Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 381,674 indexed, measured the same four ways as everything else here.
Research any industry or market to find underserved niches, unmet customer needs, and untapped opportunities. Analyzes competitor blind spots, customer complaints, emerging trends, and geographic gaps to surface specific business opportunities most people miss. No API keys or paid tools required — works with web…
Build dark, cinematic, awwwards-style landing pages with seamless scroll choreography — endless/infinite scroll loops, pinned image-morph galleries, book page-flip feature sections, full-page book sites, cross-dissolve scene transitions, unified AI-generated imagery, film-slate section markers. Use when the user asks…
TaskTime Pro is a free, open-source, local-first work manager for freelancers, covering tasks, timers, expenses, invoices, and reports. Core use requires no TaskTime account or cloud sync, works offline after the PWA is loaded or installed, and stores work records in the browser. This first-party TaskTime Pro skill…
★not rated 4
changed 1mo agoA
tokens not measured
AGPL-3.0
Production-ready skills for social media managers using Planable: draft post batches, clear the approval queue, audit the calendar, build monthly performance reports, compare clients, surface content patterns, and — with SE Ranking connected — turn SEO and AI-search gaps into social campaigns, coordinate page rewrites.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Enforces the official Rust API Guidelines (https://rust-lang.github.io/api-guidelines/) when writing, reviewing, or refactoring Rust library code. Use this skill whenever you are writing new Rust structs, enums, traits, functions, or modules that form a public API — including when designing error types, implementing…
Extract exact design specs from Apple's official Figma UI kits into SwiftUI, build signed macOS apps from a single Swift file without an Xcode project, implement password-free root operations safely, and preflight harness gates that block tool calls.
Security review of LLM applications and agents. Use when asked to review, red-team, threat-model or test an LLM feature, chatbot, RAG pipeline, MCP server or autonomous agent for prompt injection (direct or indirect), jailbreaks, system prompt or secret leakage, tool abuse, excessive agency, confused-deputy behavior…
ws — whetstone: sharpen the thinking before the work, and the work before it lands. Five skills. /ws:grill (user-only) runs a relentless, round-based interview over the design tree of a plan, decision or idea, asking the whole settled frontier at a time with a recommendation attached to every question; silence never…
★not rated 4
changed todayA
tokens not measured
originalMIT
Use when asked to explain, visualize, document, or create a dashboard for a codebase. Triggers: 'explain this codebase', 'visualize the architecture', 'create a codebase overview', 'generate project documentation', 'how does this project work', or any request to understand a project's structure and flow visually.
Build reusable, accessible, performant React components with hooks, composition patterns, and modern best practices. Use when building React UIs, creating component libraries, or optimizing React performance.
A set of general behavior rules for an AI coding assistant, written in Chinese. It requires Chinese code comments, explanations for Bash commands, Chinese notes alongside English technical steps, and Chinese reasoning.
Primary pipeline execution step after /prd-to-issues or for clearly scoped implementation work. Use to build, verify, and commit a concrete slice, delegating to /tdd for backend work and behavior-heavy frontend logic when red-green-refactor will reduce risk. Not for shaping or pre-merge review.
Build or review code for compliance with the EU AI Act, GDPR, the NIS2 Directive (EU 2022/2555), and secure-development (SSDLC) best practice. Three modes: repo gap analysis, compliance-by-design while coding, and data protection — the skill asks whether to pseudonymise (deterministic tokens, joins preserved) or…
★not rated 4 3mo agoA
tokens not measured
originalMIT
Anti-AI-slop design and copy rules for any UI work (website, web app, or interface). Use whenever building, refining, or auditing user-facing UI. Holds every visual decision to a purpose test and the result to a liveliness bar so the output feels crafted by a designer, not generated by AI. Two modes: DURING (apply…
Chambres Africaines Extraordinaires (CAE) / Extraordinary African Chambers in the Courts of Senegal (EAC) research, drafting, and analysis — the Hissène Habré case. Use whenever the conversation involves the CAE/EAC, the AU-Senegal Accord of 22 August 2012, the Statute of the Chambers, the Habré trial (2015-2016), the…
A development guide for Emlog, a PHP-based blogging and content-management system. It covers building and changing Emlog plugins, themes, templates, and related code.
Generate production-ready Helm charts on the bjw-s-labs common library (app-template v5, v4 legacy). Use for new charts, Compose-to-Helm conversion, sidecars, init containers, services, ingress, persistence, StatefulSets, HPAs, Service/PodMonitors, and NetworkPolicies.
Agentis is a browser-native multi-agent AI platform. Instead of a single AI model answering a question, Agentis deploys a coordinated team of specialized agents — researcher, analyst, coder, writer, reviewer, planner — across multiple LLM providers simultaneously, then synthesizes their outputs into one cohesive…
★not rated 4 6mo agoA0 tokens
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: