Diagnostics without a workshop marathon
Get a first structured read on the end-to-end process from documentation you already hold.
— Operations & Process
IT Change Advisory Engine
A governed change-advisory call: change request in, an Approve / Approve with conditions / Defer to CAB / Reject verdict out — scored against your own change policy, with hard gates for risk and a mandatory change-manager sign-off before anything touches production.
- Operations & Process
- Traceable reasoning
- Runs anywhere
1–2 hours → ~5 minutes
For one document, brief or record at a time
No coding required
- Input
- Process documentation, SOPs or system exports
- Output
- A process step-level view of the end-to-end process with issues named and sized
- Runs in
- Skillsize · ChatGPT · Claude · Copilot
- Export
- SKILL.md · MCP
- Time saved
- ~1–2 hours per run
— USE CASES
What people use IT Change Advisory Engine for
Where the time and cost actually sits
Quantify each process step rather than describing the process in general terms.
A baseline you can re-run
Re-run after changes land and show movement against the original baseline.
What it works from
- Process documentation, SOPs or system exports
- Volume, time or cost data where you have it
What you get back
- A process step-level view of the end-to-end process with issues named and sized
- A prioritised set of interventions with the basis shown
Why this is expensive by hand
Understanding the end-to-end process usually means interviews, a whiteboard and a map that is out of date before it is finished. Diagnostics without a workshop marathon is the typical trigger — get a first structured read on the end-to-end process from documentation you already hold. Get it right and the conclusion holds up in the room; get it rushed and it gets picked apart. Either way it costs roughly 1–2 hours of experienced attention.
How this Skill produces it
Skillsize turns that work into a Skill: you supply the material, and what comes back is a process step-level view of the end-to-end process with issues named and sized, with a prioritised set of interventions with the basis shown. What sits between input and output is the codified method: thresholds, sequencing and the points where a human confirms a call — all of it visible and editable in the Skill. Net effect: 1–2 hours down to ~5 minutes, no drift between runs, and every conclusion traceable back to the evidence behind it.
Who it's for
- Operations and continuous improvement leads
- Transformation and automation teams
- Service delivery and shared services managers
- Consultants running process diagnostics
Run it in Skillsize — or export it anywhere
IT Change Advisory Engine exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
ChatGPTClaudeCopilotAI Products (MCP)
More Operations & Process Skills
Browse the full library →Operations & Process
Refund & Compensation Engine
A clause-grounded refund decision: request in, an Approve / Partial / Goodwill gesture / Decline verdict out — every element of the remedy traced to the contract term or refund policy clause that allows it, with authority-limit gates routing anything above the agent's limit to review.
Operations & Process
Escalation Decision Engine
A governed escalation call: case in, a Hold / Monitor / Escalate / Executive escalation verdict out — scored against your own escalation policy, with hard gates for risk and commercial exposure and a mandatory owner sign-off. Nothing is ever escalated automatically.
Operations & Process
Ticket Triage & Routing Engine
A deployable triage engine: a ticket arrives, the engine pulls the account and SLA context live from your helpdesk API, scores severity and routes it — Self-serve, Tier 1, Tier 2 or Escalate — with the rule that fired shown every time.