node-catalog — for Claude Code node-catalog, emerald, community, for Claude Code, ide skills, trigger:manual, trigger:cron, trigger:webhook, trigger:channel_message, action:http

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need use this skill when the task is to identify which node types fit a pipeline step. 本地化技能摘要: Single binary agentic node-based automation tool Use this skill when the task is to identify which node types fit a pipeline step. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Use this skill when the task is to identify which node types fit a pipeline step.
Start From Node Families
Triggers start flows:
trigger:channel message
Actions run on the normal execution path:

# 核心主题

FlameInTheDark FlameInTheDark
[0]
[0]
更新于: 4/11/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
45
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need use this skill when the task is to identify which node types fit a pipeline step. 本地化技能摘要: Single binary agentic node-based automation tool Use this skill when the task is to identify which node types fit a pipeline step. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: node-catalog helps agents use this skill when the task is to identify which node types fit a pipeline step. Single binary agentic node-based automation tool Use this skill when the task is to identify which node

适用 Agent 类型

适用场景: Ideal for AI agents that need use this skill when the task is to identify which node types fit a pipeline step.

赋予的主要能力 · node-catalog

适用任务: Applying Use this skill when the task is to identify which node types fit a pipeline step
适用任务: Applying Start From Node Families
适用任务: Applying Triggers start flows:

! 使用限制与门槛

  • 限制说明: Use logic:limit to keep only the first N items from an array at inputPath.
  • 限制说明: Use logic:limit to keep only the first N items from an array at inputPath
  • 限制说明: Requires repository-specific context from the skill documentation

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

node-catalog 是什么?

适用场景: Ideal for AI agents that need use this skill when the task is to identify which node types fit a pipeline step. 本地化技能摘要: Single binary agentic node-based automation tool Use this skill when the task is to identify which node types fit a pipeline step. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 node-catalog?

运行命令:npx killer-skills add FlameInTheDark/emerald/node-catalog。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

node-catalog 适用于哪些场景?

典型场景包括:适用任务: Applying Use this skill when the task is to identify which node types fit a pipeline step、适用任务: Applying Start From Node Families、适用任务: Applying Triggers start flows:。

node-catalog 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

node-catalog 有哪些限制?

限制说明: Use logic:limit to keep only the first N items from an array at inputPath.;限制说明: Use logic:limit to keep only the first N items from an array at inputPath;限制说明: Requires repository-specific context from the skill documentation。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add FlameInTheDark/emerald/node-catalog。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    node-catalog 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

node-catalog

Single binary agentic node-based automation tool Use this skill when the task is to identify which node types fit a pipeline step. This AI agent skill

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Use this skill when the task is to identify which node types fit a pipeline step.

Start From Node Families

  • Triggers start flows:
    • trigger:manual
    • trigger:cron
    • trigger:webhook
    • trigger:channel_message
  • Actions run on the normal execution path:
    • action:http
    • action:shell_command
    • action:lua
    • action:pipeline_get
    • action:pipeline_run
  • Logic nodes shape control flow and returned data:
    • logic:condition
    • logic:switch
    • logic:merge
    • logic:aggregate
    • logic:sort
    • logic:limit
    • logic:remove_duplicates
    • logic:summarize
    • logic:return
  • LLM nodes handle prompting and agents:
    • llm:prompt
    • llm:agent
  • Tool nodes are callable helpers for llm:agent:
    • tool:http
    • tool:shell_command
    • tool:pipeline_list
    • tool:pipeline_get
    • tool:pipeline_create
    • tool:pipeline_update
    • tool:pipeline_delete
    • tool:pipeline_run

Know The Most Important Execution Patterns

  • Use action:http for direct HTTP requests in the main flow.
  • Use action:shell_command for local shell execution in the main flow.
  • Use action:lua for compact custom transformations when built-in transform nodes are not enough.
  • Use action:pipeline_run to call another pipeline from the normal execution path.
  • Use logic:return when the pipeline should produce a structured result for callers or for inspection.
  • Use llm:prompt for a single prompt/response step.
  • Use llm:agent when the model should choose and call tool nodes.

Use The Right Logic Node

  • Use logic:condition for one yes/no branch.
  • Use logic:switch for several named branches.
  • Use logic:merge to combine upstream objects into one object.
  • Use logic:aggregate to collect upstream results into arrays plus metadata.
  • Use logic:sort to sort an array at inputPath and write the result back to outputPath.
  • Use logic:limit to keep only the first N items from an array at inputPath.
  • Use logic:remove_duplicates to deduplicate an array by whole item or by one field path.
  • Use logic:summarize to compute grouped or overall metrics such as count, sum, avg, min, and max.
  • Use logic:return to stop the flow and return data.

Remember The Transformation Palette

  • In the editor, logic:merge, logic:aggregate, logic:sort, logic:limit, logic:remove_duplicates, and logic:summarize are grouped under transformation-oriented menu paths.
  • action:lua remains a general action node and is best treated as a flexible fallback when the built-in transform nodes do not fit.
  • The built-in array transform nodes clone the current payload, read an array from inputPath, and write the transformed result to outputPath so unrelated fields stay available downstream.

Remember Infrastructure Coverage

  • Infrastructure action and tool nodes also exist for Proxmox and Kubernetes.
  • Prefer reading the current pipeline snapshot before assuming which infrastructure nodes are available in use.
  • For broad pipeline construction examples and full JSON shapes, read pipeline-builder.

Favor Clear Canvas Design

  • Use explicit labels.
  • Keep ids readable and stable.
  • Keep the normal execution path visually separate from agent tool clusters.
  • Avoid adding nodes that do not change behavior.

相关技能

寻找 node-catalog 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具