5.328 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
c-c0rtexc-c0rtex/web-qa1
sansheng-gemini-video-marketplacesanshengai/sansheng-gemini-video1
ar-pluginskvothesson/ar-plugins1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenOrchestration & autonomy skills from broomva/skills: arc, autonomous, ctx-core, eve-forge, fleet, fleet-reconcile, governed-autonomy-loop, handback, handoff, p9, persist, provider-manager, resume, role-x.
Publishing & growth skills from broomva/skills: blog-post, citable, content-creation, format-first, revenuecast, seo-llmeo, social-intelligence.
Research skills from broomva/skills: checkit, deep-dive-research-orchestrator.
Robotics skills from broomva/skills: capx-agentic-robotics, orcahand.
Simulation skills from broomva/skills: data-provider, parallax, sourcer.
Strategy & decisions skills from broomva/skills: agentic-leadership, decision-log, phronesis, pre-mortem, premortem, strategy-critique.
Skill & prompt tooling skills from broomva/skills: attempt-audit, audit-harness-usage, broomva-cli, disambiguate, make-spec, mod-anything, prompt-library, prove-the-negative, skillify, skills-catalog.
Everyday utilities skills from broomva/skills: alkosto-wait-optimizer, gasgo.
Video & multimedia skills from broomva/skills: brainrot-for-good, content-engine, creative-review, launch-video, ltx-video, motion-lab, video-cut.
Closes a working session with a summary you can read, a handoff block for compacting now and a resume block for coming back another day.
Forces the agent to answer in numbered steps you can execute, with the exact command inside each step and no filler.
Makes a website start in the visitor's own theme and language, with no flash and no forced redirects.
Caveman-style token efficiency, spoken with a real Spanish regional accent: eleven dialects, two intensity levels.
Leaves a website ready to be found: robots.txt, sitemap, canonical, Open Graph, JSON-LD and the AI-crawler decision, ending in a measurement.
Audits a repository for legal exposure (AI Act marking, dependency licences, GDPR and cookies, EU consumer sales) and writes a LEGAL.md with the fix for each finding.
Turns several loose questions into a one-file HTML questionnaire with a progress bar, real multi-select checkboxes, a mandatory "Other" option and a button that copies every answer back as one block of text.
A live progress page for long agent tasks: a one-file HTML with a progress bar, percentage, what is done, what is left and what is blocked, rewritten by the agent as it works. The open tab updates by itself, and what the person has to do or decide lives on the same page.
Autonomous Telegram-bot QA: Telethon-driven E2E dialogs, reply & keyboard snapshot testing, specs generated from the bot's source code, zero-token test runs, media/stickers/voice, Mini App handoff to web-qa.
Give Claude real eyes for video: hand a whole clip to Gemini's native multimodal model and get back structured JSON.
Registra issues de mejora o fix en GitHub cuando el agente detecta un problema usando un plugin o el ecosistema
development
