Operate tube-bridge as a coherent YouTube research system: frame questions, discover sources, select subtitle tracks, classify claims, test competing hypotheses, capture timestamped evidence, build and search local corpora, and report traceable conclusions. Use for evidence-oriented YouTube research, transcript…
Uses Swing MCP to test and verify Java Swing application behavior. Use when writing or executing UI test scenarios against Swing apps - filling forms, verifying tables and trees, exercising menus and dialogs, testing keyboard navigation, and visually verifying results.
A local security-scanning service for checking skills, plugins, and MCP servers before they are installed or used. MCP is a way for AI assistants to call external tools.
Guide developers through setting up P402 as their AI routing and payment layer for autonomous agents and AI tools. Covers OpenClaw, CrewAI, AutoGPT, LangChain, custom Python or TypeScript agents, and any framework that accepts an OpenAI-compatible endpoint. Handles secrets management for Zo Computer, Replit, Railway…
Inspect and permanently clean Xcode, Simulator, and XCTest storage through Derived's MCP tools or CLI. Use when a user names Derived, links the Derived app, asks to find developer storage, identify reclaimable Xcode data, inspect cleanup candidates, or delete selected candidates or categories. Prefer MCP and CLI…
Audit an e-commerce store's agent readiness — can an AI shopping agent find, understand and BUY there? Use when asked to check or improve a store for AI agents, before attempting an automated purchase, or to compare stores. Calls the free AgentReady API/MCP (agentready.market) — deterministic score /100, grade…
Use when a user asks to integrate with APIAny, choose or compare APIAny models, estimate APIAny credits or pricing, migrate OpenAI-compatible clients to APIAny, generate APIAny model usage examples, or run confirmed APIAny image and video tasks through the APIAny MCP server.
Use this skill when the user wants to add observability, tracing, or monitoring to a Python AI agent using the Observe SDK (ioa-observe-sdk). Trigger for requests like "instrument my agent", "add observability to this agent", "add tracing to my LangGraph / LlamaIndex / Python agent", "integrate the Observe SDK", "add…
Manage projects, work packages, attachments, relations, boards, users, watchers, and notifications in a connected OpenProject instance. Use for OpenProject discovery, task workflows, project administration, file handling, dependency management, and notification triage.
Use when connected to the Trident collaborative diagramming MCP server. Covers tool ordering, real-time collaboration protocol, how to deliver live suggestions and guided explanations to human collaborators without mutating diagrams, grid layout rules, and ID enumeration before any edit.
Finds verified live Lumi Studio iPhone and iPad apps from a first-party catalog covering 46 apps and all 50 Apple locales. Use when a user asks which iOS or App Store app fits a task, especially for pay-once or one-time-unlock, privacy-conscious, learning, productivity, photo, travel, or wellness needs. Returns…
Guide for querying databases through DBHub MCP server. Use this skill whenever you need to explore database schemas, inspect tables, or run SQL queries via DBHub's MCP tools (searchobjects, executesql). Activates on any database query task, schema exploration, data retrieval, or SQL execution through MCP — even if the…
Score Solana and EVM liquidity pools before providing liquidity. Returns a 0-100 pool score, an ENTER/HOLD/EXIT/REDUCE/AVOID verdict with calibrated confidence, and a public miss-inclusive track record. Use when a user asks whether a pool is worth LPing into, which pools currently look best, or how the scores have…
Amazon-seller research using AMZScout tools — analyze a product by ASIN, evaluate a niche / category, pull keyword & PPC data, and explore a brand's Amazon catalog. Use whenever the user asks whether an Amazon product is worth selling, to analyze a niche or its competition, find/discover products, check a listing's…
Publish static sites to the web instantly with shiply.now and manage them (updates, SSL checks, custom domains, variables). Use when the user asks to publish, host, deploy, share, or update a website/page/demo/report, or wants a live URL for generated files. Triggers - "publish this", "host this", "put this online"…
FIRE this skill when the user's intent is to discover, list, visualize, document, or summarize the technologies used in a software project. This includes all of the following triggers: EXPLICIT COMMANDS: /generate-tech-stack; "generate tech stack"; "create tech stack"; "show tech stack"; "build tech stack"; "make tech…
FIRE when user intent matches any of the following conditions — EXPLICIT TRIGGERS: /workflow-generator; "generate workflow"; "create workflow diagram"; "show workflow" ARCHITECTURAL VISUALIZATION INTENT: user wants to visualize, diagram, draw, map, or generate a system architecture diagram / component diagram /…
Use in any repository configured with Remogram (.remogram.json) or Remogram MCP for forge facts — PR status, checks, merge plan, repo status, ref compare. Not for Remogram product development.
Verify Polish companies and contractors by NIP, KRS, or REGON; check VAT status and bank accounts against the Ministry of Finance White List (Biała Lista); look up REGON/GUS registry data; read KRS registry data; and validate EU VAT numbers via VIES. Uses skanfirmy.pl's free, public API — no API key and no…
Verify and rights-safely project LiquiLens Evidence Carrier, Fleet Brief, or Trade Safety Receipt JSON in local files. Use for provenance, clocks, integrity, redistribution, FDC3, OpenLineage, brief validation, or order-bound policy-receipt verification; not for collecting market data, trading, recommendations…
Route and run BeforeUsersDo QA through its MCP tools. Use when a user asks to test, QA, review, or get feedback on a website, app, feature, preview, or user flow; asks for AI QA, a personal self-review, a real human tester, QA status, video, transcript, findings, or a completed BeforeUsersDo report.