Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,013 indexed, measured the same four ways as everything else here.
Fetch and analyze an arXiv paper via tiered fallback (markdown -> arXiv HTML -> ar5iv -> PDF). Rate-limited for arxiv2md (28 req/min, deterministic). Produces a structured summary with citation, problem, key claims, method, results, limitations. Use when the user says "analyze arxiv paper", "summarize arxiv", "read…
Write and revise technical explainers in a casual, visual, example-driven format. Use for software, engineering, electronics, science, or math that needs a friendly voice, strong intuition, concrete examples, precise language, and diagrams. It adapts vocabulary and depth from five-year-olds to veteran practitioners.…
Use this agent when the user asks to review STM32 firmware code, check for bugs, validate peripheral configuration, audit interrupt priorities, check DMA setup, or review embedded code quality. This agent also regenerates code with fixes applied. Examples: Context: User wants code reviewed for correctness user…
Use when an AI agent needs to automate a real browser through Agent Browser Bridge CLI, including remote Chrome control, page extraction, clicking, typing, navigation, or screenshots.
Create Draw.io diagrams from reusable architecture diagram templates and always store editable .drawio files and exports in a diagrams/ subfolder. Use when the user asks for Draw.io, diagrams.net, editable architecture diagrams, or when an architecture workflow needs Draw.io versions of target architecture, solution…
MCP server for OpenReview — search submissions, fetch reviews, meta-reviews, rebuttals, and decisions from NeurIPS, ICLR, ACL ARR, COLM, TMLR, and more. Runs locally from the openreview-mcp Python package.
A security-audit topic for unsafe deserialization. Deserialization turns stored or received data back into program objects, and unsafe handling can create security risks.
x402 pay-per-use MCP server for IBM Granite AI — chat, code, embeddings, analysis, and time-series forecasting. Pay USDC on Solana per call. No IBM Cloud account required. Runs locally from the @three-ws/ibm-x402-mcp npm package. Needs 9 environment variables to run.
★not rated 7 3d agoA
tokens not measured
copy · 100%Apache-2.0
An MCP server for interacting with Roblox Game Clients (Delta, etc) over WebSocket+HTTP, with a server side decompile pipeline and in game UI. Runs locally from the roblox-mcp-server npm package.
Read-only MCP server for vessel AIS, ship tracking, schedules, and BYOK maritime providers. Runs locally from the @tools-mcp/vessel-traffic-mcp npm package. Needs 2 environment variables to run.
★not rated 7▲
+1 7d agoA
tokens not measured
originalMIT
Drive the lucius pairing canvas — build rich, self-contained HTML/CSS/JS/SVG one-pagers on ANY topic (architecture diagrams, product one-pagers, sales/CS collateral, design docs, explainers, simulations) as versioned iterations while pairing with a user. Use when the user says "lucius", "put it on the canvas", "new…
MCP server for Ozon Seller API + Performance API: 151 tools for prices, promos, ads, orders, returns and finance. Runs locally from the ozon-mcp-server Python package. Needs 5 environment variables to run.
★not rated 7▲
+2 1mo agoA
tokens not measured
originalMIT
Acts as the QAI Consultant marketing/PR specialist. Use whenever Gabi asks to write, draft, or plan a social media post (LinkedIn, Facebook, Instagram) promoting the QAI Consultant app or MCP server - release announcements, educational QA tips, milestones, case studies, or behind-the-scenes. Covers Romanian and…
Scientific Research Reasoning Engine for evaluating experimental and empirical claims — auditing ML training runs, ablations, and sweeps; reviewing papers; checking reproducibility; and producing structured research reports. Optional Weights & Biases integration via the experiment-audit-mcp server.
★not rated 7 1mo agoA
tokens not measured
originalMIT
Designs a complete webinar funnel - registration page promise, reminder email sequence timed against typical 35-45 percent show-up rates, webinar structure with a 70 percent teach / 30 percent offer split and the pivot script, replay window and urgency rules, and the post-webinar email sequence - with a funnel-metrics…
Advertising creative: campaign ideation, ad copywriting, social format specs, landing page CRO, brand kits and image generation direction.
★not rated 7▲
+1 3mo agoA
tokens not measured
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: