Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 376,960 indexed, measured the same four ways as everything else here.
GoogleCloudPlatform/cortex-framework
Skill Claude CodeCodex
Reference guide for business rules, naming conventions, and data modeling standards enforced during data product development.
jkrandom-sudo/opencode-plugin-peers
Command Claude Code
List same-machine opencode peers you can exchange messages with (alias of /peers, compatible with Claude Code's /list-agents).
Skill Claude Code
Run one iteration of the doc improvement loop: generate or accept questions, answer them in parallel, verify, grade, diagnose, fix the docs, and re-evaluate until convergence.
adamfaik/claude-code-pm-starter
Skill Claude Code
Make a correction permanent. Takes something the user just fixed or disliked in a session and routes it to the right file (context, a skill, or the preferences log) so it never has to be said twice. Use whenever the user corrects the same thing again, or says "remember this".
Plugin Claude Code
Bundles 6 skills, 19 agents, 5 hooks · 1,120 tokens together
12-agent spec-first coding pipeline (Analyst → PM → Architect → PlanReviewer → ScrumMaster → Coder → QA → Reviewer → StressTester → Tuner → Verdict → DevOps).
Skill Claude Code
OSINT investigation toolkit for profiling individuals. Uses Holehe for email-to-account discovery, Sherlock for username-to-social-media mapping, and GHunt for Gmail account intelligence. All tool outputs are saved to files for analysis.
Skill Claude CodeCodex
AI-powered import tariff calculator and HS code classifier for cross-border trade. Instantly look up tariff rates, HS codes, duties, and landed costs for products imported into the US. Classify any product by name — no need to know the HS code. No local setup, no API key — just ask. Powered by accio.com. Use cases…
Skill Claude CodeCodex
Lets an agent drive headless Grok CLI (grok build) instances toward a user's goal — launch/monitor/salvage non-interactive grok -p runs, configure models and local OpenAI-compatible providers, attach reference files via --prompt-json, and read token usage from JSON output. Use when the user says things like "use grok…
aliyun/aliyun-sls-agent-skills
Skill Claude CodeCodex
Manage Alibaba Cloud SLS (Simple Log Service) resources using aliyun-cli. Use when working with SLS projects, logstores, log queries, or when the user mentions Aliyun Log, Aliyun SLS, LogStore, Log Collection, or log service operations.
Plugin Claude Code
Bundles 1 skill · 55 tokens together
Enhances Claude's ability to work with, debug, and build Slint GUI applications.
aaronvanston/skills-presentations
Skill Claude CodeCodex
Visual design guidance for bold, minimal presentations. Provides layout patterns, typography hierarchy, color specifications, and slide composition rules. Use when asking "how should this slide look?", "design guidance for...", "what layout for this slide?", or when translating content into visual structure for a…
Skill Claude CodeCodex
A set of rules for building iOS interfaces with UIKit, Apple's interface framework. It defines choices for layout, navigation, colors, fonts, dark mode, keyboard handling, and related views.
MCP server Claude CodeCodexCursor +2
MCP server for searching Fiverr gigs, sellers, and reviews. Runs locally from the fiverr-mcp-server Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for Cisco Packet Tracer 9 — live IOS, OSPF, BGP, NAT, VLAN, VoIP, QoS, IPv6, wireless. Runs locally from the packet-tracer-mcp npm package. Needs 1 environment variable to run.
NoahMustafa/claude-ats-cv-skill
Skill Claude CodeCodex
Build ATS-optimised, human-sounding CVs in LaTeX (Overleaf-ready code). Trigger this skill whenever a user asks to create, rewrite, reconstruct, or improve a CV, resume, or job application document — including when they upload an existing CV, paste raw experience, or describe a target role. Also trigger when the user…
Plugin Claude Code
Bundles 4 skills · 469 tokens together
Surface an AI agent's thinking and make it auditable. Instead of a wall of prose, your agent commits its reasoning to typed nodes and explicit edges — real data you inspect and correct node by node, converging on ground truth that carries across turns, sessions, and agents. Use it as an agent harness or operating…
Skill Claude CodeCodex
Pixel-faithful clone of any web UI into the user's existing stack, using whatever sources are available — a screenshot alone, a live URL, raw HTML/CSS, or any combination. Use this skill whenever the user wants to recreate, match, replicate, or "clone" a design from a screenshot, image, URL, Figma export, or HTML…
Skill Claude CodeCodex
A Chinese-language guide for writing and revising artificial-intelligence research papers for academic conferences.
MCP server Claude CodeCodexCursor +2
A production-grade PostgreSQL Model Context Protocol (MCP) server. Runs locally from the mcpg Python package.
MCP server Claude CodeCodexCursor +2
MCP server "scout" as configured in klarlabs-studio/scout. Runs in Docker (ghcr.io/klarlabs-studio/scout:1.15.3).
Plugin Claude Code
Bundles 10 skills, 1 MCP server · 888 tokens together
WinDbg/DbgEng debugging: crash dumps, live user-mode and kernel, Time Travel Debugging (TTD), and a Hyper-V checkpoint's Secure Kernel (VTL1) — MCP server plus skills that drive it: WinDbg debugging and MSRC patch comparison.
MCP server Claude CodeCodexCursor +2
VK (VKontakte): read walls, users, communities and stats; publish, edit and comment on posts. Runs locally from the vk-mcp-server npm package. Needs 1 environment variable to run.
lingfengz/llm-dengbao-assessment
Skill Claude CodeCodex
A Chinese-language assessment method for checking large-language-model systems against China’s classified cybersecurity protection requirements and related AI security standards.
Skill Claude CodeCodex
A multi-stage workflow for mathematical modelling competitions and similar problems using documents and spreadsheet data. It covers problem review, model selection, code, charts, validation, reproducibility, and writing handoff materials.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: