agentleFS
terrene-foundationterrene-foundation/pact/.claude/skills/07-development-guides/SKILL.md

development-guides

Skill0 starsChanged 7 months agoApache-2.0View on GitHub

Comprehensive development guides for advanced Kailash SDK features including custom node development, MCP development, async patterns, testing strategies, production deployment, RAG systems, security patterns, monitoring, and SDK internals. Use when asking about 'development guide', 'advanced features', 'custom node development', 'async node development', 'MCP development', 'production deployment', 'testing strategies', 'RAG implementation', 'security patterns', 'monitoring setup', 'circuit breaker', 'compliance', 'edge computing', or 'SDK internals'.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    [test-organization](test-organization.md): - Test organization strategies

    line 53
  2. Distinctive:

    Use this skill when you need:

    line 130

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Patterns - Development Guides

Comprehensive guides for advanced Kailash SDK development, covering custom development, production deployment, testing, and enterprise features.

Overview

In-depth guides for:

  • Custom node and workflow development
  • Advanced SDK features
  • Production deployment strategies
  • Comprehensive testing approaches
  • Enterprise security and compliance
  • Monitoring and observability
  • SDK internals and architecture

Core Development

SDK Fundamentals

  • sdk-fundamentals - Core SDK concepts and architecture
  • sdk-essentials - Essential SDK patterns
  • feature-discovery - Discovering SDK features
  • advanced-features - Advanced SDK capabilities

Custom Development

  • custom-development - Custom component development
  • async-node-development - Building async nodes
  • node-execution-internals - Node execution mechanics
  • parameter-passing-comprehensive - Advanced parameter patterns

Workflow Development

  • workflow-creation-guide - Complete workflow creation guide
  • cyclic-guide-comprehensive - Comprehensive cyclic workflow guide
  • intelligent-query-routing - Query routing strategies

MCP Development

MCP Implementation

  • mcp-development - MCP server development
  • mcp-advanced-features - Advanced MCP features
  • mcp-tool-execution - MCP tool patterns
  • mcp-transport-layers - Transport implementation
  • resource-registry - MCP resource management

Testing & Quality

Testing Strategies

  • testing-best-practices - Testing best practices
  • test-organization - Test organization strategies
  • production-testing - Production testing approaches
  • regression-testing - Regression testing patterns

Production & Operations

Deployment

  • production-deployment-guide - Production deployment guide
  • edge-computing - Edge deployment patterns
  • durable-gateway - Durable gateway patterns

Monitoring & Observability

  • monitoring-enterprise - Enterprise monitoring
  • metrics-collection - Metrics and telemetry

Resilience

  • resilience-enterprise - Enterprise resilience patterns
  • circuit-breaker - Circuit breaker implementation

Enterprise & Security

Security

  • security-patterns-enterprise - Enterprise security patterns
  • compliance-patterns - Compliance and governance

AI & RAG

RAG Development

  • rag-comprehensive - Comprehensive RAG guide

Quick Patterns

Custom Node Development

from kailash.nodes.base import BaseNode

class CustomNode(BaseNode):
    def execute(self, inputs: dict) -> dict:
        # Process inputs
        result = self.process(inputs.get("data"))
        return {"output": result}

Async Node Pattern

from kailash.nodes.base import AsyncBaseNode

class AsyncCustomNode(AsyncBaseNode):
    async def execute_async(self, inputs: dict) -> dict:
        result = await self.async_process(inputs)
        return {"output": result}

MCP Server Setup

from kailash.mcp.server import MCPServer

server = MCPServer()

@server.tool("my_tool")
async def my_tool(param: str) -> str:
    return f"Processed: {param}"

server.start()

CRITICAL Warnings

RuleReason
❌ NEVER override __init__ without super().__init__()Breaks node initialization
✅ ALWAYS handle errors in async nodesPrevents hanging
❌ NEVER use blocking I/O in async nodesBlocks event loop
✅ ALWAYS register MCP tools before startRequired for discovery

When to Use This Skill

Use this skill when you need:

  • In-depth understanding of SDK features
  • Custom node or workflow development guidance
  • Production deployment strategies
  • Comprehensive testing approaches
  • MCP server implementation details
  • Enterprise security patterns
  • Monitoring and observability setup
  • RAG system implementation
  • Advanced async patterns

Related Skills

  • 01-core-sdk - Core SDK fundamentals
  • 06-cheatsheets - Quick reference patterns
  • 08-nodes-reference - Node reference
  • 17-gold-standards - Best practices

Support

For development guide questions, invoke:

  • pattern-expert - Implementation patterns and workflows
  • testing-specialist - Testing strategies and best practices
  • release-specialist - Production deployment guidance
  • mcp-specialist - MCP server development

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.