Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 386,229 indexed, measured the same four ways as everything else here.
You are an elite motion-graphics creative director who specializes in turning emotion into paper-collage animation, built for Google Omni — Google's AI video generator — and you write in one of two registers, locked at intake: AD MODE (9-figure DR copywriter: a product or offer, direct-response) or EXPLAINER MODE…
Run and troubleshoot privacy-preserving, local DSPy RLM security audits for large legacy .NET codebases. Use when asked to scan repositories for vulnerabilities, tune RLM/tool limits, fix truncation/stall issues, or produce actionable markdown/json audit outputs without loading entire codebases into model context.
Delegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills before you install them. The Skillsmith Agent diagnoses in full for free, proposes a batched fix plan, and changes files only with your per-changeset approval, with one-step undo. Triggers: "ask the Skillsmith…
Use this skill when building Solana-enabled games or apps in Godot 4 with the Godot Solana SDK. Triggers include: Solana transactions in GDScript, SPL tokens or NFTs in a Godot project, connecting browser or mobile wallets (Phantom, Solflare, Backpack) in a Godot game, calling Anchor smart contracts from GDScript…
A store-ordering assistant that reads weather, nearby events, sales, stock, waste, and shortages from Dataverse to suggest quantities for individual products. The store manager makes the final decision.
Use Sephera to keep a code change safe: check a file's blast radius before editing it, re-check every file the change touches, review the change before committing, fix breaks by following their suggestion, and gate the merge on breaking symbols that still have consumers. Trigger this skill when editing, reviewing, or…
Guide for creating, updating, and managing skills. Use when: you need to extend your capabilities with a new skill, or the user asks you to create one. Skills are persistent Markdown instruction modules auto-discovered at runtime.
An image-generation and editing tool built around the Wan2.7 model. It creates images from text, edits supplied images, combines multiple reference images, and changes visual styles.
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
Build, review, and refactor web interfaces that are easy for humans, screen readers, browser automation, Playwright tests, and AI agents to understand and operate. Use for UI components, forms, frontend features, semantic HTML, ARIA, stable locators, URL state, accessibility reviews, and agent-friendly web design.
Free web search via DuckDuckGo when Firecrawl is unavailable. No API key needed. Use ddgs CLI or Python library to find URLs, then webextract for content.
Interact with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research…
Comprehensive system control operations for security testing. Use this skill when you need unified access to file operations, process management, system information, and command execution through a single interface during authorized penetration testing.
Feed new content into the owner's central mind (this brain repo) — the ONLY way anything gets written into the brain. Use this whenever the owner says "feed this into my brain", "add this to my mind", "update my mind", "save this to the brain", or provides any new source to be remembered — a video, transcript, blog…
A website design-analysis tool that creates a complete DESIGN.md guide from a live website URL. The guide records the page’s visual rules, design reasoning, style analysis, CSS evidence, and constraints to avoid.
Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panelgate (composed-output) or the assemblygate…
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: