Claude Code plugins

Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.

slop-review

claudecodex

Native diff review window (Monaco + Glimpse) for AI coding agents. Adds the /slop-review slash command in Claude Code, a `slop-review` skill in Codex CLI, and a pi extension exposing the same `/slop-review` command.

1 skill · 1 command

dbachelder/slop-review 49

win-hooks

claudecodex

Windows auto-patcher for vibe coders.

1 skill · hooks

LilMGenius/win-hooks 49

Collection of arXiv paper management skills including CLI tool integration for fetching/searching papers and converting papers to Markdown documentation

2 skills

ultimatile/arxiv-skills 49

membrowse

claude

MemBrowse memory tracking integration for embedded firmware projects

2 skills

membrowse/membrowse-action 49

Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.

1 skill · 1 command

antonbabenko/agent-plugins 49

Convert any file, URL, or media to clean Markdown — PDF, EPUB, HTML, images, YouTube, audio, video, and more

1 skill · 1 MCP server

ojspace/md-anything 49

ai-slop-thresher

claudecodex

한국어 윤문 스킬 ai-slop-thresher와 단축 호출 thresh

2 skills

Burntgogi/ai-slop-thresher 49

supabase

claudecodex

Official Supabase plugin for Claude Code with bundled Supabase skills and MCP access for project management, database work, auth, storage, and Postgres best practices.

2 skills

supabase-community/supabase-plugin 49

flats

claudecodex

Deploy sites to your Flats host.

1 skill · 1 MCP server

gosuda/flats 49

All-in-one status line: model info, context usage, rate limits (5h/7d), project details with git branch (dirty/ahead/behind), token breakdown, CLAUDE.md/rules/MCPs/hooks counts, tool activity, agent status, and todo progress. Supports Enterprise, Max, and Pro plans with i18n (English/Korean).

1 skill · 1 command

ai-younggle-man/claude-ultimate-hud 49

pronounce

claudecodex

Hear how developers actually say kubectl, GIF, JSON, JWT and 1,930 more — with a confidence label and a source citation on every entry.

1 skill · 1 MCP server

anzy-renlab-ai/pronounce 49

Answer Ansible questions and review Ansible code using official documentation from the Ansible ecosystem. Covers ansible-core, ansible-lint, ansible-navigator, ansible-builder, ansible-creator, and molecule. Use when the user asks about Ansible concepts, syntax, best practices, deprecations, or wants Ansible code reviewed against official docs. Use when user says "check my playbook against docs", "what does Ansible say about X", "how do I use module Y", or "review my role". Do NOT use for CoP good practices review (use ansible-good-practices instead). Do NOT use for general Python or YAML questions unrelated to Ansible.

1 skill · 1 MCP server

leogallego/ai-skills-ansible 49

Review Ansible code against Red Hat CoP automation good practices. Use when the user wants to audit, lint, review, check, or validate Ansible roles, playbooks, collections, or inventory for compliance with CoP rules. Optionally validates module parameters via ansible-know MCP. Use when user says "lint my role", "check my playbook", "review best practices", or "audit my Ansible code". Do NOT use for general Python or YAML linting unrelated to Ansible. Do NOT use for answering Ansible module usage questions or checking syntax against official Ansible documentation (use ansible-docs instead).

1 skill · 1 MCP server

leogallego/ai-skills-ansible 49

Create a new Ansible content collection following all Red Hat CoP good practices. Optionally uses ansible-know MCP tools to discover existing collections on Galaxy and inspect reference collections before scaffolding. Use when the user wants to create, generate, or bootstrap a new Ansible collection. Use when user says "create a collection", "new collection", "scaffold collection", or "init collection". Leverages ansible-creator when available. Do NOT use for reviewing existing collections (use ansible-good-practices instead).

1 skill · 1 MCP server

leogallego/ai-skills-ansible 49

Build AI agents in Ruby using the claude-agent-sdk gem. Covers query() one-shot calls, Client sessions, hooks, MCP servers, streaming, structured output, sandbox settings, session management, and Rails integration.

1 skill

ya-luotao/claude-agent-sdk-ruby 49

deckify

claude

Stop making slides. Let AI build them in HTML — the medium it was born to write in. Give deckify any brand URL; in minutes you get a brand-faithful Design System markdown plus a verified 9-slide HTML demo deck. Trigger: "use deckify on https://...", "build a deck like <brand>", "extract the design system from <site>".

1 skill

seacen/deckify 49

coreviz

claude

AI-powered visual asset management for Claude Code. Search, tag, analyze, edit, and organize your media library using natural language.

1 MCP server

coreviz/cli 49

Documentation-only PM workflows for X/Twitter research through a separate Hermes Tweet runtime.

1 skill

aniganti/pm-superpowers 49

uikit-max

claude

Reviews UIKit code for modern best practices, covering deprecated APIs, Auto Layout, view controller lifecycle, accessibility, performance, concurrency, and the full iOS 26 overhaul — from iOS 13 through iOS 26.

1 skill

tornikegomareli/UIKit-Agent-Skill 49

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat, dormant skills, permission drift, hook reliability, memory hygiene, and context bloat. Evidence-grounds every judgment finding before reporting.

1 command

ncoevoet/claude-markdown-health-check 49

Work with the Wildberries (WB, Вайлдберриз) seller API through the wildberries-sdk clients: find the operation, module, token category and host, then write a call that runs.

1 skill

eslazarev/wildberries-sdk 49

arXiv paper in, narrated and fact-checked explainer video out

1 skill

SunandBean/paper2video 49

Otimiza celulares e tablets Android por ADB e Fastboot, perguntando antes até onde ir, melhora a câmera e instala um emulador de PS1 se a pessoa quiser.

1 skill

cavaleiro-ai/android-optimizer 49

8 specialized agents for collaborative software engineering: Product Manager, UX Designer, System Architect, Code Reviewer, Technical Writer, Responsible AI, GitOps Specialist, and Sync Coordinator

niksacdev/engineering-team-agents 49

delm

claudecodex

Build faster with collaborating agents in Codex and Claude Code.

Decentralized-LM/delm-agent-plugin 49

Brand, plan, build, ship, debug, and refactor in plain language, with a roadmap that tracks every task, plus a creator toolkit. 42 commands, 37 agents, 22 skills, 2 MCP servers.

22 skills · 42 commands · 2 MCP servers

mike-coulbourn/claude-vibes 48

All 30 maintainer skills and 9 agent profiles: humanize and localize prose, triage, reproduce and verify bugs, review PRs, debug ML training, profile performance, bisect regressions, audit CVEs, generate changelogs, evaluate SemVer version bumps, isolate scratchpads, fix type errors, isolate faults, conduct adversarial reviews, route architect-editor edits, generate conventional commits, resolve merge conflicts, prune context, and prepare releases.

30 skills · 9 agents

00200200/maintainer-skills-lab 48

26 ready-to-use skills for LLM observability, several shipping runnable unit-tested scripts (cost calculator, OTel span validator, PII scrubber, hallucination consistency check) plus workflows for instrumenting, evaluating, debugging, securing, and monitoring LLM apps.

26 skills

ContextJet-ai/awesome-llm-observability 48

looker-skills

claudecodex

This repository contains a collection of "skills" designed to assist AI agents and developers in writing high-quality, standardized LookML code and guiding them through Looker onboarding. Each skill encapsulates specific instructions, best practices, and examples for different aspects of Looker development.

26 skills

looker-open-source/looker-skills 48

10 specialized subagents and 15 skills for Laravel development — architecture, Eloquent, API, testing, security, performance, debugging, validation, queues, caching, and more.

15 skills · 10 agents

iSerter/laravel-claude-agents 48