Stops you from building the wrong thing by forcing a complexity check before you start coding. Blocks tasks with more than 3 unanswered questions, missing dependencies, or when you've failed the same approach 3 times. The YAGNI gate is interesting: it calculates a justified complexity ratio and blocks you if you're building something twice as complex as your project tier needs. Plugs into the context system to track attempts and gate status across sessions. The pattern library that learns from past mistakes is smart, though it needs a few projects before the confidence scores mean much. Heavy on process, but if you've ever spent a day implementing the wrong solution because requirements were fuzzy, you'll get why this exists.

skills.sh installs
259
GitHub stars
301
last updated
Aug 21, 2026

Install

$ npx -y skills add yonatangross/orchestkit --skill quality-gates --agent claude-code

Installs into .claude/skills of the current project.

Files

Quality Gates

This skill teaches agents how to assess task complexity, enforce quality gates, and prevent wasted work on incomplete or poorly-defined tasks.

Key Principle: Stop and clarify before proceeding with incomplete information. Better to ask questions than to waste cycles on the wrong solution.


Overview

Auto-Activate Triggers

  • Receiving a new task assignment
  • Starting a complex feature implementation
  • Before allocating work in Squad mode
  • When requirements seem unclear or incomplete
  • After 3 failed attempts at the same task
  • When blocked by dependencies

Manual Activation

  • User asks for complexity assessment
  • Planning a multi-step project
  • Before committing to a timeline

Core Concepts

Complexity Scoring (1-5 Scale)

Sponsors

Details

Repository
github.com/yonatangross/orchestkit
Category
Code Review & Quality
First seen
Jun 3, 2026

More from yonatangross/orchestkit

All 61
1accesslint avatarrefactoraccesslint/claude-marketplacerefactor257skills.sh installs
2mhattingpete avatarreview-implementingmhattingpete/claude-skills-marketplaceProcess and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement sugges256skills.sh installs
3cloudai-x avatardesigning-architecturecloudai-x/claude-workflow-v2Designs software architecture and selects appropriate patterns for projects. Use when designing systems, choosing architecture patterns, structuring projects, m249skills.sh installs
4longranger2 avatarplan-reviewlongranger2/claude-gpt-workflowUse when the user says "/plan-review", "plan review", or "PRD review" and provides a plan file path that needs critical review and iterative refinement with Cod247skills.sh installs
5rysweet avatarpm-architectrysweet/amplihackExpert project manager orchestrating backlog-curator, work-delegator, workstream-coordinator, and roadmap-strategist sub-skills. Coordinates complex software pr245skills.sh installs
6sickn33 avatarperformance-testing-review-ai-reviewsickn33/antigravity-awesome-skillsperformance testing review ai review244skills.sh installs