skills.rest
2lab-ai
2lab-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

decision-gate

Evaluate code changes by switching cost to assign autonomous or user-reviewed decisions.

Updated Jul 29, 2026
Search Tags:#code review#decision-making#technical validation#switching cost#autonomous judgment
One-click install
npx skills add https://github.com/2lab-ai/soma-work --skill decision-gate-2lab-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: decision-gate
Source: https://github.com/2lab-ai/soma-work/tree/main/src/local/skills/decision-gate
Command: npx skills add https://github.com/2lab-ai/soma-work --skill decision-gate-2lab-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill streamlines decision-making for code changes by categorizing decisions into tiered levels based on switching cost, enabling automated or user-based validation.

Core Features & Use Cases

  • Tier-based Decision Making: Assesses code changes against switching cost to determine whether they should be made autonomously or reviewed by a user.
  • 3-Person Review Consensus: Ensures decisions are reviewed by three parties to minimize errors and ensure robustness.
  • Autonomous Judgment: Executes decisions that are deemed safe and have a low switching cost.
  • User Question: Involves the user for decisions with medium to high switching cost, providing detailed context and options.
  • HALT & Decompose: halts implementation for very large changes and suggests decomposition into smaller tasks.
  • Use Case: When faced with a large code change, the skill can automatically decide if it's suitable for autonomous implementation or requires user approval.

Quick Start

Analyze the proposed code change in 'new-feature.md' with the decision-gate skill.

Frequently Asked Questions about decision-gate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate decision-making for code changes based on switching cost?▼

To automate decision-making for code changes, this Skill evaluates switching cost to categorize decisions into tiered levels, executing safe changes autonomously and routing complex ones to user review. It uses Python-based algorithms to determine the appropriate validation path.

What is the best way to handle technical validation for high-impact code modifications?▼

For high-impact code modifications, technical validation is handled through a 3-person review consensus. The Skill halts autonomous execution and provides detailed context and options to ensure robust decisions and minimize errors.

Can I automatically decompose large code changes into smaller tasks?▼

Yes, you can automatically decompose large code changes. When a proposed modification has a very high switching cost, the Skill halts implementation and suggests decomposing the complex task into smaller, more manageable tasks.

When should I halt autonomous code review and involve user judgment?▼

You should halt autonomous code review and involve user judgment when a proposed change has a medium to high switching cost. The Skill triggers a user question to provide context and options for decisions that exceed safe autonomous execution.

Related Skills

Explore More Software Engineering Skills→
cloudvoyantcloudvoyant

pr-fix

Fetch open pull requests and generate proposed code fixes for unresolved review comments.

Official
Intermediate
tungnguyen10tungnguyen10

openspec-apply-change

Automate implementation of OpenSpec change tasks with progress tracking.

Community
Advanced
WecoAIWecoAI
7

weco

Automate code optimization with the Weco CLI against speed, accuracy, latency, and cost metrics.

Official
Advanced
StartaleGroupStartaleGroup
3

prepr

Analyze pull request diffs to assign review tiers and agents.

Official
Advanced