run-of-show-and-staffing
Skill0 starsChanged 25 days agoMITView on GitHub
Builds the staffing plan, role cards, volunteer brief, minute-by-minute run of show, communications plan, and load-in and load-out for an artist-led athletic event of any sport. Use for "how many volunteers do we need", "write the run of show", "brief the crew", "who does what on the day", or "make the timeline for event morning".
In this repository13 other files it gives its agents.
- artist-deal-termsSkill
- artist-fit-and-conceptSkill
- content-capture-and-rightsSkill
- event-budget-pnlSkill
- event-producerSkill
- launch-campaignSkill
- permits-insurance-and-riskSkill
- press-and-mediaSkill
- recap-and-sponsor-reportSkill
- registration-and-capacitySkill
- sponsor-inventory-and-pricingSkill
- sponsor-outreach-and-closeSkill
- sport-format-designSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Every event needs these roles filled by named people.
- Very specific: line 38
Use assets/run-of-show.md.
- Distinctive: line 51
Every line: time, what happens, who leads, where, what's needed.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run of Show and Staffing
Step 1: Roles
Every event needs these roles filled by named people. One person can hold more than one at small events, except the medical lead and the event lead, who should not be doing anything else.
| Role | Does |
| Event lead | Owns the run of show, makes non-safety calls, only person who changes the plan |
| Medical lead | Medical response, nothing else |
| Weather decision owner | Monitors and makes the weather call (can be the event lead) |
| Talent handler | Artist arrival, timing, exits, protects their time |
| Check-in lead | Waivers, count, walk-ups |
| Welcome host(s) | Greets first-timers, pairs people up |
| Group / station / court leaders | Run the activity (ratios from the sport reference) |
| Sweep(s) | Last person in every group |
| Marshals | Crossings, turns, crowd flow |
| Partner liaison | Partner setup, deliverables, photos for the report |
| Content lead | Shot list, consent, approvals |
| Load-in / load-out | Setup, cleanup, leave it cleaner than you found it |
Staffing counts come from the sport reference's starting ratios, confirmed with the venue and medical lead.
Step 2: Role cards
One card per role (assets/role-card.md): what you do, where you stand, when you're needed, who you report to, what to do if X goes wrong, radio channel or group text.
Step 3: Run of show
Use assets/run-of-show.md. Work backward from the start time. Include:
- Load-in, partner setup, signage, sound check
- Crew briefing (15 minutes, always)
- Check-in open
- Welcome and safety briefing to participants (weather plan, route or rules, sweep, how to get help)
- Warm-up
- Activity blocks with exact times
- Artist moments with exact times and the handler's cues
- Partner moments
- Hang / post-event
- Load-out and site check
- Hard stop
Every line: time, what happens, who leads, where, what's needed.
Step 4: Communications
- One channel for the crew (radio or a group text), one person who speaks for the event publicly.
- Pre-written messages for: delay, cancellation, lost participant, emergency.
Step 5: Crew briefing (send 2 days out, repeat on site)
Who we are and why, the run of show, your role card, the emergency plan, the weather plan, and the one rule: nobody gets left behind.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

