HKTITAN

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Load when the user is designing UX for Meta Ray-Ban Display — glanceable HUD patterns, micro-app archetypes (transit, cooking, lists), additive-display color rules, voice vs gesture choice, audio cues, motion safety. Don't load for technical Web App wiring — that's meta-display-webapps.

Load when the user is polishing a Snap Spectacles lens for shipping — FOV / safe zone, head vs body vs world lock, comfort and motion-sickness rules, performance and thermal budgets, lens publishing and review. Don't load for early build mechanics — use snap-spectacles-build.

Load when the user is bridging a phone or external BLE device to a Spectacles lens — sending phone sensor data into a lens, building a companion app, integrating Arduino / game controllers, or asks "how do I pair my own peripheral with Spectacles." Don't load for general Lens Studio basics — use snap-spectacles-build.

Load when the user is building location-aware AR on Snap Spectacles — Custom Locations for site-specific experiences, Places API for POI data, indoor / outdoor navigation, persistent spatial anchors, or asks "how do I make AR show up in this specific real place." Don't load for general lens basics — use snap-spectacles-build.

Load when the user is wiring pinch, poke, gaze, or two-handed manipulation on Snap Spectacles — building AR buttons, sliders, draggable objects, scrollable lists, custom interactors, or asks "why isn't my Interactable firing." Don't load for general Lens Studio scene setup — use snap-spectacles-build.

Load when the user is building an HTML/CSS/JS Web App for Meta Ray-Ban Display — choosing a viewport, wiring Neural Band and Cap Touch input, designing for the additive display, handling motion sensors or geolocation, or deploying over HTTPS so MRBD can load it. Don't load for non-MRBD Meta devices — those use the DAT path; route to meta-wearables-dat.

Load when the user is integrating Meta's Wearables Device Access Toolkit into an iOS or Android app to receive camera, microphone, or sensor streams from Ray-Ban Meta or Oakley glasses — wiring registration, permissions, streaming, the Mock Device Kit, or solving "the glasses don't appear in my device list." Don't load for MRBD Web Apps — that's meta-display-webapps.

Load when the user is choosing between Meta wearables (Ray-Ban Display vs Ray-Ban Meta vs Oakley HSTN/Vanguard), comparing build paths (Web Apps vs Device Access Toolkit), or asks "which Meta glasses can my app run on" or "what can I actually build on each Meta wearable." Don't load for already-decided builds — route to the specific path skill.

The `agent` CLI — install, interactive modes (Agent / Plan / Ask), headless `-p` mode for CI, GitHub Actions integration, and how it relates to the TypeScript SDK. Use when scripting Cursor in shell pipelines or workflows instead of (or alongside) the SDK.

Cloud runtime for Cursor SDK — dedicated VMs, repo-bound runs, auto-PR creation, artifacts, and reattachment. Use when running long, review-oriented, or repo-modifying agents off the local machine.

CursorAgentError class hierarchy, isRetryable, and recovery patterns. Use when classifying SDK failures, building retry logic, or surfacing actionable messages.

File-based agent loop hooks via `.cursor/hooks.json` — pre/post commands, governance gates. Use when enforcing policy without modifying agent prompts.

Configure MCP servers on Cursor SDK agents — stdio subprocess, HTTP, and SSE transports, inline vs file-based config, and per-run overrides. Use when extending an agent's tools beyond the built-ins.

Model discovery and selection on Cursor SDK — Cursor.models.list, ModelSelection, parameters (e.g. thinking levels), per-run sticky overrides.

Project, user, and team rules that the Cursor SDK and Agent load — `.cursor/rules/*.mdc`, `AGENTS.md`, and the legacy `.cursorrules`. Use when authoring rules that the SDK will pick up via `local.settingSources`, or when writing rule frontmatter with the right type (always / auto-attached / agent-requested / manual).

Run lifecycle, streaming, follow-ups, and conversation introspection in the Cursor SDK. Use when consuming agent output, handling progress events, or chaining turns.

Build the team the way Duolingo built theirs — the Green Machine operating model, talent density over headcount, candor protocol ("focus on what, not who"), hire-slow / fire-fast, and the "no process unless it makes decisions better" rule. Use when the user is hiring, defining team rituals, debating remote vs. office, choosing a feedback model, or installing an operating system in a team that has none. Source the Duolingo Handbook (Raise the Bar + Green Machine).

UI patterns from the Duolingo design system — juicy motion, the character system as the emotional channel, design tokens (color/type/spacing), sound as a UX surface, accessibility as a default not a checklist, and "error-as-delight" detailing. Use when the user is designing a screen for a gamified or learning product, reviewing a design for "why does this feel flat," picking a motion system, building a character mascot, or auditing for accessibility. Source the Duolingo design system at design.duolingo.com.

Duolingo-style experimentation as a decision protocol — hundreds of A/B tests a week, opinions resolved by data, ideas killed quickly. Covers hypothesis design, metric selection, guardrails, sample size, novelty effects, and explicit kill criteria. Use when the user wants to run an A/B test, decide between two designs without arguing, set up an experiment program, debug why a test isn't moving, or build a culture where "show don't tell" replaces seniority-based decisions. Source the Duolingo Handbook (Show Don't Tell) and engineering blog posts.

