claude-depot

This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.

This skill should be used when the user asks to "build an MCPB", "create a desktop extension", "package an MCP server", "create an mcpb file", "distribute an MCP server", "bundle my MCP server", "create a local MCP extension", "make an MCP Bundle", or needs guidance on packaging a local MCP server for single-click installation in Claude Desktop. Covers the full workflow from project setup through packing, testing, and signing.

Clean up old cached plugin versions to free disk space. Use when the user says "clean cache", "cleanup plugins", "prune old versions", "free disk space", "plugin cache", "clear old plugins", or asks about plugin cache size.

This skill should be used when the user asks to "add MCP App support to my web app", "turn my web app into a hybrid MCP App", "make my web page work as an MCP App too", "wrap my existing UI as an MCP App", "convert iframe embed to MCP App", "turn my SPA into an MCP App", or needs to add MCP App support to an existing web application while keeping it working standalone. Provides guidance for analyzing existing web apps and creating a hybrid web + MCP App with server-side tool and resource registration.

This skill should be used when the user asks to "create an MCP App", "build a new MCP server with a UI", "build an interactive MCP View", "scaffold a new MCP App project", "build an MCP App from scratch", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.

Search and access Anthropic documentation covering Claude Code CLI, API, Agent SDK, and more. Supports natural language queries, content search, and direct topic lookup. Trigger on: /docs, documentation questions about Claude Code, Claude API, Agent SDK, prompt engineering, MCP, hooks, skills, tool use, streaming, batch processing, extended thinking, or any Anthropic platform feature.

This skill should be used when the user asks to "configure manifest.json", "mcpb manifest spec", "manifest.json fields", "user_config in mcpb", "mcpb icon configuration", "set up manifest for desktop extension", "mcpb compatibility settings", "mcpb server types", "mcp_config variables", or needs detailed reference for the manifest.json file used in MCPB desktop extensions. Provides the complete field reference, user_config schema, server type examples, and variable substitution patterns.

This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.

Build a structured research outline (items + field definitions) on a topic, mixing model knowledge with a single web-search supplement pass. Writes outline.yaml and fields.yaml to a topic-named subdirectory. Entry point of the 5-phase research pipeline.

Add more field definitions to an existing fields.yaml. Source new fields from user input or from a web-search subagent suggesting common fields in the domain.

Add more items (research objects) to an existing outline.yaml. Optionally launches a web-search subagent to suggest items in the topic's domain.

Run deep research on each item in outline.yaml by fanning out parallel web-search subagents. Writes one validated JSON per item to results/. Resumable — skips items that already have a complete JSON.

Convert per-item JSON results from /ultra-research:research-deep into a single markdown report with table of contents and per-item sections. Uses a bundled converter script — no per-run script regeneration.

Audit Claude Code rules and CLAUDE.md/AGENTS.md files for staleness, quality, and drift. Use when asked to audit rules, check stale CLAUDE.md, check stale AGENTS.md, review rules freshness, assess rules quality, improve my rules, find dead globs in rules, check if rules are up to date, review progressive disclosure setup, find contradictory rules, or optimize Claude Code memory files.

Answer questions about Tactical RMM (TRMM) — an open-source remote monitoring and management platform. Covers architecture, installation, agent deployment (Windows/Linux/macOS), MeshCentral integration, scripting (PowerShell/Python/Bash/Deno), script variables, custom fields, keystore, automated checks, tasks, automation policies, maintenance mode, alerting, email/SMS notifications, webhooks, REST API, global settings, overrides, permissions, Django admin, URL actions, user interface, software management, web terminal, management commands, reporting (Enterprise), SSO (Enterprise), third-party integrations (Bitdefender, Zammad), SNMP checks, BitLocker key retrieval, remote background sessions, and troubleshooting FAQ.