scottink-writer
Write in Scott's authentic voice - British, conversational, self-deprecating, code-first. Use when writing blog posts, technical content, or documentation.
CMS, document processing, and media generation.
Write in Scott's authentic voice - British, conversational, self-deprecating, code-first. Use when writing blog posts, technical content, or documentation.
Use to craft channel-specific outreach sequences that tie directly to detected intent signals.
Use when crafting compelling webinar narratives, engagement tactics, and attendee experiences.
Tone, diction, and phrasebook system for consistent writing + localization.
Use this skill any time the user wants to generate, create, or design images, illustrations, or visual assets. This includes: posters, banners, social media graphics, product mockups, logo concepts, thumbnails, marketing creatives, profile pictures, book covers, album art, icon designs, and any request for AI-generated imagery. Also trigger when: user says 生成图片, 做个海报, 画个插图, 设计个banner, 做个封面, 社交媒体配图, 产品效果图. If an image or visual asset needs to be created, use this skill.
Create presentation slides as standalone HTML files with automated PNG export. Use when users ask to: create slides, build a deck, make a presentation, design slides, export slides to images, or work with HTML-based presentations. Triggers: "create slides", "make a presentation", "build a deck", "slide deck", "export slides", "slides as code".
Expands and recomposes images into an IMAX 70mm portrait style (1.43:1 aspect ratio) with high-fidelity Christopher Nolan-esque aesthetics.
Transforms anime, art, or 3D rendering images into photorealistic cosplay-style photographs.
Restores vintage and blurry photos to high-definition 8k images while preserving identity.
Process videos with FFmpeg — improve quality, auto-contrast, downsample, denoise, or crop using the video_ffmpeg_process tool.
프레젠테이션 슬라이드를 미려한 HTML로 디자인. 슬라이드 HTML 생성, 시각적 디자인, 레이아웃 구성이 필요할 때 사용.
Generates Obsidian .canvas files from intent. Takes a description of what you want to visualise and produces valid JSON Canvas — mind maps, flowcharts, kanban boards, research canvases, project overviews. Activates on "create canvas", "make a board", "visualise", "map out", "mind map", or when spatial organisation of ideas is needed.
Create fixed-canvas HTML mockups for websites, mobile apps, and desktop apps so an AI agent can verify UI direction before implementation. Use when a user asks for layout ideas, wireframes, visual comparison, HTML previews, mockups, or wants to see what a sidebar, navbar, modal, dashboard section, mobile screen, or desktop panel could look like. This skill always proposes Option A, Option B, and Option C with one recommended option, mirrors the user's language in the review, uses Svelte CDN plus TailwindCSS CDN templates, starts a local preview server, captures screenshot checkpoints of the mockup region only, and turns an approved option into an implementation-ready plan.
Create YouTube thumbnails with AI image generation and face compositing. Triggers on 'create thumbnail', 'make thumbnail', 'thumbnail for', 'generate thumbnail', 'youtube thumbnail'.
Create visual overlays for video compositions — illustrations, logo displays, platform grids, motion graphics, and new component types. Use when user says: create overlay, new visual, build illustration, create illustration, design visual, new component, new motion graphic.
Extracts transcripts from video files using local WhisperX (preferred) or faster-whisper with GPU acceleration. Use when the user needs to transcribe a video, get captions, extract audio text, or convert video/audio to text. Triggers on "transcript", "transcribe", "speech to text", "video to text", "extract captions".
Extract and intelligently reframe clips from long-form 16:9 videos into 9:16 portrait or 1:1 square formats with face-tracking crop. Use for 'extract clips', 'reframe video', 'clip extractor', 'portrait crop', 'face tracking', '16:9 to 9:16', 'smart crop', 'make shorts from video', 'auto reframe'.
Local visual regression check for layout or rendering changes. Renders all gallery examples, pixel-diffs against main, and opens changed renders as BEFORE/AFTER pairs. In most cases the CI render preview on a PR is sufficient - use this skill only for pre-push confidence on risky changes or when the user explicitly asks for a local diff.
Video editing orchestrator and router. Detects video format (long-form vs short-form) and routes to the correct editing skill. Also provides shared component library, brand assets, and rules used by all editing processes. Use when user wants to edit video, create composition, add effects, make it polished, or finish the video.
Edit short-form videos (under 90 seconds) using Remotion compositions. Handles pipeline clips, standalone demos, and announcements with pop-outs, captions, SFX, and CTAs. Use for "short-form editing", "edit clip", "edit short", "pipeline clip editing", "edit demo", "short video editing", "edit announcement", "reels editing", "shorts editing", "tiktok editing".