decision

Record quest decisions with verdicts, reasons, and next steps.

2|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/Rycen7822/DeepScientist-hermes --skill decision-rycen7822
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision
Source: https://github.com/Rycen7822/DeepScientist-hermes/tree/main/resources/skills/decision
Command: npx skills add https://github.com/Rycen7822/DeepScientist-hermes --skill decision-rycen7822

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill coordinates when a quest should continue, branch, reuse a baseline, write, finalize, reset, or stop, with explicit justification and evidence.

Core Features & Use Cases

  • Cross-stage decision discipline to determine the best next action based on current evidence and quest state.
  • Structured recording of verdicts, actions, reasons, evidence paths, and next steps, enabling durable traceability.
  • Supports autonomous policies or user-guided decisions while respecting runtime contracts and safety constraints.

Quick Start

Provide the current quest state and recommended next action, with rationale and any required follow-up steps.

Frequently Asked Questions about decision

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

FAQPage Schema
How do I determine whether to continue, branch, or stop a workflow quest based on current evidence?

When evidence is mixed or the path is not obvious, workflow branching evaluates current evidence and constraints to determine the next action. It applies when user input is required or autonomous governance policies need explicit justification.

How do I record a workflow governance decision to ensure traceability across stages?

You record a governance decision by documenting the verdict, action, reason, evidence path, and next steps as a durable artifact. This structured recording enables cross-stage traceability and coordinates future quest states based on current evidence.

Can I use autonomous policies for quest branching, or does it require user-guided decisions?

Quest branching supports both autonomous policies and user-guided decisions. It respects runtime contracts and safety constraints while determining whether to continue, reuse a baseline, finalize, reset, or stop the quest based on documented evidence.

What are the limitations of using a decision artifact for mixed evidence in a quest?

A decision artifact requires explicit evidence paths and documented reasons to finalize or branch a quest. It is limited when current constraints are undocumented or when runtime contracts prevent autonomous governance actions without user input.