ツール
掲載中のすべての Skill、MCP サーバー、CLI、プラグインです。種類・職業・タグで絞り込むか、キーワードで検索できます。
職業:Full-stack / Indie +3
複数選択できます。いずれかの職業に合うリソースが表示されます。
- Full-stack / Indie524
- DevOps / SRE209
- Data analysis152
- Design239
- Frontend447
- Backend408
- Mobile & desktop96
- Game development29
- QA101
- ML / AI162
- Data engineering81
- GIS / Surveying12
- Security71
- Product / Projects246
- Architecture / Civil19
- Hardware engineering17
- Operations233
- Marketing & sales306
- Admin / Office240
- Writing / Content229
- Video / Media187
- Customer support66
- HR88
- Legal94
- Finance / Accounting142
- Investing / Analysis104
- Teachers / Students212
- Research / Academia255
- Healthcare19
- Translation / L10n84
- Founders282
タグ
複数選択できます。選んだタグをすべて持つリソースだけが表示されます。
- web-development128
- ui-design99
- data-analysis81
- python81
- cloud80
- terminal68
- code-review67
- dev-workflow65
- anthropic59
- deployment58
- subagents57
- claude-code55
- ui-components53
- database47
- backend45
- codex44
- graphic-design44
- design-files43
- code-quality42
- skill-management41
ほかにもあります。入力して探してください。
972 件

Three.js
SkillBuilds or debugs interactive 3D web scenes with Three.js: scene, camera, renderer, lights, materials, GLTF loading and controls, plus performance basics like capping pixel ratio, handling resize, disposing WebGL resources and reduced motion.
MengTo/Skills7.7k
Pricing Page
SkillDesigns or rewrites a high-converting SaaS pricing page: gathers plans, limits, upgrade triggers and objections, then structures a value headline, monthly/annual toggle, tiered plans, comparison, FAQ and trust sections with copy templates.
MengTo/Skills7.7k
Progressive Blur
SkillCreates a layered progressive blur at the top or bottom edge of the viewport by stacking backdrop-filter layers with gradient masks, with ready-to-paste HTML and CSS and knobs for height, blur steps, direction and z-index.
MengTo/Skills7.7k
Matter.js
SkillImplements 2D physics interactions with Matter.js: a minimal Engine, Render and Runner setup with bodies, optional mouse drag constraints and SPA cleanup steps, asking about canvas size and renderer when specs are missing.
MengTo/Skills7.7k
Landing Page
SkillDesigns or rewrites a single-offer, high-converting landing page for SaaS, apps or services: gathers the primary action, audience, objections and proof, then lays out hero, argument and objection-handling sections with copy templates and SEO/AEO notes.
MengTo/Skills7.7k
Cobe.js
SkillAdds a lightweight interactive WebGL globe with the cobe library: canvas sizing for device pixel ratio, location markers, rotation in onRender, resize handling and teardown, for plain pages or React/Next.js hero sections.
MengTo/Skills7.7k
Design-First UI Prompting
SkillTurns a fuzzy UI idea into a design-first prompt spec for UI generation: goal, format, layout, type system, color, imagery, exact copy, constraints and negative prompt, then iterates by changing one variable at a time.
MengTo/Skills7.7k
GSAP
SkillHelps the agent add or debug web animations with GSAP: tweens, timelines and position parameters, easing, stagger and ScrollTrigger pin and scrub, plus fixes for jank, cleanup with gsap.context() in React and refreshing after images load.
MengTo/Skills7.7k
GSAP ScrollTrigger Storytelling
SkillBuilds cinematic, scroll-driven product storytelling with GSAP ScrollTrigger: pinned scenes, scrubbed timelines, progressive UI reveals and section handoffs, with cleanup in React, simpler choreography on small screens and readable copy and CTAs.
MengTo/Skills7.7k
Marquee Loop
SkillBuilds seamless infinite marquees for logos, testimonials, screenshots or tags by duplicating the item sequence and translating the track from 0 to -50%, with stable widths, faded edges, optional hover pause and reduced-motion handling.
MengTo/Skills7.7k
WebGL Landing Steering
SkillSteers WebGL-heavy landing pages toward a chosen look by picking one of four visual lanes per page type, passing message, performance, accessibility and reliability gates, and outputting a lane, visual spec, stack, fallback and build order.
MengTo/Skills7.7k
Animation Systems
SkillGuides the agent to build a coherent, product-grade web motion system in the style of Stripe, Linear, Apple and Vercel: reusable primitives, duration and easing defaults, stagger choreography, scroll and hover patterns, performance rules and reduced-motion support.
MengTo/Skills7.7k
kubectl-ai
CLIManage Kubernetes clusters in natural language: translates intent into kubectl operations and runs them, and can serve as an MCP server for other agents. Uses Gemini by default (API key required) and also supports OpenAI and local models. Maintained by Google Cloud.
GoogleCloudPlatform/kubectl-ai7.6k
Waza
PluginTw93's lean pack of engineering-habit skills: /think to pressure-test plans, /hunt for root causes, /check to review diffs, /ui for frontend interfaces, /write to polish Chinese and English prose, and more (8 skills). Works with both Claude Code and Codex.
tw93/Waza7.6k
VTracer
CLIConverts raster images like JPG and PNG to SVG, handling color tracing, black-and-white line art and unevenly lit scans, for vectorizing logos, illustrations and old drawings. The CLI is a 1.0 preview installed with cargo (needs Rust); a desktop app is also available.
visioncortex/vtracer7.6k
GC Minimal Zine Poster
SkillTurns a theme, a line, an article or photos into a minimal, whitespace-heavy indie-zine portrait poster, and can distill reusable style rules and prompts from reference images, with built-in quality checks. Needs host image generation (e.g. Codex); otherwise outputs prompts only.
LiamGvchi/gc-minimal-zine-poster7.5k
sd
CLIA more intuitive find-and-replace tool than sed: uses JavaScript/Python-style regex syntax, supports literal string mode and in-place file edits, which suits agents doing bulk text rewrites.
chmln/sd7.4k
Backlog.md
CLITurns any folder into a Markdown task board: Claude Code or Codex break work into tasks with acceptance criteria for review before coding, managed from the terminal or a browser board. Works without Git for personal plans too. Runs locally with no account; needs Node.js or Homebrew.
MrLesk/Backlog.md7.4k
BrowserTools MCP
MCPHands your current browser session to the agent through a Chrome extension: read console logs and network requests, take screenshots, and run Lighthouse performance, accessibility and SEO audits without signing in again.
AgentDeskAI/browser-tools-mcp7.3k
Jupytext
CLIConverts and two-way syncs Jupyter notebooks with plain Python scripts or Markdown, so agents can edit research and teaching notebooks like ordinary text and diffs stay readable. Needs a local Python environment; install with pip.
jupytext/jupytext7.3k
OpenPencil
MCPOpen-source AI-native vector design tool with an MCP server built into its desktop app, connectable to Claude Code or Codex in one click. Agents read and edit .op designs in natural language, apply style guides and export React, Vue, Flutter or SwiftUI code. Needs the desktop app.
ZSeven-W/openpencil7.3k
Anthropic Sandbox Runtime (srt)
CLIAnthropic's official OS-level sandbox CLI: restricts file and network access for agents, MCP servers and any command without containers, using sandbox-exec on macOS and bubblewrap on Linux. Currently a research preview.
anthropics/sandbox-runtime7.2k
Trafilatura
CLIPython library and CLI for extracting main web content: fetches pages, crawls via sitemaps and RSS feeds, strips headers, footers and other noise, and outputs TXT, Markdown, JSON, XML and more with metadata. Also processes downloaded HTML offline.
adbar/trafilatura7.1k
Talk to Figma MCP
MCPUses a Figma plugin and a local WebSocket server so agents can read and directly edit designs: create frames and text, adjust auto layout and styles, and replace copy in bulk. Requires Bun; now maintained by Grab.
grab/cursor-talk-to-figma-mcp7.1k