Autopilot Charter Skill

Autopilot Charter Skill

Inventory the reports, briefings, and reviews you produce on a rhythm, and decide — deliberately — which ones an AI should run on a schedule, which it should only draft, and which stay human.

What This Skill Produces

• A ritual inventory: every recurring artifact, its cadence, audience, and inputs
• An automate / assist / keep-manual call per ritual, with the reason
• Guardrails for each automated ritual (review gate, failure behaviour, escalation)
• A rollout order — which ritual to automate first and why

Required Inputs

Ask for (if not already provided):

• The recurring outputs the user or team produces (weekly updates, monthly reviews, monitors, digests)
• Who consumes each one and what they do with it
• Where the inputs live (git, analytics, CRM, inbox, notes) and whether an agent can reach them
• Tolerance for error per artifact — what happens if a run is wrong or missing?

Classification Framework

Score each ritual on four questions, then classify:

• Automate — all four favourable. Schedule it end-to-end; the human sees the result, not the work.
• Assist — structure is stable but judgement or unreachable inputs remain. Schedule a draft; a human finishes it.
• Keep manual — high cost of error, or the ritual's value is the human thinking (performance feedback, strategy). Do not automate; record why so nobody re-litigates it.

Guardrails (required for every "Automate")

For each automated ritual, define:

• Review gate — does an edition ship unreviewed, or land as a draft for approval? Default to draft for anything audience-facing.
• Failure behaviour — if a run fails or a source is unreachable, does it skip, retry, or alert? A silent gap is worse than an error message.
• Staleness marker — every edition states when it ran and which sources it read.