Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 374,394 indexed, measured the same four ways as everything else here.
End-to-end international trip planning: turns "I want to go to X for N days" into a verified, bookable plan — route skeleton across cities, flight price scans (international + domestic legs), train-vs-fly decisions, hour-by-hour daily timelines with opening hours, dwell times, holiday collisions and tappable…
Speech-to-text via ExtremeRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
Add WebMCP tools to a web app: read the repo, propose a reviewable tool plan, implement against @nekuda/webmcp-sdk, and verify the tools in a browser — or connect the tools a site already has, without rebuilding them.
A framework for building web apps where the server drives page updates while the browser reacts to changes. It uses server-sent events, a way for servers to send updates to browsers over a connection, plus signals and DOM updates.
A short writing guide for the tone and style of developer-tool products. It defines writing principles, examples, wording to avoid, and adjustments for product, marketing, and support channels.
MCP server "marketplace-mcp" as configured in mendix/web-widgets. Runs ./automation/marketplace-mcp/dist/index.js with node. Needs 1 environment variable to run.
★not rated 40 2d agoA
tokens not measured
originalApache-2.0
Svelte best practices for writing, editing, or reviewing Svelte/SvelteKit components and modules. Use when touching Svelte reactivity, props, events, snippets, each blocks, styling, context, actions/attachments, stores, or Svelte 5 runes.
Auto-activates structured briefing sessions for complex legal queries -- detects when multi-agent coordination benefits from pre-execution intake and plan building.
Persistent, bitemporal memory for Claude Code: the MCP tool surface, six skills that teach the model to use it, recall injected at session start, and capture before compaction.
★not rated 40
changed 7d agoA
tokens not measured
AGPL-3.0
Engineering guardrails for Claude Code: path-scoped rules, review and verification skills, specialist subagents, and hooks that enforce what instructions only request.
★not rated 40 7d agoA
tokens not measured
originalMIT
Manage AI agent memory with P0/P1/P2 priority system and auto-archival. Use when: setting up memory management, cleaning up MEMORY.md, creating lessons files, configuring auto-archive cron, or reviewing memory structure. Reduces token usage by 70-80% while maintaining recall via semantic search.
MCP-backed workflow for building UI with @marmoui/ui. Bundles the marmo-ui skill, /marmo-ui: commands, and the Marmo MCP server so agents read real component props instead of guessing. Works free without a token; add your Pro token for on-brand generation.
★not rated 39▲
+1 2mo agoA
tokens not measured
originalMIT
Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph database.
Generate production-ready React/Next.js code from Figma designs. Instructs proper Figma MCP tool usage, component reuse strategies, and variant mapping. CRITICAL: ALWAYS use this skill when user provides a Figma link or mentions implementing/redesigning from Figma design. Never attempt manual implementation without…
Figma design system to design.md — Extract Figma design system into a structured design.md document. Automatically detects token files, style configs, and Figma MCP data to generate comprehensive design system documentation covering Colors, Typography, Spacing, Border Radius, Elevation, Responsive, and more.
★not rated 39 6mo agoA
tokens not measured
originalMIT
Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and…
A developer focused model context protocol (MCP) server for Umbraco CMS. Runs locally from the @umbraco-cms/mcp-dev npm package. Needs 5 environment variables to run.
★not rated 39 5d agoA
tokens not measured
originalMIT
Search and retrieve data from local Weaviate using semantic search, filters, RAG, and hybrid queries.
★not rated 39 10mo agoA27 tokens
originalMIT
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: