Coordinate human-in-the-loop decision gating during automated sessions.
npx skills add https://github.com/px-pride/axi-assistant --skill decision-mode
Please help me install this Agent Skill. Skill: decision-mode Source: https://github.com/px-pride/axi-assistant/tree/main/.claude/skills/decision-mode Command: npx skills add https://github.com/px-pride/axi-assistant --skill decision-mode
This skill turns AI-driven sessions into explicit, human-guided decision processes, ensuring approvals before material actions.
Begin with a chosen intensity and present the first decision point to the user for approval
High-intent search queries and answers about installing and using this skill.
Human-in-the-loop approval gates can be added to an AI workflow by enforcing decision discovery and gated execution, ensuring explicit user oversight before material actions are taken.
Decision gating in automated AI sessions is the process of pausing multi-step tasks at critical decision points to require explicit human approval, ensuring traceability and governance before proceeding.
You can control interaction depth during AI tasks using intensity enums like --strict, --balanced, and --light, which tailor the frequency and strictness of required human approvals.
Yes, decision logs for AI task governance are maintained throughout the workflow phases, providing full traceability and auditability for all gated decisions across multi-step conversations.
The best way to enforce risk management before an AI agent takes material actions is to implement structured workflow phases with strict intensity controls and mandatory gated approvals.
Strict decision gating should be avoided for low-risk, repetitive AI tasks where manual approval overhead outweighs governance benefits, making the --light or --balanced intensity modes more suitable.
linkerlinGuide AI agents through a five-step methodology for complex problem-solving.
qmuEvaluate git branch decision-making and output a JSON summary with metrics.
connor-git-yamlCoordinate ten-phase Spec-Driven Development workflows with Claude Code Task tools.
tractorjuiceGenerate governance frameworks with oversight models and compliance mappings for autonomous AI agents.
