菜单
Activate when rehearsing or testing the demo runner. Guides dry-running the 3-minute demo end-to-end against the local stack.
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
Offline, credential-free knowledge + static validators for UiPath Maestro Case footguns. Explain cryptic error codes (400300, 160009, ...) and lint caseplans, spawn inputs, and Data Fabric specs in CI — no UiPath login. Use when authoring, debugging, or reviewing UiPath Maestro Case / Data Fabric / Action Center work.
Cross-runtime skill optimizer. Use this skill when the user wants to package an Agent Skill so it runs in both Claude Code and OpenAI Codex from a single portable source. Also use when the user wants to import an existing skill (Claude Code or Codex) into the portable format, build/emit for any runtime, install a skill into Claude Code or Codex, or troubleshoot why a skill behaves differently across runtimes.
Use when the user wants to package a skill so it runs in both Claude Code and Codex from one source, import an existing skill into the portable format, install to Claude or Codex, or troubleshoot cross-runtime drift.
Structure long-running Claude Code sessions on this Python project so the agent iterates for hours instead of stopping after one pass. Use when the user mentions "long-running session", "multi-hour run", "agent keeps stopping", "agent finishes too early", "headless run", "tmux session", "milestones", "make verify", "fake success", "prevent shortcuts", or asks how to set up hooks, a verification gate, or an operating contract for an autonomous coding agent.
Activate when the BAA Boundary Reasoner Agent runs or when a regulatory inquiry hits multiple affected provider customers. Teaches how to reason about a single regulatory inquiry against multiple differing BAA terms.
Activate when designing any new case stage, child case, or grandchild case. Defines the six case-shape patterns Maestro Case must demonstrate.
| name | demo-rehearsal-runner |
| description | Activate when rehearsing or testing the demo runner. Guides dry-running the 3-minute demo end-to-end against the local stack. |
Guide dry-running the 3-minute demo end-to-end, including expected state transitions per reversal.
Total runtime: ~3 minutes (180 seconds)
| Timestamp | Event | Expected State Change |
|---|---|---|
| 0:00 | Show baseline dashboard | Normal metrics, no active cases |
| 0:15 | Day 0: Northstar anomaly | Master case opens, 3 child cases, network risk score jumps |
| 0:25 | Day 0: Alpha anomaly | Second child case opens |
| 0:35 | Day 1: Beta anomaly → Reversal 1 | Pattern Detector fires, master goal shifts, correlation visualization |
| 0:50 | Day 3: PHI signal (child event) | BAA Exposure child case opens, evidence added |
| 1:00 | Day 5: Reversal 2 | ClearFlow cleared, Nimbus identified, posture decision |
| 1:15 | Day 14: Liquidity stress (child event) | Payment Continuity escalates, cash-at-risk counter updates |
| 1:30 | Day 30: Reversal 3 | Subpoena → BAA Reasoner → 6 grandchild cases → three-level nesting visible |
| 1:50 | Day 45: Reversal 4 | Apex demands data, fiduciary conflict, tri-party HITL gate |
| 2:10 | Day 90: Reversal 5 | Litigation cascade, co-defendant posture, privilege reshuffle |
| 2:30 | Show executive brief | Current state summary, evidence pack, decision history |
| 2:50 | Closing | Demo closing line |
For each reversal, verify:
Map each reversal to its acceptance criteria in REQUIREMENTS.md and Build Brief.
