agentleFS
terrene-foundationterrene-foundation/pact/.claude/skills/08-nodes-reference/SKILL.md

nodes-reference

Skill0 starsChanged 7 months agoApache-2.0View on GitHub

Comprehensive node reference documentation for all 110+ Kailash SDK nodes organized by category: AI, API, Code, Data, Database, File, Logic, Monitoring, Admin, Transaction, and Transform nodes. Use when asking about 'node reference', 'available nodes', 'node list', 'AI nodes', 'API nodes', 'code nodes', 'data nodes', 'database nodes', 'file nodes', 'logic nodes', 'monitoring nodes', 'transaction nodes', 'transform nodes', 'which nodes', 'node documentation', or 'node capabilities'.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All nodes follow the canonical 4-parameter pattern from /01-core-sdk:

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Kailash Nodes - Complete Reference

Comprehensive reference for all 110+ workflow nodes in Kailash SDK, organized by category.

Quick Access

  • nodes-quick-index - Quick node lookup index

By Category

CategoryFileKey Nodes
AI & MLnodes-ai-referenceLLMNode, AnthropicNode, OpenAINode, VisionNode, AudioNode, EmbeddingNode, OllamaNode
API & Integrationnodes-api-referenceHTTPRequestNode, WebhookNode, GraphQLNode
Code Executionnodes-code-referencePythonCodeNode, JavaScriptNode, BashNode
Data Processingnodes-data-referenceCSVReaderNode, JSONParserNode, DataValidatorNode, FilterNode, MapNode
Databasenodes-database-referenceSQLQueryNode, AsyncSQLNode, DatabaseReadNode (+ DataFlow auto-generated)
File Operationsnodes-file-referenceFileReaderNode, FileWriterNode, FileWatcherNode, ZipNode
Logic & Controlnodes-logic-referenceSwitchNode, IfElseNode, LoopNode, MergeNode, SplitNode, CycleNode
Monitoringnodes-monitoring-referenceLoggerNode, MetricsNode, AlertNode, HealthCheckNode
Adminnodes-admin-referenceConfigNode, SecretManagerNode, SchedulerNode, CacheNode
Transactionsnodes-transaction-referenceTransactionBeginNode, SagaNode, TwoPhaseCommitNode
Transformnodes-transform-referenceMapperNode, AggregatorNode, EnrichNode, NormalizeNode

Node Selection by Use Case

TaskRecommended Node
Text generationLLMNode, OpenAINode, AnthropicNode
Vision / AudioVisionNode, AudioNode
Local LLMsOllamaNode
REST APIsHTTPRequestNode
Webhooks / GraphQLWebhookNode, GraphQLNode
Custom Python logicPythonCodeNode (most flexible)
Database CRUDDataFlow auto-generated nodes (not raw DB nodes)
CSV / JSON / XMLCSVReaderNode, JSONParserNode, XMLParserNode
File read / writeFileReaderNode, FileWriterNode
Conditional routingSwitchNode, IfElseNode
Loops / cyclesLoopNode, CycleNode
Logging / metricsLoggerNode, MetricsNode

Critical Node Patterns

All nodes follow the canonical 4-parameter pattern from /01-core-sdk:

workflow.add_node("PythonCodeNode", "node1", {"code": "result = input_data * 2"})
workflow.add_connection("node1", "result", "node2", "input_data")

CRITICAL Gotchas

RuleWhy
NEVER use raw database nodesUse DataFlow instead
ALWAYS use string-based node IDsVariables cause issues
NEVER forget .build()Required before execution

Related Skills

  • 01-core-sdk - Core workflow patterns
  • 06-cheatsheets - Node usage patterns
  • 07-development-guides - Custom node development
  • 02-dataflow - Auto-generated database nodes

Support

  • pattern-expert - Node pattern recommendations
  • dataflow-specialist - DataFlow-generated nodes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.