Verified:GitHub

classifying-actions

Classify mutating actions as auto-execute, require approval, or never using decision matrices and overrides.

2|Updated Apr 24, 2026

Search Tags:#autonomy #overrides #architecture-governance #decision-table #board-superpowers #mutating-actions #triage-rule

Ready to run

npx skills add https://github.com/PanQiWei/board-superpowers --skill classifying-actions

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: classifying-actions
Source: https://github.com/PanQiWei/board-superpowers/tree/main/skills/classifying-actions
Command: npx skills add https://github.com/PanQiWei/board-superpowers --skill classifying-actions

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

## What problem does it solve? This skill provides a governance mechanism to decide whether mutating actions in board-superpowers should auto-execute or wait for architect approval, ensuring safe and auditable changes to cards, PRs, configs, and credentials.

## Core Features & Use Cases

Decision-table authority for every mutating action.
5-step triage rule to escalate Auto actions when needed.
Dual-layer overrides (user and project) with project layer precedence.
Uses matrix.md and action-id catalogs to derive final autonomy class.

Quick Start

Provide an action_id and repo_root to obtain the final autonomy class (A, R, or N) after applying default matrix, triage rules, and overrides.

Frequently Asked Questions about classifying-actions

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

FAQPage Schema

How do I determine if a mutating action should auto-execute or require architect approval?▼

To classify mutating actions for auto-execution or architect approval, provide an action_id and repository root to apply a 5-step triage rule and decision matrix, returning an effective autonomy class of A, R, or N.

How do user and project autonomy overrides interact when classifying board-superpowers actions?▼

Autonomy overrides for classifying board-superpowers actions use a dual-layer system where project-layer overrides take precedence over user-layer overrides during conflicts to compute the final action class.

What happens when parsing fails during a mutating-action triage decision?▼

When parsing fails during a mutating-action triage decision, the classification applies a conservative fallback to ensure safe governance, defaulting to a restrictive autonomy class rather than auto-executing.

What inputs do I need to start triaging mutating actions for governance decisions?▼

To start triaging mutating actions for governance decisions, you need to provide a valid action_id and a repository root path to consult the action catalogs and derive the final class.

Can I escalate an auto-action to require architect approval using triage rules?▼

Yes, you can escalate Auto actions to require architect approval by applying the 5-step triage rule, which evaluates specific conditions to override the default decision matrix classification.

What is the decision matrix used for governing mutating actions in repositories?▼

The decision matrix serves as a rulebook authority for governing mutating actions, using matrix.md and action-id catalogs to derive the final autonomy class for safe and auditable repository changes.