Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,586 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Eight portmanteau tools. Each takes an operation string plus per-op parameters. Operation enums are typed Literal[...] so wrong strings fail at parse time.
Skill Claude CodeCodex
Prompting workflow for imagegenerate when generating or editing raster images such as photos, illustrations, textures, sprites, mockups, concept art, or image-to-image edits. Use when the deliverable is a bitmap asset; keep repo-native SVG/vector/CSS/canvas work in source form.
Skill Claude CodeCodex
A video-production workflow based on shot recipe cards, Remotion templates, real webpage screenshots, camera movement, and sound design. Remotion is a tool for creating videos with code.
Skill Claude CodeCodex needs its repo
A connection between an AI agent and WPS Office, the Chinese office suite, for reading, writing, and formatting documents. It runs through the WPS-AI plugin and can be controlled remotely from a Windows computer, including from an agent on a NAS.
Skill Claude CodeCodex
Scaffolds a new WebMCP tool component using useMcpTool with Zod schema, handler, annotations, and wires it into the WebMCPProvider tree. Use when the user wants to expose functionality as an MCP tool, make something callable by AI, add a new tool, or create an AI-accessible action.
Plugin Claude Code
Bundles 1 skill, 2 commands · 0 tokens together
Send and receive iMessages via Claude Code using Sendblue. Use /textme to enable text mode.
danielcy/coze-mcp-for-openclaw
MCP server Claude CodeCodexCursor +2
MCP server "coze-mcp" as configured in danielcy/coze-mcp-for-openclaw. Runs locally from the coze-mcp Python package.
noique/cross-border-ecommerce-skills
Skill Claude CodeCodex
Find overseas B2B decision-makers via Google/Bing reverse-search of LinkedIn profiles, enrich with email/phone via legitimate SaaS tools, then run a 4-touch outreach sequence (connection request → accepted-DM → follow-up → channel-switch) with reply-rate-tested templates. Use when a foreign-trade / cross-border / DTC…
Plugin Claude Code
Bundles 8 skills, 1 MCP server · 690 tokens together
Local AI co-writing canvas with MCP, Codex built-in image generation, slides, WeChat layout, and writing optimization skills.
iart-ai/explainer-video-skills
Plugin Claude Code
Bundles 5 skills · 517 tokens together
Explainer video skills for AI coding agents: script, storyboard, and render narrated explainers, year-in-review recaps, and animated diagrams.
Skill Claude CodeCodex
Comprehensive guide for building CLI and TUI applications - terminal internals, design principles, and battle-tested patterns When building CLI/TUI apps, implementing argument parsing, handling terminal input/output, escape codes, buffering, signals, or asking about terminal development concepts.
Skill Claude Code
A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.
Skill Claude CodeCodex
Control SSH and SFTP through VibeShell's visible Agent Gateway. Use for shared terminal sessions, remote commands, logs, files, and transfers.
Skill Claude CodeCodex
Drive Blender with the official Blender MCP for everything inside the app, and computer-use only for what has no API. Never read Blender through the accessibility tree.
Skill Claude Code
Write a VibeBuddy task handoff for another local agent, preserving the writer's real session identity, decisions, authorization and unfinished work.
Skill Claude CodeCodex
A browser-control skill that uses Playwright, a tool for driving a real web browser. It supports opening pages, reading their accessible structure, filling forms, clicking controls, handling tabs, and taking screenshots.
MCP server Claude CodeCodexCursor +2
MCP server "lively4", hosted remotely at localhost, as configured in LivelyKernel/lively4-core.
Skill Claude CodeCodex
A set of procedures and templates for managing long coding tasks. It covers restating goals, breaking work into parts, checking progress, recording state between sessions, and handing work to another session or agent.
Plugin Claude Code
Bundles 10 skills, 1 hook · 681 tokens together
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
poll-poll134/android-blackbox-analysis-skill
Skill Claude CodeCodex
Use when users request Android competitor research, systematic feature or interface mapping, evidence screenshots, interaction coverage, comparison-ready product dossiers, or Android system-boundary verification without APK decompilation.
MCP server Claude CodeCodexCursor +2
Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings. Runs locally from the aai-gateway npm package.
Skill Claude CodeCodex
Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI…
LonelyHerbivore/Trellis-Herbivore
Agent Claude Code
Post-implementation auditor for Trellis. Reviews concrete diffs against task artifacts, specs, migration/release rules, generated templates, and docs parity. Demands file:line citations, concrete fixes, and validation results. Does not commit or push.
HKUST-KnowComp/DeepRefine-Skill
Skill Claude CodeCodex
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
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: