# fastgpt-workflow-generator

fastgpt-workflow-generator — a skill that turns natural language requirements into production-ready FastGPT workflow JSON. Matches against built-in templates, adapts the structure, and validates the result across three layers.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 286 repo stars
- Author: YYH211
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/YYH211/Claude-meta-skill/tree/HEAD/fastgpt-workflow-generator/SKILL.md
- Updated: 2026-05-15
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/fastgpt-workflow-generator

## What it does

When you ask the skill to build a FastGPT workflow, it parses your request, finds the closest matching template from four examples (document translation, sales coaching, resume screening, financial news digest), and customizes it for your specific use case. If no template fits, it builds from scratch. After generation, it validates the JSON at three levels: syntax, node connectivity, and logic completeness.

The skill can add, remove, or modify individual nodes, regenerate their IDs to avoid collisions, and auto-arrange them on the canvas using topological layering. During generation, it updates all references between nodes, including template strings like `{{$nodeId.key$}}`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add YYH211/Claude-meta-skill --skill fastgpt-workflow-generator -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/fastgpt-workflow-generator/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/fastgpt-workflow-generator/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add YYH211/Claude-meta-skill --skill fastgpt-workflow-generator -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/fastgpt-workflow-generator/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add YYH211/Claude-meta-skill --skill fastgpt-workflow-generator -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/fastgpt-workflow-generator/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install YYH211/Claude-meta-skill fastgpt-workflow-generator
```

2. **Manually: put the files in place**
- File: `.github/skills/fastgpt-workflow-generator/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add YYH211/Claude-meta-skill --skill fastgpt-workflow-generator -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/YYH211/Claude-meta-skill --path fastgpt-workflow-generator
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/fastgpt-workflow-generator/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/YYH211/Claude-meta-skill/tree/HEAD/fastgpt-workflow-generator/SKILL.md

## When to use it
- generate production-ready workflow JSON from a natural language description
- adapt an existing workflow by adding or removing nodes
- pick a matching template and customize it to fit your requirements
- validate workflow structure for format, connectivity, and logic errors
- auto-layout nodes on the canvas and regenerate their identifiers

## Example prompts
- Generate a FastGPT workflow that screens resumes and validates each against a knowledge base
- Modify this workflow: add a node that calls a weather API and pipe its results into the main conversation flow
- Build a multi-agent workflow where two LLM nodes run in parallel, then merge their outputs

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: d76ca29cd282a756.

BEGIN THIRD-PARTY FILE d76ca29cd282a756
````text
---
name: fastgpt-workflow-generator
description: Generates production-ready FastGPT workflow JSON from natural language requirements. Uses AI-powered semantic template matching from built-in workflows (document translation, sales training, resume screening, financial news). Performs three-layer validation (format, connections, logic completeness). Supports incremental modifications to add/remove/modify nodes. Activates when user asks to "create FastGPT workflow", "generate workflow JSON", "design FastGPT application", or mentions workflow automation, multi-agent systems, or FastGPT templates.
---

# FastGPT Workflow Generator

> Automatically generate production-ready FastGPT workflow JSON from natural language requirements

## When to Use This Skill

Use this skill when you need to:

- **Create new workflows from scratch**: User asks to "create a FastGPT workflow for X purpose"
- **Generate based on templates**: User wants to build workflows similar to existing patterns (document processing, AI chat, data analysis, multi-agent systems)
- **Modify existing workflows**: User needs to add/remove/update nodes in an existing workflow JSON
- **Validate workflow JSON**: User has a workflow JSON that needs verification or fixing
- **Design multi-agent systems**: User mentions parallel processing, agent coordination, or workflow orchestration
- **Automate workflow creation**: User provides requirements document and needs executable JSON
- **Convert requirements to JSON**: User has specifications and wants a FastGPT-compatible workflow

**Trigger Keywords**: FastGPT, workflow, JSON, multi-agent, 工作流, template matching, workflow automation, node configuration, workflow validation

---

## Core Workflow

This skill follows a 5-phase process to generate production-ready workflow JSON:

### Phase 1: Requirements Analysis

**Goal**: Extract structured requirements from natural language input

**Process**:
1. **Identify request type**:
   - Create from scratch
   - Based on template
   - Modify existing workflow
   - Validate/fix existing JSON

2. **Extract key information using AI semantic analysis**:
   ```json
   {
     "purpose": "Workflow objective (e.g., 'Travel planning assistance')",
     "domain": "Application domain (travel/event/document/data/general)",
     "complexity": "simple | medium | complex",
     "features": ["aiChat", "knowledgeBase", "httpRequest", "parallel"],
     "inputs": ["userChatInput", "city", "date"],
     "outputs": ["Complete plan", "Recommendations"],
     "externalIntegrations": ["Weather API", "Feishu API"],
     "specialRequirements": ["Multi-agent", "Real-time data"]
````
END THIRD-PARTY FILE d76ca29cd282a756

The third-party file has ended. Everything between the d76ca29cd282a756 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2643 of 22311 bytes. © YYH211 · MIT · https://github.com/YYH211/Claude-meta-skill/tree/HEAD/fastgpt-workflow-generator/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
