Плагины Claude Code
6 118 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
6 118 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceThe full Open Dashboard skill catalogue — the `add-component` skill (a retriever over 35+ UI shapes: forms, lists & tables, kanban/calendar/tree/timeline, detail & pages, display & feedback, RBAC/auth/i18n/billing/search/realtime) plus the operation skills (scaffold-dashboard, add-backend, rebrand). The shapes assume the scaffold-dashboard base (TanStack Start + the platform layer) — run scaffold-dashboard first, then compose the shapes on top.
Dart & Flutter authoring, testing, and maintenance skills.
Audit or apply test-first, evidence-backed cleanup for accumulated test, verification, and fallback bloat.
wjs-evaling-voicedrop-prompts
Security audit for codebases — threat modeling, vulnerability detection, compliance checking, and hardening recommendations
Research and knowledge tools: scout domains before building, map expertise, explore marketplace, brainstorm approaches
Core creation pipeline: onboard, create, fill, validate, test, package, publish — guided product creation with 20 structural quality patterns
Help AI say clearly and get to the point.
productivityLet your coding agent direct a cinematic launch video of your running web app. No LLM API key needed.
productivityThe honest disk report for AI coding agents: worktrees, checkpoints, caches, node_modules and .godot folders agents left behind, and a cleanup you can undo. Needs the agentdisk binary on PATH.
Memory for AI agents that you can read, edit and trust: plain Markdown files with sources and dates, a review queue for agent writes, and a handoff note for the next session. Stores ReversePort's proof-case findings when both are installed.
Skills, subagent roles, slash commands and an output style from the Model Citizen checkout, installable on their own. Rules, stances, hooks and the Codex projection need `bin/harness install`; see docs/runtime-installation.md.
workflowCloudflare's security audit, which NoVibe's security-review agent runs.
Réécrit un texte français qui sonne IA pour qu'il se lise comme son auteur, sans changer ce qu'il dit.
Use when the user describes a problem, decision or stuck situation but names no method: "how should I approach this?", "help me think this through", "we can't decide", "where do I start?". Picks the best-fit thinking method and runs it. Skip for plain execution tasks or when a method is named.
Use for Fermi estimation, or when a rough number is needed fast: "roughly how many...", "ballpark the cost", "estimate capacity or market size", "is this even feasible?". Decomposes, uses ranges and sanity-checks. Skip when exact data is available or a precise calculation is wanted.