Skills Plugins MCP Prompt Model 博客 我的中心

extending-flowcraft

Customize Flowcraft runtime behavior with pluggable components. Covers serializers, evaluators, loggers, and orchestrators. Use when the user needs custom serialization, complex data types, edge condition expressions, custom logging, or alternative execution strategies.

DeepseekModel 官方收录技能 质量 优秀 · 78 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=gorango-flowcraft-packages-llm-skills-extending-flowcraft-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name extending-flowcraft description Customize Flowcraft runtime behavior with pluggable components. Covers serializers, evaluators, loggers, and orchestrators. Use when the user needs custom serialization, complex data types, edge condition expressions, custom logging, or alternative execution strategies. Extending Flowcraft The FlowRuntime can be configured with pluggable components to tailor behavior to specific needs. Extensibility Points Component Interface Purpose See Serializer ISerializer Serialize/deserialize workflow context serializers.md Evaluator IEvaluator Evaluate edge conditions and transforms evaluators.md Logger ILogger Custom logging infrastructure loggers.md Orchestrator IOrchestrator Alternative execution strategies orchestrators.md Quick Examples Custom Serializer import { ISerializer , FlowRuntime } from 'flowcraft' import superjson from 'superjson' class SuperJsonSerializer implements ISerializer { serialize ( data : Record < string , any >): string { return superjson. stringify (data) } deserialize ( text : string ): Record < string , any > { return superjson. parse (text) as Record < string , any > } } const runtime = new FlowRuntime ({ serializer : new SuperJsonSerializer () }) Custom Evaluator import { IEvaluator , FlowRuntime } from 'flowcraft' import jsep from 'jsep' class JsepEvaluator implements IEvaluator { evaluate ( expression : string , context : Record < string , any >): any { const ast = jsep (expression) return interpretAst (ast, context) // Your AST interpreter } } const runtime = new FlowRuntime ({ evaluator : new JsepEvaluator () }) Custom Logger import { ILogger , FlowRuntime } from 'flowcraft' class FileLogger implements ILogger { debug ( msg : string , meta ?: Record < string , any > ) { /* ... */ } info ( msg : string , meta ?: Record < string , any > ) { /* ... */ } warn ( msg : string , meta ?: Record < string , any > ) { /* ... */ } error ( msg : string , meta ?: Record < string , any > ) { /* ... */ } } const runtime = new FlowRuntime ({ logger : new FileLogger ( 'workflow.log' ) }) Custom Orchestrator import { IOrchestrator , FlowRuntime , StepByStepOrchestrator } from 'flowcraft' // Use step-by-step for debugging const runtime = new FlowRuntime ({ orchestrator : new StepByStepOrchestrator (), }) Advanced topics Serializers : Handle complex types like Date, Map, Set — see serializers.md Evaluators : Property access vs full expressions — see evaluators.md Loggers : Integrate with Winston, Pino, etc. — see loggers.md Orchestrators : Default, step-by-step, event-driven, resumption — see orchestrators.md
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。