mcpField
L
live-event-ops-review

live-event-ops-review

github.com/sylphxaiMarketing & growth150 installsUpdated today
Repository

About live-event-ops-review

A skill for planning live events as operational programs, aimed at teams responsible for event setup and delivery. It produces a runbook covering launch decisions, monitoring, rollback, support, and post-event review, with attention to fairness and operational risk.

Key features

  1. 01Map event setup and shutdown states
  2. 02Assess engagement and monetization goals
  3. 03Review fairness and operational risks
  4. 04Create launch and rollback plans
  5. 05Define monitoring and support procedures

Use cases

  1. 01Prepare a go/no-go review before an event
  2. 02Plan event monitoring and rollback
  3. 03Coordinate support and compensation during an event
  4. 04Review outcomes after an event

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sylphxai/skills --skill live-event-ops-review

After installing, type/live-event-ops-reviewin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlreferences/live-event-ops-systems.md

Details

From the project README

Live Event Ops Review

Use this skill to run live events as controlled product operations, not calendar-driven chaos.

Workflow

  1. Identify event objective, audience, duration, eligibility, reward/offer, dependencies, and blast radius.
  2. Read references/live-event-ops-systems.md.
  3. Map event configuration, rollout, eligibility, inventory/rewards, notifications, monitoring, support, compensation, and shutdown states.
  4. Separate engagement goal, monetization goal, economy impact, fairness, operational risk, and trust risk.
  5. Produce an event runbook with go/no-go, metrics, rollback, support macros, and post-event review.

When not to use

  • Do not use for generic advice the base model already handles without this skill's specific artifact contract.

Guardrails

  • Do not launch an event without monitoring, support route, and rollback/compensation plan.
  • Do not create rewards or offers that destabilize economy, pricing, or fairness without explicit mitigation.
  • Avoid fake scarcity, unclear eligibility, and invisible rule changes.

Output format

Event context:
Objective and audience:

Runbook:
- setup:
- launch:
- monitor:
- support:
- end/settle:

Risks:
- <risk> -> metric, rollback, compensation

Post-event learning:
- decision, data, follow-up

Comments

Markdown supported