Iterate

This is about building self-correcting workflows instead of hoping your prompts work on the first try. You define quality criteria with weights and thresholds, pick an evaluator type (rule-based, cross-model, human-in-the-loop), then set up a correction loop that feeds specific feedback back into retries. The key insight is that retries must include the evaluator's feedback, not just run the same input again. It includes regression detection against golden test sets and production monitoring patterns. If you're building anything where output quality matters and you need more than crossing your fingers, this gives you the scaffolding to make it converge reliably.

skills.sh installs: 341
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill iterate --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 feedback-loops reference in the agent-workflow skill for evaluation patterns and self-correction strategies.

Set up feedback loops that make workflows self-correcting and continuously improving. Iteration transforms one-shot gambles into convergent, reliable systems.

Feedback Loop Design

Step 1: Define Quality Criteria

What does "good output" look like? Score dimensions:

Dimension	Weight	Threshold	Measurement
Accuracy	0.4	≥ 0.8	Factual correctness check
Completeness	0.3	≥ 0.7	Required fields present
Format	0.2	≥ 0.9	Schema compliance
Tone	0.1	≥ 0.6	Appropriate for audience