Adapt Workflow

This handles the annoying work of moving a workflow between AI providers, model tiers, or deployment contexts. It walks you through a systematic assessment of what actually changes (prompt formats, context windows, API differences, compliance requirements) and makes sure you don't forget the boring stuff like updating cost estimates and guardrails. The adaptation checklist is practical, covering everything from provider APIs to monitoring thresholds. Worth noting that it requires you to run agent-workflow first to load the context gathering protocol, which makes sense but adds a step. Most useful when you're migrating something production-grade rather than a quick prototype, since it really focuses on the operational details that break in translation.

skills.sh installs: 333
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill adapt-workflow --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. Additionally gather: what the workflow is being adapted to.

Adapt a working workflow for a different context.

Adaptation Assessment

Dimension	Current	Target	Impact
Model provider	?	?	Prompt format, capabilities, pricing
Model tier	?	?	Context window, reasoning ability
Deployment env	?	?	Latency, availability, compliance
Team structure	?	?	Monitoring, escalation, ownership
Data sensitivity	?	?	Guardrails, logging, access controls

Provider Adaptation

Prompt format: Adjust for provider-specific features
Context limits: Resize context budget for different window sizes
Capability gaps: Identify features available in one provider but not another
Pricing model: Recalculate cost estimates
API differences: Update tool calling interfaces, error handling, retry logic