Add Duolingo-style play to any product — XP systems, juicy feedback, leagues, celebration moments, hearts/energy, and the anti-grind discipline that keeps gamification from turning toxic. Use when the user asks how to make a product fun, addictive, or "feel like a game," when designing rewards, levels, or progress, or when an existing system feels like a slot machine and they want it to feel like a craft. Source the Duolingo Handbook (Make It Fun) and the Duolingo design system.

Duolingo-style growth that doesn't break retention — viral loops, brand-as-acquisition (the TikTok playbook), referral mechanics, localization as a growth lever, and the founder-mode marketing that turned a mascot into a meme. Use when the user is planning acquisition, building a referral system, considering paid vs. organic, evaluating a marketing channel, or trying to turn an existing brand into a growth engine. Source the Duolingo Handbook (Make It Fun) and observed marketing patterns from 2022–2025.

Make product decisions the way Duolingo does — long-view over short-term, ruthless prioritization, ship-and-learn over plan-and-ship, dogfooding, and the "intuitive by default" quality bar. Use when the user is roadmapping, deciding what to cut, debating whether to ship, defining a quality bar for a feature, or trying to install a "product-led" culture in a team that defaults to feature factories. Source the Duolingo Handbook principles 1, 2, and 3 (Take the Long View, Raise the Bar, Ship It).

Duolingo-style retention engineering for any product — habit loops, streaks, leagues, churn diagnostics, day-N drop-off, and the discipline of building a "forever product." Use when the user asks how to keep users coming back, debug churn, design a streak system, time push notifications, run a leaderboard, or shift a product's metric from acquisition to retention. Source the Duolingo Handbook (Take the Long View) and blog data posts; translate every pattern to the user's actual product.

Write product copy in the Duolingo voice — "wholesome but unhinged," character-driven, screenshot-worthy. Covers push notifications, error states, onboarding, empty states, celebrations, and the now-famous threat-copy that turned a green owl into a meme. Use when the user is writing any user-facing string — notifications, microcopy, errors, marketing — and wants it to feel like a person, not a product. Source the Duolingo Handbook (Make It Fun) and observed blog/marketing patterns.

Use this skill whenever the user asks about microeconomics, macroeconomics, behavioral economics, game theory, incentives, market structure, competition, oligopoly, monopoly, pricing theory, elasticity, economic policy, fiscal policy, monetary policy, market design, nudge theory, information economics, market equilibrium, comparative advantage, trade policy, supply and demand.

Use this skill whenever the user asks about startups, entrepreneurship, venture capital, funding, seed funding, Series A, scaling, startup strategy, business models, market validation, product-market fit, fundraising, pitch decks, investor relations, growth strategy, early-stage companies, startup operations, exit strategy, lean startup, social entrepreneurship, or startup failure patterns.

Use this skill whenever the user asks about leadership, team management, organizational behavior, culture, change management, employee engagement, motivation, decision-making, influence, negotiation, conflict resolution, governance, board management, executive leadership, delegation, coaching, performance management, organizational design, team dynamics, cross-cultural management, emotional intelligence, cognitive biases, BATNA, ZOPA.

Use this skill whenever the user asks about marketing strategy, brand management, branding, digital marketing, customer acquisition, pricing strategy, market segmentation, customer insights, marketing analytics, marketing research, product positioning, go-to-market strategy, customer lifetime value, marketing ROI, content marketing, SEO, marketing channels, customer experience, brand loyalty, the 4Ps, STP framework, B2B marketing, services marketing, retail strategy.

Use this skill whenever the user asks about MBA concepts, business fundamentals, case studies, case analysis, business school topics, management education, cross-functional business problems, integrated business thinking, competitive analysis, industry analysis, company analysis, business frameworks, management principles, or learning business concepts.

Use this skill whenever the user asks about operations management, supply chain, logistics, inventory, procurement, manufacturing, lean, Six Sigma, process improvement, operations analytics, quality control, capacity planning, demand forecasting, distribution, vendor management, cost reduction, efficiency, project management, critical path, simulation, linear programming, EOQ, bullwhip effect.

Use this skill whenever the user asks about competitive strategy, positioning, business models, market entry, industry analysis, competitive advantage, SWOT, Porter's Five Forces, strategic planning, corporate strategy, diversification, acquisition strategy, strategic innovation, differentiation, cost leadership, blue ocean strategy, value chain analysis, scenario planning, platform business models, strategic alliances, growth strategies.

Use this skill whenever the user asks about digital transformation, technology strategy, AI, machine learning, data science, software product management, technology disruption, digital business models, cloud strategy, data infrastructure, analytics, big data, innovation, technology roadmaps, tech stack, automation, emerging technologies, generative AI, LLMs, blockchain, cybersecurity, agile development, disruptive innovation, technology adoption lifecycle.

