Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计提醒

iii-low-code-automationiii 低代码自动化

Agent Skill

iii-low-code-automation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

222

周安装

9

GitHub Stars

15,323

下载量

70
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:iii-low-code-automation(iii 低代码自动化)
来源仓库:https://github.com/iii-hq/iii
仓库路径:skills/iii-low-code-automation
安装命令:
npx skills add https://github.com/iii-hq/iii --skill iii-low-code-automation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/iii-hq/iii --skill iii-low-code-automation

简介

iii-low-code-automation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 它可辅助梳理项目结构、追踪代码变动、管理 Issue 生命周期或生成协作摘要。
  • 通过 npx skills add 命令从指定仓库安装,具体用法请参考原始 README。
  • 使用前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Low-Code Automation Chains

Comparable to: n8n, Zapier, LangFlow

Key Concepts

Use the concepts below when they fit the task. Not every automation needs all of them.

  • Each "node" in the automation is a small registered function with a single job
  • Nodes chain via named queues using TriggerAction.Enqueue — easy to add, remove, or reorder steps
  • HTTP triggers receive external webhooks (form submissions, payment events)
  • Cron triggers start scheduled automations (daily digests, periodic syncs)
  • PubSub broadcasts completion events for downstream listeners

Architecture

Automation 1: Form → Enrich → Store → Notify
  HTTP webhook → auto::enrich-lead → auto::store-lead → auto::notify-slack

Automation 2: Cron → Fetch → Transform → Store
  Cron (daily) → auto::fetch-rss → auto::transform-articles → auto::store-articles

Automation 3: Payment webhook → Validate → Update → Notify
  HTTP webhook → auto::validate-payment → auto::update-order → publish(payment.processed)

iii Primitives Used

PrimitivePurpose
registerWorkerInitialize the worker and connect to iii
registerFunctionDefine each automation node
trigger({..., action: TriggerAction.Enqueue({queue})})Chain nodes via named queues
trigger({function_id: 'state::set', payload})Persist data between nodes
trigger({..., action: TriggerAction.Void()})Fire-and-forget notifications
registerTrigger({type: 'http'})Webhook entry points
registerTrigger({type: 'cron'})Scheduled automations

Reference Implementation

See ../references/low-code-automation.js for the full working example — three automation chains: form-to-Slack notification, RSS feed aggregation, and payment webhook processing.

Common Patterns

Code using this pattern commonly includes, when relevant:

  • registerWorker(url, {workerName}) — worker initialization
  • trigger({function_id, payload, action: TriggerAction.Enqueue({queue: 'automation'})}) — node chaining
  • Each node as its own registerFunction with auto:: prefix IDs
  • Small, focused functions that do one thing (enrich, validate, store, notify)
  • trigger({function_id: 'state::set', payload: {scope, key, value}}) — persist between nodes
  • const logger = new Logger() — structured logging per node

Adapting This Pattern

Use the adaptations below when they apply to the task.

  • Add new automation chains by registering HTTP/cron triggers and chaining functions
  • Each node should be independently testable — accept input, produce output
  • Use separate queue names when different chains need different retry/concurrency settings
  • For unreliable external services, wrap calls in try/catch and handle failures explicitly
  • Keep node functions small — offload complex logic to dedicated functions

Pattern Boundaries

  • If the task requires durable multi-step workflows with saga compensation and step tracking, prefer iii-workflow-orchestration.
  • If the task involves multiple AI agents handing off work, prefer iii-agentic-backend.
  • Stay with iii-low-code-automation when the primary concern is simple trigger-transform-action chains with minimal orchestration overhead.

When to Use

  • Use this skill when the task is primarily about iii-low-code-automation in the iii engine.
  • Triggers when the request directly asks for this pattern or an equivalent implementation.

Boundaries

  • Never use this skill as a generic fallback for unrelated tasks.
  • You must not apply this skill when a more specific iii skill is a better fit.
  • Always verify environment and safety constraints before applying examples from this skill.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.59%
按下载量换算24

Claude

29.94%
按下载量换算21

Cursor

19.72%
按下载量换算14

Gemini CLI

9.3%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills