Loading...
Loading...
Found 1,180 Skills
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
Build a premium, scroll-driven interactive landing page for any business: a service company, a physical product, a food brand, a drink brand. Scroll becomes the timeline. Video scrubs frame by frame under the wheel, sections pin and advance, rails pan sideways, headlines assemble line by line, the page ground shifts colour as you travel, and the pointer moves things that are not scrolling. Interviews the human first (their vibe, their journey, one unbroken world or distinct scenes, and what assets they already own), then picks a page grammar and a signature move so no two builds share a skeleton, generates photoreal assets through kie.ai or builds from the user's own footage and photos, writes real semantic HTML on a design-system floor, and verifies the result by screenshotting its own scroll. Use for "scrollytelling", "scroll animation site", "a site where scrolling plays a video", "Apple-style landing page", "3D scroll world", "interactive landing page", "make my brand a scroll experience", "make it feel different", "this looks like a template", "a unique scroll site", or any request for a site that should feel like an experience rather than a document.
v2.5.0 — Use when bootstrapping, completing, updating, or auditing project documentation, or documenting a feature/module/epic: AGENTS.md + docs/, ADRs, roadmap, docs/features/<slug>/, docs/plans/<slug>/. Triggers: "document this project", "bootstrap docs", "sync docs", "audit docs", "docs vs code", "from zero", "new feature", "nueva feature", "promové el plan", "after ark-check", "arkgate bridge", "knowledge dashboard", /documentation-manager. Intents: integrate, audit, from-zero. Feature autopilot v2; Implementation bridge opt-in; ArkGate post-gate sync; dashboard HTML; polyglot + monorepo hubs; team governance (docs/team); living claims v0 + local CI structural audit (Knowledge OS first increment toward 100×). On conflict code wins.
Use when building game UI (menus, HUD, dialogue box, settings/save screens) on top of Pixi'VN with an external JS framework (React, Vue) or with plain PixiJS components — mounting HTML or PixiJS UI layers over the canvas, navigating between UI screens/routes, theming a shadcn/ui-based template, and connecting UI components to game storage/settings. Covers `canvas.htmlLayers.add`/`get`/`remove` and the PixiJS-only layer helpers `canvas.layers.add`/`get`/`remove`.
Use when someone asks for a new Hairline figure, or runs /hairline-create with an idea. Draws one isometric line figure that answers the pointer, in the style and on the engine of @lucasmarkes/hairline, and hands it over as a single self-contained HTML file.
Turn complex topics, code, research, or model outputs into clear explanations, diagrams, interactive HTML, or polished narrated explainer videos. Use when the user asks to explain visually, animate a concept, build an explorable explanation, or make an explainer video.
Hub hiệu ứng cuộn trang — 64 bản GỐC nguyên văn (freefrontend/CodePen, MIT) ở repo Rheinmir/uiux-asset để copy nguyên file, kèm 7 hiệu ứng vanilla nhẹ: reveal-on-scroll, staggered text, scroll highlight, sticky shrink nav, scroll-to-top, scrollspy TOC, parallax nhẹ data-speed. Vanilla HTML/CSS/JS, tôn trọng prefers-reduced-motion. Gọi khi user nói "hiệu ứng scroll", "scroll reveal", "scroll to top", "scrollspy", "parallax nhẹ", "highlight khi cuộn", hoặc /scroll-effects. KHÁC `blur` (WebGL chuyển ảnh nặng GPU) và `timeline` (trục mốc thời gian) — đây là các hiệu ứng cuộn trang dùng hàng ngày, nhẹ, không dependency.
Audit and revamp existing web interfaces into polished, professional, product-specific experiences while preserving behavior and working within the current frontend stack. Use for requests to improve a vibe-coded, generic, template-like, inconsistent, dated, amateur, or visibly AI-generated UI; redesign an existing page, app, dashboard, landing page, or component; establish stronger art direction, hierarchy, typography, spacing, color, responsiveness, accessibility, interaction states, or visual coherence; or perform a premium UI polish pass on HTML, CSS, JavaScript, React, Vue, Svelte, Next.js, and similar frontend codebases.
Back up and reset Claude Desktop local state on macOS and Windows, inspect network egress, DNS/WebRTC, proxy, and relay configurations, and automatically deliver an HTML quality-check receipt plus a navigable Claude account-ban prevention guide. Before use, first pause to confirm the task scope: clear Claude’s local usage traces, or perform only a network check. The guide separately walks first-time users and users who have previously been restricted through manual preparation (time zone, egress, TUN, pre-login self-checks, account and payment, routine usage, and a pre-flight checklist), then invokes the skill for quality checks. The environment can be checked independently; this skill does not promise to sever server-side associations or prevent account bans. Do not apply it to Linux or unverified installation methods.
Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.
Universal document converter for transforming Markdown to PDF, DOCX, HTML, LaTeX, and 40+ other formats. Covers templates, filters, citations with BibTeX/CSL, and batch conversion automation scripts.
Read GitHub repos the RIGHT way - via gitmcp.io instead of raw scraping. Why this beats web search: (1) Semantic search across docs, not just keyword matching, (2) Smart code navigation with accurate file structure - zero hallucinations on repo layout, (3) Proper markdown output optimized for LLMs, not raw HTML/JSON garbage, (4) Aggregates README + /docs + code in one clean interface, (5) Respects rate limits and robots.txt. Stop pasting raw GitHub URLs - use this instead.