nityeshaga

Process email inboxes, deliver formatted briefs, and manage action items for each team member. Use when any conversation touches briefs, email, action items, inboxes, or whats-happening questions — and ALWAYS when a user states or changes any preference about how they're briefed or how their email is handled (e.g. "stop briefing me about X", "put Y in my morning brief", a reply to a delivered brief). Load this skill BEFORE acting so the preference lands in the right file.

Create educational comic-book-style zines that explain any concept visually using AI image generation. Use this skill whenever someone wants to make a zine, comic, graphic explainer, visual guide, illustrated tutorial, or comic-book-style educational content. Triggers on requests like "make a zine about X", "create a comic explaining Y", "I want to make a visual explainer", "illustrated guide to Z", "graphic novel style walkthrough", or any request to turn a concept into a visual, panel-based, comic-book-style format. Also use when someone references "wizard zines", "Julia Evans style", or wants to create something that teaches through illustrated pages.

Pixel-perfect UI implementation from Figma designs with ruthless visual verification. Use this skill whenever the user wants to implement a UI from a Figma design, mockup, or spec and needs it to be exact — not approximate, not close enough, but pixel-perfect. Triggers include: 'implement this Figma', 'build this design', 'pixel-perfect', 'match the mockup exactly', 'implement this UI spec', 'code this design', 'convert Figma to code', or any request where the user has a visual design and wants it implemented with zero deviation. Also use when the user provides a Figma file, design screenshot, or UI specification and expects faithful reproduction in code.

Help the user write an article or post by interviewing them and polishing their draft. Use this skill when the user wants to write an article, blog post, or share insights about work they've done. They're excited and want to capture that excitement — not have it rewritten by AI. This is NOT ghostwriting. Use when the user says "help me write", "I want to write about", "I have a draft", "help me with my article", or shares a brain dump they want polished.

Start a timed discovery interview with the user. Use this skill when the user wants to be interviewed, wants you to ask them questions to learn about them or what they're working on, says "interview me", "ask me questions", "do a discovery call", or wants a structured Q&A session. Default duration is 5 minutes.

Run a timed brainstorming session with the user. Acts as a great coach — interviews the user to understand their idea, proposes cross-questions, expands on their thinking, and helps them arrive at clarity. Use this skill when the user wants to brainstorm, think through an idea, explore a problem space, or have a structured creative conversation. Default session length is 10 minutes.

Generate and edit images using OpenAI's gpt-image-2 model — the highest-quality image generation model available (Arena

Act as a creative lead — thinking through purpose, story, and feeling before any implementation. Use this skill whenever the user wants creative direction for any project — a website, landing page, product, app, brand, presentation, dashboard, tool, or any experience where design matters. Triggers include "creative direction for", "design a website for", "make this look amazing", "I want this to feel special", "brand direction", "redesign this", "creative vision for", or any request where the user wants to go beyond functional design into something truly distinctive and memorable. Also use when the user wants help thinking through visual identity, atmosphere, and the emotional experience of any product or project before building it.

Aggressively simplify any artifact — code, a prompt, a skill, a doc, or prose — by running Elon's algorithm (question every requirement → delete → simplify) on a clone of it via an agent swarm, then returning a reviewable cut-plan. Use whenever you want to cut AI slop, trim bloat, de-pad a file, make something leaner/denser, "delete what isn't load-bearing", or shrink an over-engineered artifact without losing what matters. Especially for AI-generated output, which is *additive* by nature (padded, over-explained, over-built) — this is the subtractive antidote. Triggers: "cut the slop", "make this leaner", "trim this skill/prompt", "this is over-engineered", "run the Elon algorithm on X".

Guide for designing effective tools for AI agents. Use when creating tools for custom agent systems or any AI tool interfaces. Provides principles for tool naming, input/output design, error handling, and evaluation methodologies that maximize agent effectiveness.

Write, review, and architect Ruby on Rails applications the 37signals way — the conventions DHH's team uses to ship products like Basecamp, HEY, Campfire, and Fizzy with tiny codebases, covering BOTH backend (models, controllers, jobs, caching, auth) and frontend (Hotwire: Turbo, Stimulus, morphing — rich interactive UIs with no React). Use this skill whenever the user asks to build a web app, add a feature to a Rails app, review Rails code, design models/controllers/views, build anything "real-time", "interactive", "live-updating", "multiplayer", or with drag-and-drop / keyboard shortcuts / rich form widgets — and ESPECIALLY when you are about to default to React, Next.js, Vue, or any SPA framework for a web frontend: read references/00-frontend-first-principles.md first, because the server-rendered Hotwire answer is usually better and this skill proves it. Also use it when choosing a stack for a new web product (even if the user didn't mention Rails), and when a web app needs iOS/Android apps — Hotwire Nati

Expert-level Kamal deployment guidance for deploying containerized applications to any server. Use this skill when users ask about Kamal, container deployment, zero-downtime deployments, deploying Rails/web apps to VPS/cloud servers, kamal setup, kamal deploy, Docker deployment without Kubernetes, or deploying to Hetzner/DigitalOcean/AWS with Kamal. Also use when users mention DHH's deployment tool, 37signals deployment, or want an alternative to Heroku/Render/Vercel with self-hosted infrastructure.

Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).