This is the antidote to over-engineering. It catches you when you've built a six-agent pipeline for what should be a single prompt, or abstracted a config system before writing any actual features. The best part is the Complexity Test: four questions that force you to justify every component, especially "would removing this break anything?" It's opinionated about what not to cut (error handling, logging, your golden test set) and what usually goes first (premature optimization, abstraction layers with one implementation). Pairs well with evaluate to prove you didn't sacrifice quality while simplifying. Honestly, most teams should run this before their first demo.

skills.sh installs
336
GitHub stars
602
last updated
Aug 21, 2026

Install

$ npx -y skills add sharpdeveye/maestro --skill temper --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 agent-architecture reference in the agent-workflow skill for topology patterns and when multi-agent is justified.


Pull back from over-engineering. The most common mistake isn't building too little — it's building too much.

Over-Engineering Detection

Signs you've over-engineered:

  • Multi-agent for a single-agent problem
  • Premature optimization before you have performance data
  • Abstraction layers with one implementation
  • Configuration for things that never change
  • Evaluation loops on non-critical outputs
  • Framework before features

The Complexity Test

For each component:

  1. Is this solving a problem we actually have? (not "might have")
  2. Is this the simplest solution that works?
  3. Would removing this break anything? (if not, remove it)
  4. Can someone new understand this in 5 minutes? (if not, simplify)

Tempering Strategies

Collapse Unnecessary Agents

Sponsors

Details

Repository
github.com/sharpdeveye/maestro
Category
Automation & Workflows
First seen
Jun 3, 2026

More from sharpdeveye/maestro

All 22
1tech-leads-club avatarmermaid-studiotech-leads-club/agent-skillsExpert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AW335skills.sh installs
2casper-studios avatardata-analysiscasper-studios/casper-marketplaceData analysis, visualization, and storytelling skill for financial and RevOps contexts. Use when: analyzing revenue data, building forecasts, cohort analysis, c333skills.sh installs
3secondsky avatarbun-workerssecondsky/claude-skillsUse for Web Workers in Bun, worker_threads, parallel processing, and background tasks.333skills.sh installs
4jdrhyne avatargoogle-adsjdrhyne/agent-skillsQuery, audit, and optimize Google Ads campaigns. Supports two modes: (1) API mode for bulk operations with the google-ads Python SDK, (2) attached-browser mode 331skills.sh installs
5el-feo avatartailscaleel-feo/ai-contextComprehensive Tailscale VPN setup, configuration, and management for mesh networking, secure access, and zero-trust infrastructure. Covers installation, CLI com327skills.sh installs
6incept5 avatareve-skill-distillationincept5/eve-skillpacksDistill repeated work into Eve skillpacks by creating or updating skills with concise instructions and references. Use when a workflow repeats or knowledge shou327skills.sh installs