TigerAI-A2A-Code2n8n-Skill-Pack

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.

Searches the reference-workflows/ corpus (2,061 real n8n workflows) and cookbook/ (8 curated patterns) to find the 3-5 closest examples to the user's described intent, then explains how each one works in plain language and how it differs from the user's need. Use when the user says "範例查詢模式", "找範例", "show me examples", "有沒有人做過", "類似的 workflow", or vaguely describes a goal and wants to see prior art before committing to a design.

Activates a 5-stage guided Q&A interview to help users describe their automation in plain natural language when they don't know how to start. Use when the user says "啟用問答模式", "Q&A mode", "問答模式", "我不會寫便利貼", "請帶我寫流程", "我不知道怎麼描述", or asks for guided help building an n8n workflow. Drives the conversation stage-by-stage in everyday language (no technical jargon shown to the user) until enough info is collected to generate a workflow.

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, choosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, API calls, format conversion, batch processing logic, or any custom JavaScript. Covers SplitInBatches loop patterns, cross-iteration data, pairedItem, and real-world production patterns.

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use cases — only use Python when the user explicitly prefers it or the task requires Python-specific standard library capabilities (regex, hashlib, statistics).

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between nodes, or referencing webhook data in workflows. Use this skill whenever configuring node fields that reference data from previous nodes — expressions are how n8n passes data between nodes, and getting the syntax wrong is the most common source of workflow errors.

Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are required for each operation, how displayOptions control field visibility, and when to use patchNodeField for surgical edits vs full node updates.

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities. Consult this skill whenever a validate_node or validate_workflow call returns errors or warnings — it knows which warnings are false positives and which errors need real fixes.

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, or scheduled tasks. Always consult this skill when the user asks to create, build, or design an n8n workflow, automate a process, or connect services — even if they don't explicitly mention 'patterns'. Covers webhook, API, database, AI, batch processing, and scheduled automation architectures.