Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 374,719 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Use this skill when a user asks for SEO keyword research, keyword discovery, search volume analysis, keyword difficulty, search intent mapping, topic clusters, content opportunities, competitor keyword gaps, or a keyword strategy for a domain, URL, product, market, or seed topic. When a website is provided, crawl and…
Huskyauto/VisionClaw-Agent-Public-Release
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 MCP server · 88 tokens together
VisionClaw Agent — multi-tenant agentic AI platform exposing 243 production tools, 16 specialist personas, hybrid-search Skill-RAG, and a self-improving skill registry over MCP. One-click access to project management, Drive/email/calendar, web research, code execution, multi-channel messaging, schema-aware databases…
daetojemax/figma-to-swiftui-skill
Skill Claude CodeCodex
Implement or update iOS SwiftUI UI from Figma designs; also use for implementation plans, token mapping, or asset export for that UI.
Plugin Claude Code
Bundles 2 skills · 55 tokens together
Create and review Readwise highlights; save articles to Reader; triage your reading queue — all from Claude Code.
Skill Claude Code
A workflow for using Jujutsu, a version-control tool similar to Git, with rules for starting work, committing changes, and managing bookmarks.
Plugin Claude Code
Bundles 3 skills, 4 hooks, 1 MCP server · 111 tokens together
The memory layer Claude Code doesn't have. A persistent knowledge graph that learns from your conversations — your AI assistant never starts a session blind.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
singkitlee/vedic-astro-pyjhora-skill
Skill Claude CodeCodex
A Vedic astrology analysis system that uses birth details to create and examine an astrological chart. Vedic astrology is a tradition that interprets the positions of celestial bodies at a person’s birth.
Skill Claude CodeCodex
A task-execution procedure for an AI agent, written in Chinese, that emphasizes understanding the goal, confirming the task, completing all steps, checking the result, and delivering it. It also requires the agent to reveal assumptions and constraints.
Command Claude Code
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
Skill Claude CodeCodex
Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.
ibm-self-serve-assets/building-blocks
Skill Claude CodeCodex needs its repo
Expert Confluent Cloud architect specializing in creating complete, production-ready streaming solutions with Infrastructure-as-Code (Terraform), Apache Flink SQL (including MLFORECAST time-series forecasting), and Python producers. Generates structured artifacts organized by domain (code, scripts, documentation) for…
Skill Claude CodeCodex
This skill should be used when setting up Riff - the hands-free voice AI system with a smart ring controller (Riff Bridge) and voice narrator (Riff Voice). Triggers include "set up riff", "install riff", "configure riff", "set up the ring", "set up voice", "riff bridge", "riff voice", or any request to install or…
santosomar/ethical-hacking-agent-skills
Skill Claude Code
Creates Nuclei YAML templates for vulnerability detection across HTTP, DNS, TCP, SSL, and other protocols. Use when converting a confirmed vulnerability, misconfiguration, or exposure into a reusable automated check — for example, turning a manual finding into a detection rule, writing a CVE check, or codifying a…
Skill Claude Code
Cut a Hexkit release — update the changelog, bump every version-of-record, run the gate, commit, and tag. Use when the user asks to "release", "ship a version", "cut vX.Y.Z", "bump and tag", "tag a release", or otherwise wants to publish a new Hexkit version. Operates only on the hexkit-devutils repo (the desktop app…
anilcancakir/laravel-ai-sdk-skills
Skill Claude CodeCodex
A test skill.
coinglass-official/coinglass-api-skills
Skill Claude CodeCodex
CoinGlass API skill. Routes to the appropriate sub-skill based on user intent. Covers futures, ETF, options, spots, on-chain, indicators, account, and other market data.
Skill Claude CodeCodex
A skill that describes law爷 as a professional legal adviser, including its role, style, principles, and areas of knowledge.
baochunli/pi-collaborating-agents
Skill Claude CodeCodex
Operating guide for coordinator and spawned subagents using the collaborating-agents extension. Covers agentmessage actions, subagent spawning, subagent session inspection, reservations, delivery semantics, limits, defaults, and failure handling.
MCP server Claude CodeCodexCursor +2
MCP server for Reqable local capture data. Runs locally from the reqable-mcp Python package.
jango-blockchained/mcp-freecad
MCP server Claude CodeCodexCursor +2
MCP server "mcp-freecad" as configured in jango-blockchained/mcp-freecad. Runs locally from the mcp-freecad Python package.
shouldnotappearcalm/a-share-mcp
MCP server Claude CodeCodexCursor +2
MCP server "a-share-mcp" as configured in shouldnotappearcalm/a-share-mcp. Runs locally from the a-share-mcp Python package.
Plugin Claude Code
Bundles 1 skill, 4 agents · 347 tokens together
Tech-lead orchestration mode: the top-tier model keeps architecture and decisions, a role roster of cheaper subagents does the implementation, the routine, the digging and the review. Save tokens without losing quality.
Skill Claude CodeCodex
AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.
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: