All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 418,030 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
TypeScript and JavaScript coding style conventions, centered on top-down narrative ordering (caller first, helpers below) and functions over classes. Read before writing or reviewing TypeScript/JavaScript code, including code inside a spec or a plan.
Skill Claude CodeCodex
verify from andforce/Openclaude.
stefan-jansen/claude-code-toolkit
Skill Claude CodeCodex
API authentication patterns including JWT, OAuth 2.0, API keys, and session-based auth. Covers token generation, validation, refresh strategies, security best practices, and when to use each pattern. Use when implementing API authentication, choosing auth strategy, securing endpoints, or debugging auth issues.…
SummerKaze/skill-arkts-syntax-assistant
Skill Claude CodeCodex
ArkTS syntax, migration, and optimization guide for HarmonyOS/OpenHarmony development. Triggers on: .ets files, ArkTS keywords, HarmonyOS/OpenHarmony context, @ohos packages. Help with syntax reference, TypeScript migration, performance optimization, compile errors, state management, component development, and…
Skill Codex
Audit system prompts, agent prompts, router prompts, tool/function-call prompts, and coding-agent instructions as executable contracts. Use before writing or seeding prompts; blocks vague "fix this / write code" tasks missing ownership and verification. Works with Hermes, Claude Code, Codex, OpenCode, OpenClaw.
Skill Codex needs its repo
Audit generic AGENTS.md, CLAUDE.md, and SKILL.md instructions for deterministic drift and model-era obsolescence candidates, then generate evidence-backed, reversible remediation prompts. Use when users ask to clean up, modernize, retire, or evaluate accumulated coding-agent instructions. Do not use it to…
Skill Claude CodeCodex
Cria um SKILL.md completo para Claude Code a partir de qualquer workflow, sessão executada ou ideia nova. Acionar quando o usuário pedir para criar, montar, construir ou salvar uma skill — mesmo que não use a palavra "skill". Triggers: "cria uma skill", "transforma isso em skill", "quero automatizar esse processo"…
andrewstellman/quality-playbook
Skill Claude CodeCodex
Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches.…
MCP server Claude CodeCodexCursor +2
MCP server "datanav" as configured in hike-lab/public-data-lens. Runs datanav.api.mcp_server with .venv/bin/python. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 164 skills, 3 commands, 1 agent, 2 hooks, 1 MCP server · 18,381 tokens together
Access PostHog analytics, feature flags, experiments, error tracking, and insights directly from your AI coding tool. Optionally capture Claude Code sessions to PostHog LLM Analytics.
MRCalderon3D/everything-game-dev-code
Plugin Claude Code
A universal game development scaffold for Claude Code with layered rules, agents, skills, commands, hooks, contexts, and isolated engine packs for Unity, Unreal, and Godot.
Plugin Claude Code
Bundles 3 skills · 68 tokens together
Coordinate reusable monitored OpenAI Codex agents from Claude Code.
dylantarre/animation-principles
Skill Claude CodeCodex
Use when implementing reduced motion alternatives, vestibular-safe animations, WCAG compliance, or designing for users with motion sensitivity.
Cursor rule Cursor
Rules for managing project documentation and AI instructions. They distinguish docs/ for explaining what the project is and why it works that way from rules/ for telling AI how to work.
Skill Claude CodeCodex
Drive a team of other AI coding CLIs from the current session through the reevesagents MCP server. Use when the user asks to delegate work to another model, run several agents in parallel, or orchestrate a multi-agent team. It can spawn Claude Code, Codex, Kimi, Qwen, OpenCode and other installed CLIs each in its own…
tzachbon/claude-model-router-hook
Plugin Claude Code
Bundles 5 agents, 4 hooks · 130 tokens together
Automatic model switching for Claude Code based on prompt complexity. No API key required.
Plugin Claude Code
Plugin marketplace listing 1 plugin: llm-router.
Skill Claude CodeCodex
A toolkit of mental models—reusable ways to examine decisions, systems, data, strategy, and human behavior. It chooses a response mode and combines a small number of models to organize the analysis.
Skill Claude CodeCodex
Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that dagr view renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.
Plugin Claude Code
Plugin marketplace listing 1 plugin: inkbox.
Cursor rule Cursor ✓ vendor
Use these rules to manage your Neon projects, branches, databases, and other resources programmatically using the Neon TypeScript SDK.
xjli360/sealeap-amazon-ad-skills
Skill Codex
A playbook for planning advertising on Amazon US for clothing products, using an ASIN lifecycle. An ASIN is Amazon's product identifier; the lifecycle describes whether a product is new, growing, mature, declining, or seasonal.
Cursor rule Cursor
Uni-App X conditional compilation.
Plugin Claude Code
Bundles 2 skills · 165 tokens together
Mastra framework and Factory supervisor skills with progressive disclosure for development, API inspection, troubleshooting, and operations.
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: