Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,706 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Generates a structured multi-file feature implementation plan after a detailed requirements interview. Triggers ONLY on the explicit /plan-me command (optionally with a feature name, e.g. /plan-me user-auth). Do NOT trigger on natural-language planning requests like "make a plan", "help me plan X", or similar — only…
Skill Claude CodeCodex
Provides visa requirements, entry regulations, and travel document guidance for international destinations.
Skill Claude Code
Delegate coding to Google Antigravity CLI (agy). Use when the user asks to build, code, debug, or fix something and Antigravity is a better fit than Codex — or as a parallel coding agent alongside Codex.
Skill Claude CodeCodex
Query employee records, search by name/department/city, and generate department salary statistics from a local SQLite HR database. Use when looking up employees, running headcount reports, or comparing department compensation.
Skill Claude CodeCodex
Set up, maintain, or operate a personal wiki vault (second brain). Three branches: Setup, Maintain, Operate. Trigger for: "set up my second brain", "lint my wiki", "schedule my vault operator", "check wiki health", "operate my second brain", or any vault bootstrap, maintenance, or operator task — even phrased casually.
Skill Claude CodeCodex
A prompt-writing system for making matching sets of anime-style educational knowledge cards with a recurring mascot character. Each card combines a character, layout, colours, art style, and educational content.
Plugin Claude Code
Bundles 5 skills · 448 tokens together
Azure DevOps skills for AI coding agents — work items, pull requests, and post-merge cleanup.
Skill Claude CodeCodex
Create, inspect, update, validate, publish, and operate GPTBots Agents, FlowAgents, LoopAgents, Audio Agents, and Workflows (.bot/.flow). Use for GPTBots configuration and prompt design, Tools/MCPs/Skills, model lookup, version release or rollback, Open API calls, evaluation and RAG testing, conversation LogTree…
full-stack-skills/agent-skills
Plugin Claude Code
Bundles 22 skills · 1,414 tokens together
Agent Skills provides the complete toolchain for working with Agent Skills.
Skill Claude CodeCodex
Use when the user asks to "write a prompt for DeepSeek", "compose a DeepSeek prompt", wants to send a task to a DeepSeek model, needs to launch a DeepSeek subagent. Also use when explicitly named: DeepSeek. Trigger on any request to draft, refine, or assemble a prompt targeting a DeepSeek-family model — for either…
Skill Claude CodeCodex
Một kỹ năng tạo câu mở đầu ngắn cho video trên mạng xã hội. Nó dành cho người làm video cần giữ sự chú ý của người xem ngay từ những giây đầu.
Skill Claude CodeCodex
The foundational template for Self-Evolving Agent Skills (SEAS). Standardized for autonomous learning and safety.
Skill Claude CodeCodex
Review PyTorch test refactoring for correctness and completeness against the decoupling standards defined in the refactor-test-decoupling skill. Accepts a test file path (whole-file review), a PR URL, a git diff, or a branch name. Use this when asked to review a test refactoring PR, check a test decoupling change…
Skill Claude CodeCodex
Manage and troubleshoot Hyperlift applications through the Spaceship public API. Use when the user wants to list or inspect Hyperlift applications, trigger or monitor builds, read build or runtime logs, inspect resource metrics, read or update environment variables, restart an application, or start/stop (scale) an…
Skill Claude CodeCodex
Standard playbook for performing a per-customer billing audit in SubSync. Use whenever the user asks to "audit billing", "check overdue", "review payment status", or otherwise needs a holistic view of a single customer's billing health. Covers the canonical 3-call sequence and the summary format that downstream UI…
Skill Claude CodeCodex
Build terminal user interfaces (TUI) with the Python Textual framework. Use when the user wants to create a terminal app, TUI, CLI dashboard, interactive terminal tool, or any rich terminal interface using Python. Triggers on mentions of Textual, TUI, terminal UI, terminal app, terminal dashboard, ncurses alternative…
supertypeai/sectors-agent-skills
Plugin Claude Code
Bundles 2 skills · 172 tokens together
Query financial market data from the Sectors API (api.sectors.app) for IDX and SGX markets.
colorzhang/coding-agent-skills
Skill Claude CodeCodex
AI-DLC workflow guide for software development. Triggers on AI-DLC, AIDLC, or ai-dlc keywords.
Skill Claude Code
Use agentkaizen to measure and prove whether your AI coding agent actually follows instructions. Works natively — no installation required. Use this skill when: you want to score a recent Codex or Claude Code session and check rule compliance (did it branch before work? stay within tool limits?); you changed AGENTS.md…
Skill Claude CodeCodex
Playwright testing. Use this skill to write and run automated tests for web applications using Playwright.
Skill Claude CodeCodex
Query databases (PostgreSQL, MySQL, SQLite, SQL Server) and inspect schema metadata. Use when the user wants to run SQL queries, list tables/views, or inspect table columns against any database. Runs non-interactively by inferring the database type and connection string from context; only ask the user when those…
Skill Claude CodeCodex
Generates ZK Framework ZUL pages (.zul) through a structured 5-step workflow: requirements clarification, ZUL generation, validation, controller generation, and a rendered-image self-review. Every step also stands alone, so use this skill for a single step too — validating an existing .zul, writing the…
Skill Claude CodeCodex
Use fllib stores, widgets, utils, and extensions in Flutter apps. Use when requests mention fllib APIs or integration.
Plugin Claude Code
Bundles 8 skills, 7 commands, 3 agents · 1,516 tokens together
Agent skills for Arenadata Cluster Manager (ADCM) bundle development - building a bundle from spec.yaml, validating it against a live ADCM, authoring config.yaml prototypes and Ansible actions, deploying and tearing down test clusters, and triaging failed jobs. Connection settings are resolved per user; no instance…
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: