菜单
Build or run Autonomous Ops workflows for AX Performance Advisor, including investigation queues, evidence acquisition plans, follow-up questions, change drafts, validation planning, and readiness gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyze slow AX frontends, problematic users/clients, broad inventory queries, and machine-wide impact without installing client parsers.
Generate AI learning and decision-quality artifacts such as recommendation memory, similarity search, acceptance simulation, narrative variants, anomaly explanations, and action confidence tuning.
Generate autonomous AI/USP investigation artifacts including evidence scout, investigation tree, root-cause debate, recommendation quality gate, KPI storyboard, and anonymized pattern library.
Generate guarded admin execution previews with policy gates, confirmation tokens, audit records, and rollback/validation metadata.
Generate advanced operational USP outputs including SLO burn rate, maintenance sequencing, cost of delay, release gates, retention candidates, known issue matching, and executive briefings.
Prioritize AXPA findings using cost-of-delay risk points and deferred-risk reasoning.
| name | autonomous-ops-copilot |
| description | Build or run Autonomous Ops workflows for AX Performance Advisor, including investigation queues, evidence acquisition plans, follow-up questions, change drafts, validation planning, and readiness gates. |
Use this skill when the user wants AXPA to move from analysis into controlled operational planning without directly changing production systems.
scripts/autonomous_ops.py.evidenceAcquisitionPlanner first; missing evidence must be collected or explicitly accepted as a limitation.investigationQueue and rootCauseDecisionTree to decide the next diagnostic step.changeDrafts and validationRunPlanner only for findings with enough evidence and an owner.