skills-composition

Compose multiple agent skills into orchestrated workflows with HITL gates.

15|2|Updated Dec 13, 2025
One-click install
npx skills add https://github.com/d-padmanabhan/agent-engineering-handbook --skill skills-composition
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skills-composition
Source: https://github.com/d-padmanabhan/agent-engineering-handbook/tree/main/skills/skills-composition
Command: npx skills add https://github.com/d-padmanabhan/agent-engineering-handbook --skill skills-composition

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents messy, fragile agent workflows by standardizing how to chain multiple skills with clear contracts, optional dependencies, and user confirmation for risky phases.

Core Features & Use Cases

  • Chaining patterns: Build multi-step slash command workflows where outputs feed subsequent skills (or run in parallel when independent).
  • Scope resolution: Prefer project-scoped skills over personal ones using Cursor/Cline discovery order to avoid surprises.
  • Graceful degradation: Automatically detect sibling/optional skills and skip them when absent instead of failing the whole workflow.
  • HITL gates: Insert human-in-the-loop prompts before expensive, irreversible, or scope-expanding steps.
  • Error handling & contracts: Pass parameters explicitly and ensure one phase’s failure doesn’t corrupt earlier artifacts.
  • Decision guidance: Decide whether to create a new skill vs extend an existing one to reduce skill sprawl.

Quick Start

Ask the agent to design a slash command workflow that composes web-research-kb-refresh, technology-consolidation-analysis, and an optional consolidation-dashboard with a HITL confirmation before refreshing the knowledge base.

Frequently Asked Questions about skills-composition

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I chain multiple agent skills into a single workflow without breaking when one fails?

Workflow composition standardizes how to chain multiple agent skills with clear contracts and explicit error handling. This approach ensures that a missing optional sibling skill is skipped automatically instead of corrupting earlier artifacts or failing the entire workflow.

What is the best way to add human-in-the-loop confirmation gates to multi-phase slash command workflows?

Standardized workflow composition inserts human-in-the-loop gates before expensive, irreversible, or scope-expanding phases in multi-phase slash command workflows. This maintains predictable execution and safe user confirmation across sequentially chained agent skills.

How do I resolve scope conflicts between project and personal agent skills during workflow orchestration?

Workflow orchestration resolves scope conflicts by preferring project-scoped skills over personal ones using standard discovery order. This prevents execution surprises by ensuring the correct skill version runs during multi-phase agent workflow composition.

Does workflow composition support parallel execution for independent agent skills?

Yes, workflow composition supports parallel execution for independent agent skills. It standardizes parameter passing alongside sequential and parallel chaining patterns to maintain predictable, maintainable orchestrated workflows.

When should I extend an existing agent skill versus creating a new one to avoid skill sprawl?

Workflow composition provides decision guidance to evaluate extending an existing skill versus creating a new one. Applying the one-skill-one-capability principle reduces skill sprawl and maintains clear contracts within orchestrated agent workflows.