用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/ForceInjection/domain-driven-design-skills --skill template-generator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Conduct deep academic research for philosophy, neuroscience, cognitive science, and theoretical computer science (computability, complexity, AI theory, logic). Use when user asks to: research academic topics, find scholarly papers, conduct literature reviews, analyze citations, synthesize research findings, explore philosophical arguments, investigate consciousness/cognition, study computability/decidability/Turing machines, or analyze academic debates. Triggers on: 'research papers', 'literature review', 'academic sources', 'scholarly articles', 'philosophy of mind', 'computability theory', 'neuroscience studies', 'find papers on', 'what does the research say'.
Create clear action plans with steps, success criteria, and risk awareness. Use before implementing features, making changes, starting projects, or anytime you need a roadmap to success. Triggers on "plan this", "how should we approach", "what's the strategy", "steps to complete", or when facing complex multi-step work.
Add keyboard navigation to a feature using CommandRegistryService. Use when implementing keyboard shortcuts, vim-style navigation, or hotkeys for a page or component.
基于 SOC 职业分类
正在显示 SKILL.md
| name | template-generator |
| description | Generate workflow templates with coherent node graphs and integration tests |
Generate workflow templates: discover nodes, design graphs, wire edges correctly, create tests.
sourceOutput → targetInput (port names must match exactly)Directory structure:
apps/api/src/nodes/
├── input/ # TextInputNode, ImageInputNode, NumberInputNode...
├── preview/ # TextPreviewNode, ImagePreviewNode, NumberPreviewNode...
├── text/ # Summarization, translation, sentiment
├── image/ # Generation, manipulation
├── audio/ # Processing, transcription
├── anthropic/ # Claude models
├── openai/ # GPT models
├── logic/ # ConditionalForkNode, ConditionalJoinNode
└── ... # json/, math/, fetch/, browser/, etc.
Search commands:
Grep pattern="translate" path="apps/api/src/nodes" glob="*.ts"
Glob pattern="apps/api/src/nodes/text/*.ts"
Read node interface - look for nodeType.inputs and nodeType.outputs:
Read file_path="apps/api/src/nodes/text/bart-large-cnn-node.ts"
Key fields: inputs[].name → targetInput, outputs[].name → sourceOutput
The type field defines how the workflow is triggered:
| Type | Description | Entry Node |
|---|---|---|
manual | User-initiated via UI/API | Input nodes (TextInputNode, etc.) |
email_message | Triggered by incoming email | ReceiveEmailNode |
http_request | Triggered by HTTP request (sync) | HttpRequestNode |
http_webhook | Triggered by webhook (async) | HttpRequestNode |
scheduled | Triggered on schedule (cron) | ReceiveScheduledTriggerNode |
queue_message | Triggered by queue message | ReceiveQueueMessageNode |
Finding trigger-compatible nodes: Nodes declare which triggers they work with via the compatibility field in their nodeType. Search for compatible nodes:
Grep pattern="compatibility:.*email_message" path="apps/api/src/nodes" glob="*.ts"
Grep pattern="compatibility:.*http_request" path="apps/api/src/nodes" glob="*.ts"
File: apps/api/src/templates/{template-id}.ts
import type { WorkflowTemplate } from "@dafthunk/types";
import { TextInputNode } from "../nodes/input/text-input-node";
import { BartLargeCnnNode } from "../nodes/text/bart-large-cnn-node";
import { TextPreviewNode } from "../nodes/preview/text-preview-node";
export const myTemplate: WorkflowTemplate = {
id: "my-template",
name: "My Template",
description: "What it does",
icon: "file-text",
type: "manual",
tags: ["text", "ai"],
nodes: [
TextInputNode.create({
id: "text-to-process",
name: "Text to Process",
position: { x: 100, y: 100 },
inputs: { value: "Sample text...", rows: 4 },
}),
BartLargeCnnNode.create({
: ,
: ,
: { : , : },
}),
.({
: ,
: ,
: { : , : },
}),
],
: [
{ : , : , : , : },
{ : , : , : , : },
],
};
Positioning: Inputs at x:100, processing at x:500, outputs at x:900. Stack vertically with 200px spacing.
Naming: IDs are kebab-case (text-to-translate). Names are short Title Case, omit "Preview" for outputs.
ConditionalForkNode - splits flow based on boolean:
condition (boolean), value (any)true, false (only ONE has value)ConditionalJoinNode - merges exclusive branches:
a, b (exactly ONE must have value)result[BooleanInput] ──condition──► [Fork] ──true──► [ProcessorA] ──►┐
[TextInput] ────value──────► ──false─► [ProcessorB] ──►├─► [Join] ──► [Preview]
Register in apps/api/src/templates/index.ts:
import { myTemplate } from "./my-template";
export const workflowTemplates = [..., myTemplate];
Test file {template-id}.integration.ts:
describe("My Template", () => {
it("should have valid structure", () => {
expect(myTemplate.nodes).toHaveLength(3);
expect(myTemplate.edges).toHaveLength(2);
const nodeIds = new Set(myTemplate.nodes.map(n => n.id));
for (const edge of myTemplate.edges) {
expect(nodeIds.has(edge.source)).toBe(true);
expect(nodeIds.has(edge.target)).toBe(true);
}
});
});
Run: pnpm typecheck && pnpm --filter '@dafthunk/api' test {template-id}
| Output | Compatible Inputs |
|---|---|
| string | string, any |
| number | number, any |
| boolean | boolean, any |
| image | image, blob, any |
| audio | audio, blob, any |
| json | json, any |