MorrisLu-Taipei

End-to-end Code2n8n Path B auto-pilot. Auto-activates when the user (a) pastes a GitHub repository URL with any Code2n8n intent, OR (b) says "啟動 Path B 計劃" / "start Path B plan" / "kick off Path B" / "Path B 全自動" / "auto-pilot Path B" / "pipeline this MIT repo" / "把這個 repo 做成 n8n" / "Code2n8n 跑這個" / "Code2n8n this repo" / "make this n8n" / "上架完成報告 一條龍". Drives the full 12-stage pipeline: License gate → Inventory → Partition (Connector / Plugin / runtime Sub-agent) → Pre-Security Review → Build artefacts → Generate workflows → V&V Layer 1 + 2 → Activate to n8n → Completion report. Architecture is split: main agent executes, sub-agent (fresh context, no shared history) acts as critic with VETO power per the v0.28.1 A2A directive. CRITICAL LANGUAGE RULE: all sticky notes, prose artefacts, completion report — MUST be written in the SAME language the user used to trigger the SKILL (English request → English sticky notes; Chinese request → Chinese sticky notes; etc.).

Use when introducing ANY external dependency into the project — npm packages (`npm install` / `pnpm add` / `yarn add`), GitHub repo content fetched via curl / WebFetch, external workflow JSON files received from third parties, or container base image bumps. Enforces multi-tier security review SOP (provenance check, source code review for high-trust packages, commit-hash lock for raw content fetches, ingestion gate for workflow JSON, AI Coder must pass SCA gate before claiming "ready"). Required by `code2n8n-pipeline` Stage 7 before any `npm install` runs.

Review an AI-coded application or n8n workflow for production security and change-control readiness. Use for security audits, production readiness, enterprise governance, auth/SQL/secret review, SECURITY-CAVEATS.md, version control, rollback, release tagging, CI/CD, or before declaring a Code2n8n port deployable.

Applies TigerAI enterprise-grade design patterns when generating n8n workflows — Atomic Orchestration, Universal Worker (FastAPI), Specification-Driven Development (SDD), and security/governance constraints. Use when the user mentions enterprise / production / 企業級 / 原子化 / orchestration / FastAPI worker / SDD, or when a workflow involves heavy compute (PDF/MP3/image processing), regulated data, or multi-team handoff. Drives architectural decisions like loop transparency (batchSize=1), location-transparent workers, and mandatory error/audit annotations.

Convert an existing program / system into an n8n workflow that preserves enterprise governance — login, audit, version control, handover, cross-system orchestration. Use when the user asks to "把這個程式 / 專案 / 系統移到 n8n", "Code2n8n this repo", "port this codebase to n8n", "convert this serverless function / web app / script into n8n", or anytime the input is a running codebase and the desired output is an n8n workflow plus the docs/validation that go with it.

Convert n8n Code (JS) nodes into native declarative nodes (Set / Filter / Merge / Crypto / Aggregate / ConvertToFile) so the workflow is readable by n8n-experts who don't know JavaScript. Use when the user asks to "原生化", "改成 n8n 原生 node", "reduce Code nodes", or refactor an n8n workflow JSON to remove JS where possible.

Standard SOP for reading and writing n8n workflows via the n8n REST API — read sticky notes from a workflow, push generated JSON back, list workflows, activate/deactivate, manage executions. Use when the user references a workflow by ID/URL, asks to "deploy" or "push to n8n" or "讀 n8n", or when sticky-note-to-workflow needs to fetch source/write target. Uses raw HTTP REST API only; no MCP dependency.

Core skill that converts a Layer 1 Sticky Note (DSL-formatted user requirement) into a complete three-layer n8n workflow JSON — Layer 1 preserved, Layer 2 nodes generated, Layer 3 AI commentary auto-written. Use when the user pastes a sticky note draft, references an existing workflow ID containing user sticky notes, or asks to "generate the workflow" / "build it" / "產 workflow" / "幫我寫 workflow" after providing a DSL spec. This is the central executor — it orchestrates the n8n-mcp tools, validates output, and emits a JSON ready for n8n import.