workflow-agent
选择并改写 ComfyUI 工作流模板，输出可直接提交到 ComfyUI API 的完整 JSON。当需要准备渲染任务、选择模型、调整参数时触发。
Best use case
workflow-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
选择并改写 ComfyUI 工作流模板，输出可直接提交到 ComfyUI API 的完整 JSON。当需要准备渲染任务、选择模型、调整参数时触发。
Teams using workflow-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/workflow-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How workflow-agent Compares
| Feature / Agent | workflow-agent | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
选择并改写 ComfyUI 工作流模板，输出可直接提交到 ComfyUI API 的完整 JSON。当需要准备渲染任务、选择模型、调整参数时触发。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Workflow Agent 管理和组装 ComfyUI 工作流。 ## 模板位置 `/home/node/.openclaw/workspace/workflows/` ## 工作流程 1. 根据 Prompt Agent 的输出选择模板（如 `sdxl_basic.json`）。 2. 用 Python `json` 模块读取模板，替换以下字段： - 节点 `6` 的 `inputs.text` → 正向 prompt - 节点 `7` 的 `inputs.text` → 反向 prompt - 节点 `3` 的 `inputs.seed` → 随机整数 - 节点 `3` 的 `inputs.steps` → 按复杂度动态设置 - 节点 `3` 的 `inputs.cfg` → 按风格动态设置 - 节点 `5` 的 `inputs.width` / `inputs.height` → 按画面类型动态设置 3. 输出替换后的完整 JSON（不附加解释文本）。 ## 模型选择规则 - 默认写实/通用：`sd_xl_base_1.0.safetensors` - 快速实验：`flux1-schnell-Q5_K_S.gguf`（需要 Flux 专用工作流） - 用户未指定时用 SDXL ## 参数精细化规则 ### 1) CFG（按风格） - 写实/照片：`4-6`（更自然） - 动漫/插画：`7-9`（更风格化） - 概念艺术：`6-8` - 未知风格默认：`7.0` ### 2) Steps（按内容复杂度） - 简单场景（单主体）→ `20` - 复杂场景（多人物 + 背景）→ `30` - 精细细节（特写、珠宝、建筑）→ `35-40` ### 3) 分辨率（按画面类型） - 人物特写/肖像：`768x1024`（竖版） - 风景/全景：`1024x768`（横版） - 默认/不确定：`1024x1024` ## 参数默认值（兜底） | 参数 | 默认值 | |------|--------| | steps | 25 | | cfg | 7.0 | | width | 1024 | | height | 1024 | | sampler | euler | | scheduler | normal | ## 禁止事项 - 不修改节点连接关系（只改 inputs 值） - 数值字段不得写成字符串（seed 必须是 int，cfg 必须是 float）
Related Skills
n8n Workflow Mastery — Complete Automation Engineering System
You are an expert n8n workflow architect. You design, build, debug, optimize, and scale n8n automations following production-grade methodology. Every workflow you create is complete, functional, and follows the patterns in this guide.
n8n-workflow-automation
Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.
swarm-workflow-protocol
Multi-agent orchestration protocol for the 0x-wzw swarm. Defines spawn logic, relay communication, task routing, and information flow. Agents drive decisions; humans spar.
agentic-workflow-automation
Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff artifacts.
byt-workflow
YouTube video translation workflow, download audio, launch Doubao, play audio, capture translation
banner-youtube-translate-workflow
Complete workflow: download YouTube audio, launch Doubao, play audio, capture translation. Activates when user needs full video translation.
ayao-workflow-agent
Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should be delegated to coding agents, (2) managing parallel coding tasks across front-end and back-end, (3) monitoring active agent sessions and coordinating review, (4) user says 'start task', 'assign to agents', 'swarm mode', or references the ayao-workflow-agent playbook. NOT for: simple one-liner edits (just edit directly), reading code (use read tool), or single quick questions about code.
dify-workflow
Use when creating, editing, debugging, or validating Dify workflow DSL for self-hosted Dify. Start from an exported workflow of the target instance, edit minimally, and verify by re-importing.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
task-review-workflow
Standard PR review and merge workflow for task-driven development. Use when reviewing a programmer agent PR linked to a task, deciding merge vs change request, handling post-merge actions (Trello + branch cleanup), and sending a clear outcome handoff.
task-development-workflow
TDD-first development workflow with structured planning, task tracking, and PR-based code review. Use when building software projects that require clarification phases, planning approval gates, Trello task management, test-driven development, Git branching policies, and PR feedback loops with reviewers.
gui-workflow
State graph navigation, workflow recording and replay with tiered verification.