Automation Governance

Frameworks and tooling for evaluating AI automation readiness (Google DeepMind Intelligent AI Delegation) and auditing AI agents against W3C User Agent fiduciary duties (Protection, Honesty, Loyalty).

version from plugin.json: 1.0.0
license from plugin.json: Apache-2.0
author from plugin.json: ghchinoy · https://github.com/ghchinoy
repository from plugin.json: https://github.com/ghchinoy/agent-skills
keywords plugin keywords, from plugin.json: delegation
governance
automation-readiness
user-agents
w3c
fiduciary-duties
ethics
safety
deepmind
multi-agent
hitl
name from plugin.json: automation-governance
conformance derived from plugin.json $schema: Targets Agent Plugins 1.0.0.
source derived: plugins/automation-governance/plugin.json

Skills

Automation Readiness Evaluatorautomation-readinessEvaluates whether a skill, workflow, or process should be fully automated, partially automated with human-in-the-loop (HITL) checkpoints, or kept human-led. Implements Google DeepMind's Intelligent AI Delegation framework (arXiv:2602.11865) using an 11-axis diagnostic scorecard, hard gate vetoes, autonomy tiers, and an operational guardrail matrix. Use when deciding whether to automate a process, conducting automation risk assessments, determining delegation autonomy, or configuring monitoring and verification guardrails.
W3C User Agent Fiduciary Duties Evaluatoruser-agent-dutiesEvaluates AI agents, coding harnesses, MCP integrations, and web-connected applications against the W3C Technical Architecture Group (TAG) User Agents specification (https://www.w3.org/TR/user-agents/). Checks the canonical W3C URL for upstream specification updates, classifies software component boundaries (§ 2.1), and scores any agent across 12 fiduciary axes under the three W3C User Agent duties: Protection (§ 3.1), Honesty (§ 3.2), and Loyalty (§ 3.3), applying 5 non-negotiable fiduciary hard gates.