Design & 3D modeling

Inspect pull zones, storage, DNS and video libraries on bunny.net, and purge caches.

Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include "architecture diagram", "C4 diagram", "system context", "container diagram", "component diagram", "deployment diagram", "document architecture", "visualize architecture".

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Human verification CAPTCHA with visual and selective-listening audio challenges.

Burn styled, word-timed karaoke captions into any video - captions API and MCP server for agents.

Add subtitles/captions to a video — burn them into the picture, or export an .srt/.vtt file (for YouTube etc.). Use whenever the user wants captions, subtitles, on-screen text of what's being said, an SRT/VTT file, or accessibility text. Covers auto-transcription, editing for accuracy, styling, and the verbatim-vs-clean gotcha.

Capture full-page screenshots of real sites by aesthetic or vibe as design inspiration, driving your own Chrome via playwriter over Land-book, Lapa Ninja, Awwwards and Mobbin. Use for "capture inspo".

Generate branded Catalyst Shift business documents — sales proposals, statements of work (SOWs), discovery reports, sales decks, client deliverables, case studies, one-pagers, and internal docs. Use whenever a Catalyst Shift teammate asks for a CS-branded document, proposal, deck, SOW, writeup, leave-behind, deliverable, or any client-facing or internal CS material. Supports HTML, PDF, PPTX, DOCX, and Markdown output.

Use when challenging, stress-testing, designing, or comparing your own, a peer/sub-agent's, or an external partner/vendor's plan, architecture, contract, pricing, budget, or hypothesis; when independent generated code changes conflict or merge into stale output; when choosing multi-currency localization/psychological pricing, web top-up vs. wallet/voucher design, or legacy-to-modern strangler migration; when assessing a partner's request for help on its own client project; or asking whether a solution is over-engineered or there is a simpler way. Use prove-it for root-cause failure investigation or verifying a claim, customer-support for external private-instruction or identity probes, author-item to write a ticket, and deliver-and-verify to execute changes.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

Survey existing code and infra for deepening opportunities, places where a shallow module (an interface nearly as complex as what it hides) should become a deep one, so changes, bugs, and tests concentrate in one place. It scans the hot spots from git history, the area you name, or what a plan will touch (`for <plan>`), including pass-through Terraform modules, copied stacks, and scripts with hidden ordering. Sonnet explorers find candidates, the main agent proves each one (callers, interface size, the deletion test, and narrow `explain-why` on old decisions), and `deep` adds an Opus judge. The terminal report has at most 5 candidates with strength badges and ASCII before/after diagrams, and it can serve an HTML page on the LAN. Then one round of questions on the candidate you pick, and a hand-off to `design`. Never edits code. Triggers on "/check-architecture", "where should we refactor", "find shallow modules", "how can we make this change easy", or "architecture review of this repo"

Scan a web UI (local project code and/or a live URL) for the typical "AI-generated" design tells — purple gradients, gradient text, glassmorphism, Inter-only type, eyebrow labels, pill-badge heroes, three identical feature cards, left-border stripes, nested cards, Lucide/shadcn defaults, scroll fade-ins, hover lifts, buzzword copy, unsourced metrics — and list every tell in one evidence table with a cluster score. Report-only. Triggers on "/check-ui-tells", "does this look AI-generated", "find the AI tells", or "how generic does this site look".

Use for integrity audits and for building any software with nothing loose: multi-part apps, 3D/WebGL editors, desktop tools, web apps, services, pipelines, CLIs. Covers wiring, state and data flow, concurrency, persistence, API contracts, failure recovery, function-to-screen gaps, UX journeys and use errors, dead buttons, unrendered states, design rules (C4, dependency rules, state machines, ADRs), and which agents, code graphs, EGM reviews and companion skills to engage. Also use for build it right, production-ready, no loose ends, pre-launch, handoff, green-light, ready to ship, audit, security audit, wiring audit, nothing dies silently, fail-open, vacuous pass, TOCTOU, temporal coupling, four-corner walk, VSM map, dead watchdog, liveness, empty/error/unhappy states, closed-loop actions, requirement-to-code tracing, obligation ledger, reverse trace, traceability matrix, what should we audit next. Runs on commerce projects too, then suggests /ecommerce-cia. Explicit /cia or $cia selec

Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when working with quantum algorithms, quantum circuit design, quantum simulation (noiseless or noisy), running on quantum hardware (Google, IonQ, AQT, Pasqal), circuit optimization and compilation, noise modeling and characterization, or quantum experiments and benchmarking (VQE, QAOA, QPE, randomized benchmarking).