Connect tools and services to a user's Poke — built-in integrations (Linear, Notion, GitHub, Sentry, Vercel, Gmail, Outlook, etc.) and custom MCP servers via poke.com/integrations/new. Use when the user asks to "connect X to Poke", "add a custom MCP integration", "list available Poke integrations", "disconnect a service", or builds a recipe that requires specific integrations.

Connect a local MCP server to a Poke agent using the `poke` CLI — `poke login`, `poke mcp add` for remote URLs, and `poke tunnel` to forward a local port to Poke for development. Use when the user wants to "expose my MCP server to Poke", "test my MCP locally with Poke", "connect Poke to my localhost", or registers a remote MCP URL.

Build with the Poke Python SDK — `pip install poke`. Mirrors the Node SDK with snake_case methods (`send_message`, `create_webhook`, `send_webhook`), richer exception types, and an MCP callbacks middleware for async tool progress updates. Use when the user is on Python (3.8+), writing a FastAPI/Flask/Django app, or building an MCP server in Python that needs Poke callbacks.

Build and publish Poke Recipes — shareable install bundles that combine onboarding context, a first message, required integrations, and a `poke.com/r/<code>` install link. Use when the user asks to "make a Poke recipe", "share my Poke setup", "create an install link", "publish to poke.com/recipes", or wants to monetize a Poke workflow via payouts.

Build with the Poke developer SDK and REST API — send messages to a user's Poke agent, create webhook triggers, authenticate with API keys, and understand the platform (channels, Kitchen, integrations, recipes). Use when the user asks to "send a message to Poke", "call the Poke API", "use the poke npm package", "integrate with poke.com", or builds anything against `poke.com/api/v1`.

Design and wire up Poke webhook triggers — translate an event source (deploy fail, new signup, alert) into a `createWebhook` + `sendWebhook` pair with a sensible condition/action and a safe payload shape. Use when the user asks to "trigger Poke when X happens", "notify Poke from my app", "build a Poke webhook", or wires Poke into CI/cron/serverless events.

Inspect or mutate the user's Swiggy food / Instamart cart through swiggy-cli. Use when the user says "add X to my cart", "what's in my cart", or "clear the cart".

Place a Swiggy food or Instamart order via swiggy-cli, with the right safety rails. Use only when the human has explicitly asked to checkout — not as a continuation of "add to cart".

How to drive the swiggy-cli (a wrapper over the official Swiggy MCP servers) from inside an agent. Always run in machine mode, branch on stable error codes, and prefer the generic Layer B commands.

Discover Swiggy Dineout restaurants, check available reservation slots, and book a table via swiggy-cli. Use when the user asks "book a table at X" or "is Y free at 8pm tomorrow".

Search restaurants, menu items, grocery products, or dineout venues on Swiggy via the swiggy-cli. Use when a user asks "find me X on Swiggy" or "what biryani places are open near me".

List, inspect, and live-track Swiggy food and Instamart orders via swiggy-cli. Use when the user asks "where's my order" or "what did I order yesterday".

Use when making architectural decisions, adding components, or understanding how PeaPod's pieces fit together. Provides context on the protocol design, component boundaries, and data flow to help agents make correct design choices.

Use when finishing a chunk of work or when the user asks to commit or to update Cursor context. Commit and push with a clear message; optionally add or update a rule, skill, or subagent in .cursor. Execute without prompting (autonomous mode).

Use when building, testing, or verifying pea-core or the workspace. Run cargo build and cargo test for pea-core from repo root; fix compilation or test failures. Execute without asking for confirmation (autonomous mode).

Use when implementing features or fixes that correspond to .tasks checklists. Open the relevant .tasks file (e.g. 01-pea-core, 02-windows), implement unchecked items, and mark completed items with [x]. Run fully autonomously: no confirmation for build, test, commit, or push.

Use when working on Windows, Android, Linux, iOS, or macOS protocol implementations (pea-windows, pea-android, etc.). Follow the corresponding .tasks file (02–06); ensure wire format and discovery match pea-core and .tasks/07.

Work with the URL compression system in kheMessage. Use when modifying how content is stored in URLs, debugging encoding issues, or optimizing compression.

Work with the contenteditable editor implementation. Use when modifying text input behavior, cursor handling, or undo/redo functionality.

Add or improve Markdown parsing and rendering in kheMessage. Use when adding new Markdown syntax support, fixing formatting issues, or enhancing the text editor.

Work with QR code generation and display. Use when modifying QR functionality, fixing QR rendering, or adding QR features.

Customize or extend the theming system in kheMessage. Use when adding new themes, modifying colors, or enhancing theme switching.

Best practices for using Cursor—rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources. Use when setting up Cursor, initializing or creating the .cursor folder, writing .cursor/rules or AGENTS.md, creating commands or skills, configuring .cursorignore, working with Agent, discovering rules or MCPs (e.g. cursor.directory), making codebases cursor-compatible, or asking about Cursor workflows, TDD, git commands, or large codebases.

Use the Notion CLI (`ntn`) to interact with the Notion API, manage workers, and upload files. Use when the user asks to "call the Notion API", "deploy a worker", "upload a file to Notion", "create a page", "query a database", or any task involving the `ntn` command.