Chain

This is your orchestration layer for complex multi-step workflows. It forces you to map out sequential, parallel, conditional, or iterative tool chains with explicit data contracts between each step. The real value is in the structure: you define exactly what each tool consumes and produces, how failures propagate, and where retry logic kicks in. The mandatory prep step pulls in workflow principles and makes you think through error handling before you start chaining tools together. Useful when you're building pipelines that need to survive real world failures, not just happy path demos. The validation checklist alone will save you from the classic mistake of assuming step N output magically fits step N+1 input.

skills.sh installs: 339
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill chain --agent claude-code

Installs into .claude/skills of the current project.

Files

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the tool-orchestration reference in the agent-workflow skill for composition patterns and error handling.

Design tool chains that do complex work reliably. A chain is only as strong as its weakest link.

Chain Patterns

Sequential: A → B → C (each step depends on the previous) Parallel: [A, B, C] → Merge (independent steps run simultaneously) Conditional: A → (if X then B, else C) → D (branching based on results) Iterative: A → Check → (if not done) → A again (loop until convergence)

Chain Design Process

For each chain, define:

## Chain: [Name]

### Steps
1. [Tool A] — [what it does] — Input: [schema] — Output: [schema]
2. [Tool B] — [what it does] — Input: [output of step 1] — Output: [schema]
3. [Tool C] — [what it does] — Input: [output of step 2] — Output: [schema]

### Data Flow
Step 1 output.field_a → Step 2 input.source_data
Step 2 output.results → Step 3 input.items

SKILL.md on GitHub