All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,856 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.
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.
Plugin Claude Code
Bundles 1 skill · 161 tokens together
Production readiness audit for apps built with AI coding tools. Detects your stack, audits 5 domains, and produces a scored punch list with copy-paste fixes.
HKUST-KnowComp/DeepRefine-Skill
Skill Claude Code
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.
Skill Claude Code
Scan a repository that already has Claude Code configuration (hooks, skills, CLAUDE.md, settings, MCP servers) and package it into a valid MCS techpack.yaml for distribution via mcs. Use this skill whenever the user wants to create a tech pack from an existing repo, convert a Claude Code setup into a shareable MCS…
UnpaidAttention/fable5-methodology
Plugin Claude Code
Bundles 26 skills, 4 agents, 5 hooks · 2,986 tokens together
Self-enforcing engineering methodology extracted from Claude Fable 5 for less advanced models: prime directives + integrity rules injected each session, 26 on-demand skills, 4 contracted subagents (builder, qa-verifier, code-reviewer, research-scout), and 6 lifecycle hooks that gate destructive commands and unverified.
Skill Codex
Run and validate AutoVideo-Agent Markdown-to-video workflows, including the v0.1-compatible deterministic offline command and v0.2 provider mode with ComfyUI media, Mock or Command TTS, scene-level SRT, normalized timelines, FFmpeg, and deterministic QA. Use for build, plan, provider, or QA requests; MiniMax, hosted…
SystemCraftsman/strimzi-kafka-cli
MCP server Claude CodeCodexCursor +2
Command Line Interface for Strimzi Kafka Operator. Runs locally from the strimzi-kafka-cli Python package.
Skill Claude CodeCodex
Sıfırdan production-ready bir SaaS uygulaması kur. Ödeme, kimlik doğrulama, veritabanı, e-posta, landing page, SEO ve API güvenliği dahil tüm katmanları kapsar. Kullanıcı SaaS kurmak, web uygulaması başlatmak, AI aracı oluşturmak veya online ürün çıkarmak istediğinde bu skill'i kullan — "startup kur", "proje başlat"…
Cursor rule Cursor
Cursor rule "rtfmbro" from marckrenn/rtfmbro-mcp, covering cursor instructions for package documentation, package documentation policy and workflow.
Plugin Claude Code
Bundles 15 skills, 9 agents · 301 tokens together
Multi-agent workflow framework for building, testing, and shipping statistical software packages.
Plugin Claude Code
Bundles 5 skills · 663 tokens together
A collection of practical agent skills from DevBrothers, including workflows for interviews, agent instruction files, automatic fixes, strategy advice, and designing work outputs.
Skill Claude CodeCodex
Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.
Skill Codex
Assess an open-source codebase for Arm/aarch64 readiness with the Arm MCP Server and produce a professional, evidence-backed Markdown and PDF case-study report. Use when a user asks to scan, assess, validate, enable, or fix Arm support; check multi-architecture containers or dependencies; create an Arm enablement…
Skill Claude CodeCodex
Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.
heyadam/claudedesign-to-swiftui
Plugin Claude Code
Bundles 1 skill, 1 command · 145 tokens together
Convert Claude-generated HTML design prototypes (URL or .tar.gz) into SwiftUI View files.
Skill Claude CodeCodex
A tool for moving an OpenClaw agent to another device, including its configuration, memory, skills, and credentials.
Skill Claude CodeCodex
Trace and investigate GitHub Copilot CLI sessions with agent-strace. Use when the user wants to capture a Copilot session, replay agent activity, explain a decision, diagnose repeated tool calls or failures, inspect cost, or audit a recorded session.
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 hook · 68 tokens together
Auto-start and manage the Tamp token compression proxy.
Plugin Claude Code
WakaTime plugin for Claude Code - Track your AI usage, lines of code generated, and time spent prompting AI.
Skill Claude CodeCodex
Authors, reviews, and hardens Bash scripts for the stability and security properties a linter cannot verify on its own, including strict-mode semantics and the cases errexit ignores, cleanup and locking on every exit path, injection-safe handling of untrusted input and filenames, PATH and environment control…
heloraai/Seedance2.0-Prompt-Optimizer-skill
Skill Claude CodeCodex
A prompt-writing skill for Seedance, an AI video-generation platform.
Skill Claude Code
Build deep codebase understanding using Capsule context, progressive-reader, and specialist agents instead of overwhelming main context. Triggers on: don't have context, understand codebase, learn about, need background. Implements progressive context building.
Plugin Claude Code
Bundles 4 skills · 293 tokens together
OpenTelemetry skills and reference documentation for AI coding assistants.
Skill Claude CodeCodex needs its repo
Creating effective riglets means writing knowledge (SKILL.md) that agents will rely on. This guide focuses on how to write high-quality documentation for riglets, organized efficiently.
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: