Explore and implement app or site redesigns through free Mobbin reference research, four distinct ImageGen directions, user selection or delegated choice, and matched visual critique. Use for image-led design exploration, not routine UI fixes or implementation of an already selected design.
Build or audit an isolated Netlify/Vercel-style pull-request preview workflow using GitHub Actions and the project's existing hosting provider. Use when eligible PRs need separate live preview environments, stable and immutable URLs, GitHub reporting, affected-target builds, and safe fork handling. Do not use for…
Downloads embedded videos from web pages. Fetches the page, identifies the video hosting service (Vimeo, YouTube, etc.), resolves the correct embed/player URL, and downloads using yt-dlp. Handles private/unlisted videos that require referer headers or embed URLs. Use this skill when someone says "download this video"…
Download video from X/Twitter posts using yt-dlp. Use when the user wants to "download this X video", "save this tweet video", "grab video from Twitter", or provides an x.com/twitter.com status URL with a video. Handles HLS streams and uses --print aftermove:filepath for reliable path detection.
Design, implement, debug, or test Cloudflare Durable Objects when the task specifically involves per-key coordination, strongly consistent object-owned state, RPC or HTTP interfaces, alarms, WebSocket hibernation, bindings, or class lifecycle. Do not trigger for ordinary stateless Workers or Cloudflare Agents SDK work…
Use when working with AI Engineer Europe 2026 developer-facing endpoints, public schedule JSON, speakers JSON, llms.txt files, MCP access, and the local aieng CLI.
Diagnose, improve, or operate person-centered face matching across photo libraries, video, social profiles, directories, events, and other media when reference discovery, identity verification, detection failures, unknown people, or safe face-to-person assignment are involved. Use for face recognition and…
Operate or diagnose SmolForge repositories and Forge Deploy/Sites when the task requires Forge-specific CLI, authentication, manifest, or release behavior on forge.smol.ai or .sites.smol.ai. Do not use for generic Git or Cloudflare work, public-page review, product strategy or analytics, or ordinary code changes that…
Prefer the clean future product contract over legacy or backward compatibility. Use when the user invokes $future-only, says the product is preproduction or has no users, permits breaking changes, or explicitly says not to preserve legacy APIs, schemas, data, migrations, configuration, behavior, or tests.
Generalize a concrete fix, example, correction, or recurring failure into evidence-backed broader solutions and durable prevention. Use when explicitly asked to broaden, systematize, or extract transferable lessons.
Configure or audit Google Workspace (formerly G Suite) organization settings for open collaboration, user autonomy, external sharing, Groups privacy, Gmail delegation, Calendar, Meet, Chat, Drive, Directory, and profile editing. Use for new Workspace setup, restrictive-default cleanup, onboarding a small collaborative…
Create, revise, or review Latent Space and Forward Deployed Engineering YouTube thumbnails using saved brand resources, curiosity-led editorial preferences, cast and company coverage rules, timestamp-safe layout, and approved examples. Use for Latent Space or FDE episode thumbnails, not unrelated channels.
Build or refactor a long-running AI workflow that needs visible progress, durable partial results, resume after interruption, or atomic publication. Use for multi-stage extraction, indexing, batch analysis, evaluation, or report workflows. Do not use for a short synchronous model call or a UI-only streaming feature.
Build or improve progress, cancellation, result handoff, and reliability when creating or changing a user-facing slow asynchronous action, model call, media job, queue, or multi-step workflow. Applies to batch size, concurrency, and rerun changes affecting the visible wait; do not wait for a stuck-action complaint.…
Design or revise a multi-candidate AI media-generation workspace with reference attachment, model/provider capability routing, generation history, or explicit draft-to-publish flows. Use when those workflow concerns are central to the requested product. Do not use for individual canvas tools, ordinary image editing…
Generic media transformation orchestrator — download videos from any source (X/Twitter, Zoom, YouTube, web embeds), upload to YouTube, transcribe with timestamps, generate chapters, create thumbnails with GPT-Image-2, and A/B test titles. Use when the user wants to move a video from one platform to another, or asks to…
Design, build, or review responsive mobile web-app UX when a phone experience needs task-first layout, usable touch controls, compact media comparison, mobile navigation, overlays, forms, or responsive validation without degrading the desktop experience. Use for requests to make an existing web app work well on…
Given a local video or video URL, downloads the media if needed, extracts slide frames and key moments, transcribes the audio, and writes a Markdown timeline that interleaves screenshots with the transcript at the associated timestamps. Use when asked to turn a video into a multimodal notes file, slide-synced…
Fully automated new Mac setup for fullstack web developers and AI engineers. Generates and executes idempotent shell scripts to install dev tools, CLI utilities, GUI apps, AI/ML tooling, shell config, and macOS preferences — all via Homebrew, fnm, uv, and defaults commands. Use this skill whenever someone says "set up…
Turn an ongoing task or conversation into evidence-informed opportunities and an actionable decision workspace. Use when the user asks what next, invokes $next-steps, or wants to explore, compare, combine, and prioritize possible directions. Adapt from a short conversational recommendation to a richer interactive…
Audit or improve observability for named production questions, incidents, or opaque operations using privacy-safe telemetry. Use only when the user explicitly asks for an observability or instrumentation pass, telemetry design, dashboards or alerts, or when inability to explain production behavior is the primary…
Transcribe long-form audio, YouTube videos, podcasts, interviews, or panels; summarize them; extract chapter markers; and draft publishing assets like titles, YouTube descriptions, show notes, and tweet/X copy. Use when a user shares a YouTube link or audio/video file and asks for transcription, diarization, summaries…
Productize a working prototype by adding a bounded set of explicitly requested operational or product services. Use only when the user asks for a broad productization pass or names product-service gaps such as permissions, API access, audit history, admin operations, or production operability as the primary task. Do…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: