Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 387,409 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Trigger continual harness refinement from the Python REPL. Use when you notice a repeated failure, reusable tactic, delegation role, or behavior policy that should be persisted as a harness entry. Returns immediately; refinement runs when the current turn ends.
Skill Claude CodeCodex
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
andrea9293/mcp-documentation-server
Skill Claude CodeCodex
Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…
Plugin Claude Code
Bundles 1 skill · 239 tokens together
Agent skill for the KSafe Kotlin Multiplatform encrypted persistence library — setup, usage patterns, anti-patterns, and debugging.
Skill Claude CodeCodex needs its repo
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
MCP server Claude CodeCodexCursor +2
MCP server "ai-kline" as configured in QuantMLResearch/AI-Kline. Runs locally from the ai-kline Python package.
Plugin Claude Code
Bundles 1 command, 19 hooks · 14 tokens together
Pixel-art office that visualises Claude Code agents. Registers the hooks that forward subagent, MCP and session activity to the office server on port 3334.
Plugin Claude Code
Bundles 4 skills, 2 MCP servers · 243 tokens together
iOS development pack: XcodeBuildMCP and an iOS Simulator MCP, plus skills for simulator build/run, axe UI automation, TestFlight releases and signing troubleshooting.
lucy-cxy/oss-investment-scorecard
Skill Claude CodeCodex
Evaluate an open source project through a venture investor's lens. Owner Mode is a health check for maintainers (where the project stands, what an investor would ask, what to do next). Investor Mode decides whether a project is investable by a USD VC fund in the AI cycle. ALWAYS use this skill when the user asks to…
Skill Claude Code
A video-editing workflow for adding variety-show-style graphics to interview footage, such as animated text, cards, speaker labels, chapter headings, and other on-screen effects.
Skill Claude CodeCodex
Identify security vulnerabilities and suggest secure coding practices.
skydoves/android-testing-skills
Skill Claude CodeCodex
Use this skill to wire adb reliably into CI — bash idioms, exit codes, parallel device fan-out with xargs -P, port forwarding (adb forward LOCAL REMOTE vs adb reverse REMOTE LOCAL — opposite argument order, the most common scripting bug), test-runner status codes (-1 error, -2 failure, -3 ignored, -4…
Skill Claude CodeCodex
A tool for finding real Taiwan court judgments and legal interpretations with verifiable citations before answering questions about Taiwan law.
Skill Claude CodeCodex
Optional house rules for bladebro. Bladebro itself needs no skill — the package registers its MCP server with pi and the five tools arrive complete. Add your own preferences here if you want the agent to use bladebro in a particular way.
Skill Claude CodeCodex
This is a sample Pet Store Server based on the OpenAPI 3.0 specification. You can find out more about. Use when working with the Swagger Petstore - OpenAPI 3.0 or when the user needs to interact with this API.
Totoro-jam/battle-tested-patterns
Plugin Claude Code
Agent skills built on the Battle-Tested Patterns catalog — adopt patterns into your code, or audit your code against the catalog.
Skill Claude CodeCodex
Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.
opencoredev/login-with-chatgpt
Skill Claude CodeCodex
Integrate Login with ChatGPT (@opencoredev/loginwithchatgpt-): let users sign in with their own ChatGPT account and run AI requests against their ChatGPT plan. Use when adding ChatGPT account login, mounting createChatGPTHandler, rendering the LoginWithChatGPT React button or useLoginWithChatGPT hook, wiring…
rrezartprebreza/spring-boot-skills
Plugin Claude Code
Bundles 34 skills · 1,604 tokens together
39 Spring Boot 3, Framework 6, security review, supply chain, incident response, Spring AI, and MCP skills.
Skill Claude CodeCodex
Operate a multi-controller UniFi deployment behind one MCP server. Use when there is more than one controller, when a task must run against a specific controller, when a controller is unreachable, or when a controller's credentials need to be managed.
crawfordxx/xiaoma-durex-copywriter
Skill Claude CodeCodex
A Chinese-language copywriting method based on layered meanings and deliberate space for the reader to interpret. It produces short copy, optional longer copy, and image concepts in five aspect ratios after offering several options.
Skill Claude CodeCodex
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
Skill Claude CodeCodex
Build TUIs with a Raycast-like React API using termcast. Implements @raycast/api components (List, Detail, Form, Action) rendered to the terminal via opentui.
Skill Claude CodeCodex
Use this skill when the user wants to build with the Claude API or Anthropic SDKs.
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: