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.

vinv

claude

Give your agent runtime evidence: semantic code search, dead-code detection, and fault localization over real runs — zero code changes (Python).

1 MCP server

VinvAI/VinvAI 48

Google Ads data analysis and reporting skill for AI agents

1 skill

Bin-Huang/google-ads-open-cli 48

Universal dataset import for FiftyOne supporting all media types (images, videos, point clouds, 3D scenes), all label formats (COCO, YOLO, VOC, CVAT, KITTI, etc.), multimodal grouped datasets, LeRobot v3 robot-learning episode datasets, and Hugging Face Hub datasets. Use when users want to import any dataset regardless of format or source, load datasets from Hugging Face, handle autonomous driving data with multiple cameras and LiDAR, import LeRobot robot-learning episodes, or create grouped datasets from multimodal data.

1 skill

voxel51/fiftyone-skills 48

Export FiftyOne datasets to standard formats (COCO, YOLO, VOC, CVAT, CSV, etc.) and Hugging Face Hub. Use when converting datasets, exporting for training, creating archives, sharing data in specific formats, or publishing datasets to Hugging Face Hub.

1 skill

voxel51/fiftyone-skills 48

Find duplicate or near-duplicate images in FiftyOne datasets using brain similarity computation. Use when users want to deduplicate datasets, find similar images, cluster visually similar content, or remove redundant samples. Requires FiftyOne MCP server with @voxel51/brain plugin installed.

1 skill

voxel51/fiftyone-skills 48

fak

claude

Adjudicate every tool call like a syscall. fak's MCP server exposes capability-gated adjudication verbs (fak_adjudicate / fak_syscall / fak_admit) so Claude Code can screen a proposed tool call, run one through the kernel, or quarantine a result before it enters context.

1 MCP server

anthony-chaudhary/fak 48

Operate Multica from a local coding agent via the multica CLI: issues, comments, metadata, mentions, and status side effects.

1 skill

multica-ai/multica-cli 48

AWS の構成図を draw.io の形式(.drawio)で描く Skill。 / Draws AWS architecture diagrams as draw.io files (.drawio).

1 skill

sagochiko/aws-drawio-diagram-skill 48

Rigorous, fair peer review in two modes. (A) Red-team your OWN draft before you submit — a simulated panel (a generous champion, the brutal Reviewer 2, a novelty-hawk Area Chair) predicts the reviews and hands you a prioritized fix list. (B) Review SOMEONE ELSE'S paper when you're an assigned reviewer or helping your advisor — a fair, venue-formatted, submission-ready review. Grounded in official NeurIPS/ICLR/ACL reviewer guidelines; every criticism pinned to a location and checked against ACL's H1–H17 list of illegitimate critiques. No invented flaws.

1 skill

xf686/Meet-Reviewer-2 48

88API-Image-Gen

claudecodex

一个插件调用 88API 全部生图模型,支持 gpt-image、香蕉、Grok 等多种生图模型。适配 Claude、ZCode、DSH 等多种客户端!

1 skill

blackdm666/88API-image-gen 48

itwinai

claude

Integrate scientific training code into itwinai: distributed training, HPO, logging, profiling and scalability reports

1 skill

interTwin-eu/itwinai 48

Create social preview images grounded in a project's own images, examples, and purpose.

1 skill

morluto/generate-social-preview 48

sqlsim

claudecodex

Guidance for running SQL queries, scripts, load tests, and measured multi-threaded workloads with the native sqlsim CLI.

1 skill

microsoft/sqlsimtools 48

sqlpysim

claudecodex

Guidance for running sqlsim-compatible SQL workloads from Python with Microsoft's native mssql-python driver.

1 skill

microsoft/sqlsimtools 48

Debloat, switch off screen tracking (ACR) and vendor mic/camera access, speed up, calibrate picture and sound, and replace the launcher on Android TV / Google TV over ADB.

1 skill

JohnWayneeee/cleantv 48

caprock

claude

Ask Caprock from Claude Code: Second Brain memories and decisions, what past sessions did, spend and tokens per repo, CI status, stuck sessions. Read-only, local; needs the Caprock app running.

1 MCP server

dspv/caprock 48

ADT CLI, ABAP code review, Transport Request release gate, and SAP integration wiki.

shrek-abaper/sap-engineering-skill 48

The complete library of Agent Skills — AI agents & orchestration, MCP & SDKs, Oracle & cloud, frontend & animation, engineering workflow, content & brand, and creative production. Skills auto-activate when relevant.

155 skills

frankxai/claude-skills-library 47

hypervibe

claude

Bootstrap a full-stack T3 project (Next.js + tRPC + Drizzle + Tailwind + shadcn/ui) with modular addons for database, auth, payments, email, storage, i18n, analytics, domain, and SEO. Deploys to Vercel with GitHub integration.

90 skills · 1 MCP server · hooks

flavien-ia/hypervibe-harness 47

Swiss Legal Intelligence -- BGE/ATF/DTF precedent research, case strategy, legal drafting, and citation verification across all 26 Swiss cantons with Anwaltsgeheimnis privacy protection.

17 skills · 30 commands · 21 agents · 10 MCP servers · hooks

fedec65/bettercallclaude 47

AI agent skills for VTEX platform development — Architecture, FastStore, Payment, VTEX IO, Marketplace, and Headless Frontend.

46 skills

vtex/skills 47

amplitude

claudecodex

Use Amplitude as an expert analyst - instrument Amplitude, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts

36 skills · 1 MCP server

amplitude/mcp-marketplace 47

up

claudecodex

ultrapack — lean, opinionated skill pack for spec-driven, git-centered development

20 skills · 6 commands · 6 agents

btseytlin/ultrapack 47

Verification framework for Midnight claims — verifies Compact code by compiling and executing test contracts, SDK/TypeScript claims by type-checking and devnet E2E testing, ZKIR circuits by running through the WASM checker and inspecting compiled structure, witness implementations by cross-domain type-checking and execution against compiled contracts, or by inspecting source code. Multi-agent pipeline with explicit /verify command.

19 skills · 2 commands · 7 agents · hooks

midnightntwrk/midnight-expert 47

stratarts

claude

27 professional business strategy skills: idea validation, market analysis, business modeling, marketing, metrics, and fundraising frameworks

27 commands

maigentic/stratarts 47

Enterprise-grade AI Agent Skills for software development, DevOps, SRE, security, and product teams.

25 skills

addxai/enterprise-harness-engineering 47

Core knowledge for writing Midnight Compact smart contracts — contract structure, data types, ledger declarations, circuits, witnesses, and common patterns.

15 skills · 3 commands · 3 agents · hooks

midnightntwrk/midnight-expert 47

nette

claude

Conventions and best practices for Nette Framework, Latte templating engine, and NEON configuration format

20 skills

nette/agent-plugins 47

cem

claude

LSP and MCP support for Custom Elements - intelligent autocomplete, validation, and AI-native component understanding

12 skills · 1 MCP server · LSP

bennypowers/cem 47

gemini

claude

Use Gemini CLI from Claude Code for code reviews and task delegation.

3 skills · 8 commands · 1 agent · hooks

abiswas97/gemini-plugin-cc 47