5555 plugins de marketplaces públicos de Claude Code. Cada uno agrupa skills, comandos de barra, agentes, hooks o MCP servers que se instalan juntos.
copilot-primitives-claudegbb-acelerators/awesome-harness-primitives2
helderberto-skillshelderberto/agent-skills1
rudder-agent-skillsrudderlabs/rudder-agent-skills1
portugues-tecnico-controladokayquer/portugues-tecnico-controlado1Envía el repo con .claude-plugin/marketplace.json y listaremos cada plugin.
Enviar marketplace
Inspect Windows application storage, understand local disk usage, and safely move approved cleanup items to the Recycle Bin.
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
Helder Berto's 🛠️ Battle-tested software engineering skills for AI coding agents 🤖, from idea to PR.
TinyRobot component library code generation and implementation guidance
面向第三方 AI Agent 的安装与执行指南：如何使用 webmcp-cli 与浏览器页面交互。包含已注入 WebMCP 工具的页面领域专用工具说明。
指导如何使用 WebMCP SDK库去开发WebAgent的技能包，将前端应用快速智能化。它包含 TinyRemoter，WebMcpServer，WebMcpClient，createRemoter， AI-Extension插件开发的文档及指南。
为现有 Vue 3 + Vite 应用增量接入 TinyRobot Chat、GenUI、业务 WebMCP、业务 Skill 与 PageTool。
Installs every RudderStack skill plugin in one step: core knowledge, CLI, MCP, Terraform, Profiles and AI events.
devtoolsRewrites pt-BR technical text with 9 controlled-language rules, frozen terminology and AI-filler removal. Regression suite included.
writingInstall every skill in this repository as one plugin: production-grade, tailwind-v3-to-v4-migration, create-skill-autoresearch, tribunal, database-documentation, and app-ai-guardrails.
观远 BI · 马甲实战版：标准操作使用官方六组件；补充受限环境取数速查、只读汇总与数字出处、串行分块与恢复、看板口径档案与逐格验收，以及 ETL 治理、引擎报错、自定义图表、v7 发布和 SuperApp 兼容经验。官方版本以 references/official-cli-compatibility.md 的已审阅基线为准。
Aggregated (not authored here). Broad Apple-framework skills — SwiftUI, UIKit, Swift Testing, Concurrency, SwiftData, App Intents, WidgetKit, StoreKit, HealthKit, MapKit, TipKit, apple-aso, hig, simulator-utils, xcuitest, and more (a handful more ship disabled by default in disabled-skills/). By Prisma Labs (vabole), MIT.
workflowAggregated (not authored here). SwiftUI patterns — state, performance, Swift Charts, macOS multi-window, Liquid Glass, plus an Instruments-trace toolchain. By Antoine van der Lee (AvdLee), MIT.
workflowAggregated (not authored here). SwiftUI pitfalls LLMs make, deprecated-API watchlist, accessibility, and iOS 26 / Liquid Glass guidance. By Paul Hudson (twostraws), MIT.
workflowAggregated (not authored here). Ultra-compressed communication mode that cuts ~65% of output tokens (author's measurement), now grown into a 20-skill suite (commit discipline, review, refactor verbs, plus 4 skills — caveman-discover, caveman-manage, caveman-evidence-review, caveman-setup — for the author's hosted Caveman Cloud commercial service). Ships SessionStart and UserPromptSubmit hooks (needs node on PATH; runs on every prompt). General agent behavior. By JuliusBrussee; skills are MIT, the repo also ships a Business Source License 1.1 engine.
workflowAggregated (not authored here). 'Lazy senior dev' mode — forces the simplest, shortest solution. General agent-behavior skill. By DietrichGebert, MIT.
workflowAggregated (not authored here). ADHD-friendly output mode — leads with the next action, numbers steps, restates state each turn, makes wins visible. General agent-behavior skill. By Ayoub G. (ayghri), MIT.
workflowAggregated (not authored here). `xcodebuild` / `xcrun simctl` CLI reference — discover schemes, find simulators, build, install, launch, and screenshot in a loop. The CLI-driven counterpart to this catalog's idb-driven `interactive-simulator-ux-audit` and Tuist-scheme `host-driven-xcuitest-e2e`. By pz, MIT.
workflowPlan features as PRPs (Product Requirements Prompts): implementation blueprints with requirements, codebase context and validation steps, then execute them
A cross-vendor, review-gated implementation loop: dispatch coding units to Codex (pinned plain codex exec) or a sandboxed Claude Code (claude -p in a git-less copy), have the other vendor's model review the diff, iterate, gate on the full test suite, then ship as a PR. Encodes hard-won environment constraints (read-only git, no full-suite runs, stuck-job handling) and eight user-configurable dials.
