All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 434,126 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Skill Claude CodeCodex needs its repo
Write and run tests for bash scripts with bashunit. Use when adding or fixing tests for shell code, when a bashunit run fails, or when asked to raise coverage of a bash script. Covers loading the code under test, the assertion catalogue, the fast edit-run loop, and the API traps that produce silently-passing tests.
Skill Claude CodeCodex
Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.
Skill Claude CodeCodex
Use this skill whenever using the MintHCM MCP to check whether the task you are about to perform, or the information you are looking for, is already in the documentation.
Cursor rule Cursor
AtomicMemory persistent memory protocol and MCP tool usage.
Skill Codex
Use this skill when helping users build applications with AI4J in their own Java or Spring Boot projects, including first chat, streaming, tool/function calls, MCP, RAG, memory, Agent runtime, Coding Agent CLI embedding, FlowGram integration, provider configuration, dependency selection, and troubleshooting. It guides…
caipe-io/ai-platform-engineering
Cursor rule Cursor
Project Development Guidelines.
MCP server Claude CodeCodexCursor +2
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint. Remote server at micro.mu.
Plugin Claude Code
Plugin marketplace listing 1 plugin: phd-skills.
Plugin Claude Code
Bundles 3 skills, 1 agent, 4 hooks · 137 tokens together
Multi-agent task orchestration with visual terminal panes. Decomposes complex dev tasks into parallel Claude Code instances coordinated through dependency-aware waves.
Skill Claude CodeCodex
A task-routing and checking workflow for explicitly requested Metis work. It assigns work to defined roles, records checks, and limits recovery when something fails.
Skill Claude CodeCodex
Use when reviewing a CLIARE measurement artifact directory, explaining score changes, triaging issues, finding evidence, or proposing CLI remediation work from artifact-map.json, scorecard.json, issues.json, command-index.json, condition-dictionary.csv, shape.json, and evidence.jsonl.
Plugin Claude Code
Bundles 4 skills · 182 tokens together
Experimental skills for Claude Code Superpowers - new techniques and tools under development.
Command Claude Code
Initialize a new project with Claude OS.
vtroisWhite/andrej-karpathy-skills
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Plugin Claude Code
Bundles 1 skill · 162 tokens together
Grounds a coding agent's architecture decisions in real arXiv prior art: parallel isolated reads of papers found category-wise (divergence), converged into one recommended path with citations, a first step, and known failure modes to avoid.
Skill Claude Code
Create or revise academic conference posters in HTML/CSS and export print-ready PDFs. Use for poster design, layout edits, and print export.
MCP server Claude CodeCodexCursor +2
Local-first documentation for AI agents. Offline, instant, private doc retrieval. Runs locally from the @neuledge/context npm package.
panggungunvibe/atutun-xhs-cover
Skill Codex
A prompt generator for vertical Xiaohongshu covers in the Atutun style. Xiaohongshu is a Chinese social platform for lifestyle and product-sharing posts; the style uses large Chinese titles, a person cutout, checklists, stickers, arrows, and high-contrast layouts.
Skill Claude Code
Anti-detection browser automation for AI agents. Use when the user needs stealth web browsing, undetectable scraping, fingerprint spoofing, proxy rotation, or privacy-focused browser automation. Triggers include "stealth scrape", "anti-detection", "bypass fingerprinting", "camofox", "camoufox", "undetectable browser"…
Plugin Claude Code
Bundles 30 skills, 25 commands, 2 agents, 1 MCP server · 3,839 tokens together
Design engineering skill + system for AI coding agents: anti-slop UI, outcome recipes, spec-driven design, design-review + a11y agents, MCP quality gates.
Skill Claude Code
A workflow for publishing second-hand items on Xianyu, a Chinese marketplace for used goods. It turns an item description and images into a category, title, listing text, and a ready-to-submit listing.
Plugin Claude Code
Bundles 39 skills · 3,843 tokens together
A plugin containing 26 practical skills and scripts for automating work as a solo business owner, including content, community, communication, and computer tasks.
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Skill Claude CodeCodex
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task. Use when ClawMetry is installed on this machine and you want to check whether you are re-reading files, spinning in loops, or burning budget.
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: