Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 383,346 indexed, measured the same four ways as everything else here.
bgembalczyk/agent-antigravity-mcp
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 9 tokens together
MCP server + skill for Google Gemini Antigravity agent: sandbox code execution, web search, GitHub clone-branch-PR workflow, cron triggers.
Skill Claude CodeCodex
Use when an agent needs Brazilian financial market data, including stock quotes, historical prices, dividends, fundamentals, FIIs, currencies, crypto, inflation, Selic, Treasury indicators, REST integrations, MCP workflows, or a brapi Custom GPT Action.
Plugin Claude Code
Bundles 1 skill · 409 tokens together
Community remake of 叁笙's sourced book/video-to-interactive-HTML distillation skill.
Skill Claude CodeCodex
Manage iCloud Hide My Email addresses — list, create, edit, deactivate, export.
Skill Claude CodeCodex
Use this skill when the user wants to find unexplored tool, app, or project ideas that nobody has built yet. Triggers: 'nobodybuilt', 'find me an idea', 'what should I build', 'viral tool idea', 'unexplored niche', 'blue ocean', 'surprise me with an idea', 'what hasn't been built yet', or when the user sends a…
Skill Claude CodeCodex
A structured research workflow for studying companies and markets in mainland China and Hong Kong. It covers industry selection, supply-chain research, financial-report checks, and investor sentiment.
Bosh-Kuo/awesome-agent-toolkit
Skill Claude CodeCodex
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
Command Claude Code
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
raydeveloperF/App-Store-Connect-release-kit
Plugin Claude Code
Bundles 6 skills · 587 tokens together
A coordinated App Store Connect launch kit for localized metadata, keywords, screenshots, Pixelmator PXD editing, and safe ASC API task execution.
Skill Claude CodeCodex
Execute web-application assessment from setup and recon through injection, access control, auth/session issues, API, and SSRF chains.
Skill Claude CodeCodex
A Chinese-language guide for creating business and pricing plans. It first classifies the situation, such as launching a new paid product, changing prices, or exploring a new way to earn revenue.
Vladick-Pick/business-ontology
Skill Claude CodeCodex
Use after accepted ontology cards change. Compiles cards into the registry graph, checks links, and prepares the model for dashboard, MCP, or agent consumers.
Skill Claude CodeCodex
Use this skill when the user asks about Teamfight Tactics (TFT) — comps, items, augments, economy, pivoting, positioning, or any gameplay advice. Triggers: 'tftcoach', 'tft', 'teamfight tactics', 'what comp should I play', 'what items should I build', 'should I pivot', 'which augment', 'tft help', 'when to level'…
Plugin Claude Code
Bundles 1 skill, 2 hooks · 62 tokens together
Finds where a Claude Code session wasted tokens (uncached context, context bloat, oversized tool output, redundant reads, wrong-tier routing) and coaches the fix. Adds a live cost/context statusline and a non-blocking end-of-session coach.
liqinling1994-cloud/qinling-qu-ai-wei
Skill Claude CodeCodex
A Chinese-language editing workflow for making writing sound less formulaic and more like natural human writing. It can adapt the rewrite to styles such as plain description, essays, or letters.
Skill Claude CodeCodex
Deprecated: bmad-build is now the official implementation method. Only use this when explicitly invoked by name.
gootf/austrian-judgment-protocol
Skill Claude CodeCodex
Judgment protocol (production-grade): a unified Austrian-school decision framework for entrepreneurs, CEOs, and CTOs — Kirzner (opportunity discovery/alertness), Packard (demand-side entrepreneurship), Rumelt (strategy diagnosis), Hayek (knowledge problem), Foss & Klein (judgment authority)…
calebvbi/stream-deck-plugin-development
Skill Claude CodeCodex
Create, develop, test, troubleshoot, package, and certify Elgato Stream Deck plugins that use the Node.js SDK. Use for Stream Deck repository or runtime work involving manifests, actions, keys, dials, Neo, Property Inspectors, settings, profiles, animation, Marketplace validation, or causal QA. Do not use for general…
Skill Claude CodeCodex
Use for KIE.ai image/video planning, product visuals, marketplace assets, campaigns, review gates, and safe generation.
Plugin Claude Code
Bundles 14 skills · 1,926 tokens together
Agent skills that write blog content that ranks and doesn't read like AI.
Skill Claude CodeCodex
Observability for TypeScript services: one wide event per request or job, high-cardinality fields, span and metric design, OTel export, tail sampling. Use when adding or reviewing logging, tracing, telemetry, metrics or OTel wiring, deciding what a request or job should record, or debugging production from what a…
Skill Claude CodeCodex
Analyze disk space, find large files, stale data, and dev caches, and help the user safely free up disk space or move files to other drives (e.g. C to D). Use when the user asks what is taking up space, says their drive or disk is full, asks what to delete, asks what can be moved to another drive, wants to find large…
Skill Claude CodeCodex
Acts as a technical lead pairing with a developer on a user story — reads the story, explores the codebase to understand the tech stack and existing patterns, then produces a concrete file-by-file implementation plan with specific guidance on what to change, where, and why. Use when a developer says things like "how…
Skill Claude CodeCodex
Evaluator-Governed Recursive Improvement (EGRI) framework for turning ambiguous goals into safe, measurable, rollback-capable recursive improvement systems. Use when the user wants to: (1) build a self-improving system for any domain (ML, RAG, workflows, ETL, UI, compiler tuning, etc.), (2) formalize a vague…
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: