How to drive claude (Claude Code) as a non-interactive CLI tool — headless runs, MCP servers, permissions, output formats, and piping. Use when scripting Claude, spawning a sub-agent from another process, or wiring Claude into CI/automation.
Full browser UAT for web apps — Playwright testing with console/network error capture, accessibility checks, i18n validation, and bug triage. Use when running screen-by-screen UAT or testing specific features in any web or hybrid app (React, Vue, Angular, Ionic, Next.js, etc).
Use this skill when the user wants to verify that a real-world physical procedure was performed correctly using camera input — bolt installation, equipment pre-op checks, lockout/tagout, PPE verification, lab protocols, surgical site prep. Also use when the user asks about AR/XR procedure verification, persistent…
Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.
Turn a functional or technical spec into working, validated modern ABAP/RAP using abap-mcp — scaffold the foundation deterministically, implement behaviors, gate every file through fix/lint, generate tests, deliver in activation order. Use when the user has a requirement or spec and wants code started for them; do not…
Plan engaging puzzle-based activities for classrooms, parties, team-building, and events. Generates structured activity plans with printable puzzle recommendations, timing, difficulty levels, and direct links to free puzzle generators. Use when planning educational activities, party games, team events, or any occasion…
Monitor US-Iran strike probability using open-source indicators - news alerts, Iran internet connectivity, oil prices, flight traffic, military tanker detection, weather, Polymarket odds, and Pentagon activity. Use when user asks about "Iran strike probability", "strike radar", "Iran situation", "US attack Iran"…
Shiplight QA toolkit — the single entry point for all Shiplight test/QA work. Use ONLY when the user explicitly says 'shiplight' (e.g. 'write a shiplight test', 'use shiplight to verify X', 'shiplight cover') or invokes /shiplight. Routes to subcommands: init, setup-test-auth, update, create-yaml-tests…
Orchestrate original songs, score-first piano/orchestra works, instrumentals, or guided meditations from brief through craft, notation, Suno/Lyria packets, taste review, and verified generation. Use for "make a song", "compose piano", "orchestra", "sheets/tabs", "produce this", "create in Suno", "Lyria", "guided…
A skill for controlling the iTerm2 terminal app through its programming interface. It can work with terminal windows, tabs, sessions, panels, profiles, and layouts.
Produces structured judgment briefs for contested situations — news events, decisions, conflicts, strategy questions. Surfaces hidden bets, real disagreements, unspeakable truths, and who concretely pays. Use when the user wants sharper thinking about something messy, not a summary.
Core best practices for the Dinero.js money library. Use when writing, reviewing, or refactoring code that creates Dinero objects, performs arithmetic on monetary values, or handles money in JavaScript/TypeScript. Triggers on imports from 'dinero.js', monetary calculations, or price/cost handling logic.
Drive terminal sessions, panes, and TUIs from an agent, and prove what they render. Five distinct jobs — multiplex terminal work (sessions/windows/panes) as a tmux/screen replacement; snapshot any pane as a pixel-perfect PNG, headless, with no terminal emulator or display server; run the lens verify loop (run → settle…
Event Pod gives your agent a persistent world model — structured context that survives across sessions, models, and tools. Not a transcript. A causal model with certainty scores that gets sharper over time.
Run shell commands and transfer files over SSH via the tunnel-manager MCP server — on a single host (tmremote) or fanned out across an inventory group (tminventory), plus SSH reachability and key-auth checks. Use when the agent must execute a command remotely, copy a file to/from a host, run something across a whole…
Use when controlling a browser from the agent — daily tasks (open a site, fill a form, scrape), smoke-test after feature work, upload/download/dialogs. Prefer compact tools; never request screenshots unless a visual bug needs evidence.
Use when working on Minecraft Java mods, NeoForge, Forge, Fabric, KubeJS, ProbeJS, datapacks, resource packs, Minecraft shaders/client visuals, modpack crashes, Gradle mod workspaces, local mod jars, Modrinth/CurseForge metadata, mappings, Minecraft docs, or version migration.
ChangeDetection.io is a self-hosted or SaaS tool for monitoring web pages for changes — price drops, restock alerts, content updates, defacement monitoring. It's one of the most popular self-hosted tools (31k+ GitHub stars).
Ten pure-offline flight-ops calculators for pilots. (1) gradient — flexible climb/descent solver over {distance, time, GS, altitude, ROC, angle, %-gradient, ft/NM}. (2) fueluplift — Jet A-1 kg↔L↔USG↔lbs reconciliation with SG + temperature correction and the industry 3% tolerance rule. (3) windcomponents …
Deterministic EVM bytecode capability observations, EIP-1967 proxy resolution, current gas-price telemetry, and sourced market observations for autonomous applications on Base (Chain ID 8453).
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: