OpenParable
Skip to content
← Back to skills

Middleware Chain Designer

Development
middleware-chain-designer

Middleware Chain Designer is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Design middleware and interceptor chains for SDK extensibility

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/sdk-platform-development/skills/middleware-chain-designer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/middleware-chain-designer, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Middleware Chain Designer Skill

Overview

This skill designs middleware and interceptor chain architectures that enable SDK extensibility through pluggable request/response processing.

Capabilities

  • Design middleware interfaces and contracts
  • Implement interceptor chains with ordering
  • Support before/after hooks for requests
  • Enable custom transport implementations
  • Implement retry and circuit breaker middleware
  • Design logging and tracing interceptors
  • Support middleware composition
  • Configure middleware priority ordering

Target Processes

  • Plugin and Extension Architecture
  • Custom Transport and Middleware
  • SDK Architecture Design

Integration Points

  • SDK core HTTP clients
  • Authentication handlers
  • Logging frameworks
  • Retry libraries
  • Custom transports

Input Requirements

  • Extensibility requirements
  • Middleware ordering needs
  • Hook types required
  • Composition patterns
  • Transport abstraction needs

Output Artifacts

  • Middleware interface definitions
  • Interceptor chain implementation
  • Built-in middleware (logging, retry)
  • Transport abstraction layer
  • Middleware composition utilities
  • Documentation and examples

Usage Example

skill:
  name: middleware-chain-designer
  context:
    middlewareTypes:
      - request
      - response
      - error
    hooks:
      beforeRequest: true
      afterResponse: true
      onError: true
    builtInMiddleware:
      - logging
      - retry
      - timeout
      - compression
    ordering:
      priority: true
      named: true
    transports:
      - http
      - websocket
      - custom

Best Practices

  1. Define clear middleware interfaces
  2. Support ordered execution
  3. Enable middleware composition
  4. Provide built-in common middleware
  5. Allow transport customization
  6. Document middleware authoring