Art & Design

twitterapi-io-read

github.com

Read-only skill for twitterapi.io — look up public X/Twitter data (tweets, user profiles, followers and followings, advanced search, replies, quotes, trends, lists, communities) through the twitterapi.io REST API with a single x-api-key header. Use when the user wants to search, analyze or monitor public posts and accounts. Read-only: no posting, no account login, no credentials beyond the API key.

$ npx skills add kaitoInfra/twitterapi-io
Voir la compétence→

herohunt-ai/herohunt-mcp

github.com

HeroHunt People Search MCP server. Search for talent across LinkedIn, GitHub, and StackOverflow from any MCP-compatible AI agent.

$ npx skills add herohunt-ai/herohunt-mcp
Voir la compétence→

lerchenflo/claudeskills

github.com

Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.

$ npx skills add lerchenflo/claudeskills
Voir la compétence→

lerchenflo/claudeskills

github.com

Provides instructions for installing and using the `android` CLI. The `android` command-line tool is a critical tool for Android development and helps you create new Android projects, run Android apps on devices, manage and interact with Android virtual devices (including screenshots and UI inspection), manage Android SDK components, look up official Android documentation, and discover and install official Android skills.

$ npx skills add lerchenflo/claudeskills
Voir la compétence→

iwishwp/AgentOS

github.com

操作 AgentOS 桌面(niri/Wayland):窗口与工作区管理、GUI 应用无障碍操作、浏览器自动化、文件产物、桌面通知与呈现。任何挂载了 AgentOS 八个 MCP 扩展(niri/desktop/system/files/session/a11y/browser/cred)的 agent 框架可用。涉及"操作用户桌面上的应用/窗口/文件/通知"时使用。

$ npx skills add iwishwp/AgentOS
Voir la compétence→

silasroliver-hue/replica-skill-cursor

github.com

>- Plans the stack, database schema and API for an app clone, from the recon map replica-recon wrote. Picks boring, managed tech, turns the inferred data model into real SQL with indexes and access rules, lists every route by flow, and orders the build as a thin vertical slice first. Use when the user says "plan the clone", "what stack should I use", "design the database", "write the schema", "plan the API", "architecture for my version of X", or after /replica-recon finishes.

$ npx skills add silasroliver-hue/replica-skill-cursor
Voir la compétence→

GreenWich-art/agent-skills

github.com

桌面 GUI 操作的统一编排入口。当用户要求操作一个只有图形界面的应用(改设置、点按钮、填表单、操作无 CLI/连接器的软件)时使用此 skill。提供四级能力:①路由决策——判断任务该走连接器、浏览器控制、Office 技能、命令行还是 computer use 桌面接管;②授权引导——检测并引导用户完成 macOS 辅助功能/屏幕录制权限授权,处理授权不生效等常见坑;③任务派发与验证——按目标/边界/失败处理三段式描述派发 GUI 任务,并以最终截图为准确认结果;④AX 兜底层——内置 axctl 工具做元素级无障碍读写(AXPress 语义点击,不碰鼠标不抢焦点),适用于 computer use 不可用或轻量场景。台前调度全场景实测(macOS 15 + 27.0.1 复检)。触发词:操控电脑、操作某个软件、点某个按钮、GUI 操作、电脑设置。

$ npx skills add GreenWich-art/agent-skills
Voir la compétence→

silasroliver-hue/replica-skill-cursor

github.com

>- Rebuilds an app screen by screen from the recon map: app shell first, then the core flow as a vertical slice, then every screen with all its states, ticking off the feature matrix as it goes. Writes every line fresh, never the original's code, assets or copy. Use when the user says "build the clone", "build screen S07", "start building", "rebuild this screen", "implement the booking page", or after /replica-design.

$ npx skills add silasroliver-hue/replica-skill-cursor
Voir la compétence→

vibbs/agent-skills

github.com

Build an interactive, self-contained HTML architecture explainer — one authored topology projected through audience personas, analytical lenses, eras, and a narrated tour, delivered as a single zero-network .html file that reads as an article, presents fullscreen, and embeds in any page. Use whenever the user wants to visualize or explain a system: "how does X work", "diagram our architecture", "system overview", "component map", "explain this pipeline", "make a diagram for the blog / for a client / for the docs", HLD or LLD, data flow, or turning a codebase or design doc into something a reader can explore. Strongly prefer this over Mermaid, ASCII art, drawio, or static SVG whenever the system has nested groups, more than one audience, or will be read by someone who is not in the room to narrate it.

$ npx skills add vibbs/agent-skills
Voir la compétence→

kodawarimax/omni-design-studio

github.com

コンセプト質問シート・参考デザイン(画像/URL/100件人間キュレーション)から色彩・構図DNAとキャッチコピーを0msで決定論的抽出し、サブスク0円の最上位画像モデル(Codex `image_gen` [gpt-image-2.5-sunburst] または Antigravity `image-generator` [Imagen 4 Ultra])の写真素材と合成して、①Webサイト、②300DPI印刷ポスター(PNG/PDF)、③パッケージ(3Dモックアップ&展開図SVG)、④プロモーショナルビデオ(9:16縦型&16:9横型MP4)を1コマンドで生成する統合デザインスキル。下位モデル(Flash Low / DeepSeek Flash / Luna)でも迷わず同一品質を出せる3ステップ決定論設計。

$ npx skills add kodawarimax/omni-design-studio
Voir la compétence→

g-ki/agent-skills

github.com

Breaks an RFC, design doc, or finished productive-thinking session into small 1-story-point tickets a team can pick up independently, with acceptance criteria, files to touch, and dependencies. Use when the user wants to split a design or feature into tickets, stories, or tasks, plan a sprint from an RFC, or asks "how do we deliver this".