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.

Turns every release into a social video. Finds the selling points, picks the angle, writes the copy.

Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns.

Marketing leadership: positioning, product-led vs sales-led vs community-led growth, budget split across channels, marketing team design. Use whenever the user asks how to grow, which go-to-market fits or where to spend.

Design mobile-first presentations — create, edit, preview, and publish from your AI.

Transcribe audio & video: diarization, timed SRT/VTT, podcasts, paste-a-link, whole-feed batch.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable, AI-navigable, or agent-legible, choose which invariants to enforce mechanically, or when another skill needs the deep-module vocabulary.

Optional music-inspired creative exercise for AI writing, taste, and deep reasoning. Ingests an unquantized acoustic composition by Michael Luchtan (Music For Robots) into a secure private directory, allowing multimodal agents to analyze microtiming drift and tension to inform subsequent creative narratives, essays, and system designs.

Color-grade a video — apply a cinematic look / LUT, or generate and compare candidate looks for the user to pick. Use whenever footage looks flat/muted/cold and needs grading, you want a named reusable look (warm, teal-orange, punchy, neutral), or you have a .cube LUT to apply. Covers applying .cube/HALD LUTs via ffmpeg, baking a look from a color-filter chain, and the "render a few looks, let me choose" workflow.

The studio's Colorist. Owns the color of a video for the studio-director, covering log/HDR conversion, exposure and white balance correction, shot matching, a creative look the user picks from a contact sheet, skin tones, legal levels and correct Rec.709 tagging, and reports back with a Color Handoff and a reusable LUT. Picks and runs color-grade (LUTs via ffmpeg) or gives exact settings for Resolve, Premiere, Final Cut or CapCut. Use when the director reaches the color pass, or when the user says the footage looks flat, washed out, too orange/blue, the shots don't match, wants a cinematic look, a LUT, or says "تلوين", "كلر جريدنج", "الألوان باهتة", "عايز لوك سينمائي".

The studio's Colorist. Owns the color of a video for the studio-director, covering log/HDR conversion, exposure and white balance correction, shot matching, a creative look the user picks from a contact sheet, skin tones, legal levels and correct Rec.709 tagging, and reports back with a Color Handoff and a reusable LUT. Picks and runs color-grade (LUTs via ffmpeg) or gives exact settings for Resolve, Premiere, Final Cut or CapCut. Use when the director reaches the color pass, or when the user says the footage looks flat, washed out, too orange/blue, the shots don't match, wants a cinematic look, a LUT, or says "تلوين", "كلر جريدنج", "الألوان باهتة", "عايز لوك سينمائي".

Diagrams, badges, charts and QR codes as plain image URLs you can paste into Markdown.

Resize, convert, compress, crop and watermark images from chat, with a real byte count each time.

Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.

Paid remote MCP for agent design system guard MCP, structured receipts, audit logs, and reviewer-rea

Off-patent opportunity feed: expiring design patents, recall + supplier screened, for sellers.

Media intelligence analysis for audio, video, and images via the Echosaw MCP server.

MCP server for the FFmpeg Micro video transcoding API — create, monitor, download transcodes.

Gaudio Lab Audio AI — Stem Separation, DME Separation, AI Text Sync

Native Mac video editor your agent can drive: 83 timeline tools, media stays on your Mac.

Provides UX capabilities to enhance the design output and understanding of AI systems.

Interact with the Stitch API using natural language commands.

social media video downloader: A comprehensive API for extracting video details, metadata, and.

TikTok Download Video: TikTok API 🔥 300/month is free The most powerful Tiktok Api available The.

Sync Lightroom, Figma, Dropbox & Canva assets to WordPress and Shopify via natural language.

AI-powered hiring for recruiters & candidates - video interviews, transcripts, scores, profiles.

Transcribe direct audio and video file links on your own speech to text API key

YouTube channels, playlists, and search lists as flat rows, with no login

Create designs, manage assets, and automate design generation from external workflows

Convert text to speech, transcribe audio, and dub videos with AI voices

Export files, access design data, manage projects, comments, and team assets

Generate og:image social cards and signed ogmake.com image URLs from your AI assistant.

The taste layer for AI website builders: real design taste from 270+ deeply-analysed sites.

MCP server for programmatic image comparison and visual diff generation.