
Amplify
When your workflow works but hits limits on edge cases or output quality, this skill walks you through targeted upgrades. It's structured around four strategies: better prompts (few-shot examples, chain-of-thought), better tools (new capabilities, verification steps), better context (RAG, real-time data), or better models (upgrading for critical steps). The impact assessment table showing cost versus latency versus quality tradeoffs is genuinely useful. The core discipline here is amplifying one thing at a time with before-and-after measurements, which prevents the common mistake of throwing everything at a problem and not knowing what actually helped. Requires the agent-workflow skill as a dependency.
- skills.sh installs
- 344
- GitHub stars
- 602
- last updated
- Aug 21, 2026
Install
$ npx -y skills add sharpdeveye/maestro --skill amplify --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. Consult the tool-orchestration reference in the agent-workflow skill for adding tools effectively.
Take a working workflow and make it more capable. Amplification adds new abilities without breaking existing functionality.
Amplification Strategies
Better Prompts
- Add few-shot examples for edge cases the model currently mishandles
- Add chain-of-thought for tasks where reasoning quality matters
- Add negative instructions for common mistakes
- Upgrade output schema with more structured fields
Better Tools
- Add tools for capabilities the model currently lacks
- Improve existing tool descriptions for better selection accuracy
- Add confirmation steps for high-stakes operations
- Add tools for verification/validation of outputs
Better Context
Sponsors
Details
- Repository
- github.com/sharpdeveye/maestro
- Categories
- Code Review & Quality, Automation & Workflows
- First seen
- Jun 3, 2026