$ npx skills add g-ki/agent-skills
Voir la compétence→

brunofbloq/embedded-agent-skills

github.com

Design, implement and execute embedded firmware verification across host unit/mocks, static analysis, Renode or QEMU simulation, hardware-in-the-loop, J-Link/ST-Link/OpenOCD, UART/RTT, and physical measurement. Use for test strategy, regression, fault injection, acceptance gates, timing/stack/resource evidence and CI test automation on bare-metal, RTOS and embedded Linux targets. Select the cheapest credible test backend and clearly separate virtual-model evidence from real hardware qualification.

$ npx skills add brunofbloq/embedded-agent-skills
Voir la compétence→

g-ki/agent-skills

github.com

Facilitates Tim Hurson's 6-step Productive Thinking Model for hard engineering problems (architecture decisions, refactors, feature design), grounded in the actual codebase, and turns the finished session into a Technical RFC. Use when the user wants to think a problem through step by step, run a structured design session, or write an RFC from one.

$ npx skills add g-ki/agent-skills
Voir la compétence→

brunofbloq/embedded-agent-skills

github.com

Implement, modify, debug, review and optimize embedded firmware for STM32, ESP32, Cortex-M and related MCUs using bare-metal C/C++, FreeRTOS, Zephyr or vendor HALs. Use for peripheral drivers, GPIO, SPI/I2C/UART/CAN, DMA, ISR, boot, power, concurrency, build failures and small code changes; also low-level embedded Linux drivers/BSP implementation. Prefer embedded-architect for major design decisions and embedded-qa for independent test strategy and verification.

$ npx skills add brunofbloq/embedded-agent-skills
Voir la compétence→

brunofbloq/embedded-agent-skills

github.com

Design, evaluate and review embedded systems across bare-metal MCUs, RTOS, embedded Linux and heterogeneous SoCs. Use for new feature or product architecture, compute/OS selection, hardware-software partitioning, system topology, interfaces, concurrency and IPC, resource/latency/power budgets, recovery, architectural trade-offs and architecture-changing refactors. For substantial work use a two-phase architecture review and approved module-by-module implementation workflow; skip the full gate for isolated fixes that do not change architecture.

$ npx skills add brunofbloq/embedded-agent-skills
Voir la compétence→

aurumiles/Skill

github.com

SKILL CAROSELLI CANVA — Crea un carosello Instagram per @aurumiles dentro Canva (create-design / copy-design di #8), stile deciso con Davide il 24-25 set 2026: font Anton/Roboto/OpenSauce, oro su nero, una foto vera di Davide solo in copertina. Usala SOLO quando Davide chiede esplicitamente «in Canva» o di clonare/adattare un carosello già fatto in Canva. Per i caroselli nello stile delle lezioni (rosso su nero, Oswald, fatti qui da Claude) usa la skill `caroselli-claude`.

$ npx skills add aurumiles/Skill
Voir la compétence→

alty-oss/dev-design

github.com

Use when delivering a UI change with its decisions, verification evidence and remaining limitations.

$ npx skills add alty-oss/dev-design
Voir la compétence→

alty-oss/dev-design

github.com

Use when a UI task needs its audience, primary job, content, constraints and success criteria clarified before design.

$ npx skills add alty-oss/dev-design
Voir la compétence→

alty-oss/dev-design

github.com

Use when mapping existing UI tokens/components or defining a coherent token and component contract for implementation.

$ npx skills add alty-oss/dev-design
Voir la compétence→

alty-oss/dev-design

github.com

Use when reviewing UI keyboard access, focus, accessible names, structure, contrast and motion behavior.

$ npx skills add alty-oss/dev-design
Voir la compétence→

alty-oss/dev-design

github.com

Use when establishing a distinctive visual direction for a new UI or an intentional redesign.

$ npx skills add alty-oss/dev-design
Voir la compétence→

Shaked-sz/claude-corp

github.com

Run the corp Design studio - a live UI/UX co-design session with the user, using the taste design skills and Claude's Design artifact type, staffing design workers, and reporting the approved direction back to the corp manager. Use when the user or the corp manager runs /corp:design-studio, or asks to "open the design studio".

$ npx skills add Shaked-sz/claude-corp
Voir la compétence→

Shaked-sz/claude-corp

github.com

Run work as the corp manager - size the task, staff the specialist teams (architecture, security, design/UX, planning, development, QA, talent) at junior/normal/senior levels, route work between them, keep the shared board, verify every result, and report to the user. Use when the user says /corp:manage, "act as the manager", "run this with the teams", "corp", or hands over a project-sized goal.

$ npx skills add Shaked-sz/claude-corp
Voir la compétence→

SailRain/scientific-plotting-skill

github.com

Plot existing time-domain numerical data as pure time series or paired phase trajectories and waveforms, or render existing MAT categorical planes as sheared slices; arrange, export, and verify figures for the target placement. Do not use for generating simulation data, modifying models, numerical solving, designing classification criteria, or analyzing dynamical mechanisms.

$ npx skills add SailRain/scientific-plotting-skill
Voir la compétence→