framework/engineering/skills/engineer-plugin-mcp/SKILL.md
Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping, and validation. Use when adding an MCP server to a plugin.
npx skillsauth add korchasa/flow engineer-plugin-mcpInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill for MCP tools inside an AI IDE plugin. Keep server implementation host-neutral and generate host-specific wiring separately.
Do not treat this skill as a full MCP protocol or host configuration specification. Protocol versions, SDK APIs, host config fields, approval policies, and validation commands can change. Before implementation, open the current official docs for the MCP protocol and every requested host, then cite or link the pages used in the output.
Fetch only the sections needed for the current task. For any host not listed, find its official MCP, plugin, extension, or connector docs first. If no official docs exist, say so and separate verified behavior from assumptions.
For implementation requests, produce:
For design-only requests, return the same shape as a concise design response without writing files or running smoke tests.
tools
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools
Recommend which LLM model to use for a task. Use when asked "which model / best LLM for X", "pick a model for this task", or for a model shortlist ranked by live leaderboard evidence (coding, reasoning, agentic, tool-use, price, speed). Live-fetches public leaderboards and ranks models with per-axis rationale and citations.
development
Produce a comprehensive Product Requirements Document (PRD). Use when the user asks to write a PRD or formalize a feature's scope, goals, and success metrics.