skill-composition

name	skill-composition
description	Skill composition and chaining: design multi-skill workflows, chain skill outputs as inputs, build reusable skill pipelines, and orchestrate complex tasks from atomic skill building blocks

Skill Composition & Chaining

When to activate

• Building complex workflows that require multiple skills in sequence
• When a single skill cannot handle the full task scope
• Designing reusable skill pipelines for recurring multi-step processes
• Orchestrating skills across different domains (e.g., design → code → test → deploy)
• When skill outputs need to feed into downstream skills as structured inputs

When NOT to use

• Single-purpose tasks that one skill handles completely
• Simple sequential commands that don't need state passing between steps
• When the workflow is ad-hoc and unlikely to recur

Instructions

1. Skill Composition Patterns

Sequential Pipeline (Linear Chain):

Skill A → output → Skill B → output → Skill C → final output

Use when each step depends on the previous step's output.

Fan-Out / Fan-In (Parallel + Merge):

         ┌→ Skill B ─┐
Skill A ─┤→ Skill C ─├→ Skill E (merge)
         └→ Skill D ─┘

Use when independent analyses can run in parallel before merging.

Conditional Branching:

Skill A → router → Skill B (if condition X)
                  → Skill C (if condition Y)

Use when the next skill depends on the output of the previous one.

Recursive / Iterative:

Skill A → evaluate → Skill A (refine) → evaluate → done

Use when output quality improves with iteration (e.g., write → review → revise).