLC runtime to build or fix code with enforced gates and cross-family review. Use when the user asks to build, implement, or fix something in a code repository and wants gated, reviewed delivery rather than ad-hoc edits.

Generate, refresh, or open this repo's Agent Context Center dashboard — a single self-contained offline HTML file that inventories the repo's AI configuration (agents, skills, hooks, commands, MCP servers, rules, docs, open TODOs). Use when the user asks to build, refresh, regenerate, or view that dashboard, and to re-stamp it after editing the repo's AI markdown when a dashboard.html already exists under a provider folder.

Load the local Postgres database with a small set of sample rows for development.

Enforces fetching current library documentation before writing any code. Triggers at session start or before any implementation work. Prevents building on stale LLM knowledge by requiring verification against current docs via Context7, official sites, or web search.

Produce a single self-contained HTML file instead of a markdown document when the deliverable is spatial, comparative, interactive, or long-lived. Use this skill aggressively — agents undertrigger here. Trigger on requests for implementation plans, PR writeups, code reviews, module maps, architecture explanations, design systems, component sheets, prototypes (animations or click-throughs), SVG figures, flowcharts, slide decks, feature explainers, concept explainers, status reports, weekly updates, incident post-mortems, retrospectives, and throwaway editors (triage boards, flag toggles, prompt tuners, anything draggable). Trigger on phrasings like "write me a plan", "review this PR", "explain how X works in this repo", "compare these approaches", "show me design directions", "prototype this interaction", "give me a deck", "write a status update", "draft a post-mortem", "make me a triage board", "lay out the options". Trigger when the natural markdown output would exceed roughly 200 lines, or would contain thr