
Refine
This is your final quality pass before shipping a working workflow. It runs through a comprehensive checklist covering prompts, tool descriptions, error messages, logging, and configuration, then tells you exactly what's broken, where it is, and how to fix it with a priority rating. The checklist is opinionated but practical: four-zone prompt patterns, explicit output schemas, specific error messages with corrective actions, PII redaction in logs, no magic numbers. It explicitly won't change behavior or suggest redesigns, just polish what already works. Best used after your workflow functions correctly but before you'd feel comfortable handing it to someone else. The mandatory context gathering step means it needs existing workflow state to audit against.
- skills.sh installs
- 357
- GitHub stars
- 602
- last updated
- Aug 21, 2026
Install
$ npx -y skills add sharpdeveye/maestro --skill refine --agent claude-codeInstalls 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.
This is the final quality pass. The workflow works — now make it excellent.
Refinement Checklist
Prompts
- Every prompt follows the 4-zone pattern (role, context, instructions, output)
- Output schemas are explicit and validated
- Negative instructions clarify what NOT to do
- No contradictory instructions
- Few-shot examples included for ambiguous tasks
- Chain-of-thought used for multi-step reasoning tasks
Tool Descriptions
- Every tool has a multi-line description: what, when to use, when NOT to use, returns
- Input parameters have descriptions and types
- Error responses are documented
- At least one example input/output in the description
Error Messages
Sponsors
Details
- Repository
- github.com/sharpdeveye/maestro
- Categories
- Debugging, Automation & Workflows
- First seen
- Jun 3, 2026