run-of-show
Skill2 starsChanged 3 months agoMITView on GitHub
Use in the final two weeks before any event, or when the user says "run of show", "run sheet", "the schedule for the day", "who does what on the day", "timeline for the event". Builds the hour-by-hour for every day of the event with an owner on every line, including setup, rehearsal, and breakdown. Writes workspace/events/<event>/run-of-show.md.
In this repository23 other files it gives its agents.
- artifact-evalSkill
- audience-machineSkill
- conference-activationSkill
- event-and-scale-osSkill
- event-budgetSkill
- event-contentSkill
- event-followupSkill
- event-logisticsSkill
- event-measurementSkill
- event-program-setupSkill
- event-retrospectiveSkill
- event-selectionSkill
- executive-dinnerSkill
- invite-motionSkill
- meeting-engineSkill
- owned-eventSkill
- roundtable-and-salonSkill
- speaking-and-stageSkill
- sponsorship-negotiationSkill
- staffing-and-briefingSkill
- venue-selectionSkill
- virtual-eventsSkill
- writing-qualitySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
No line without a name. "The team" is not an owner.
- Distinctive: line 81
Every line has a named owner: No exceptions
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
The hour-by-hour document that makes the day boring. Every line has a time, an action, and a named owner, and it covers the day before and the breakdown as well as the event itself.
When to use
- T-2 weeks on any event
- Multi-day events, or an event with a side event attached
- Any event where more than two people from your side are involved
Inputs
- Reads:
workspace/events/<event>/logistics.md,workspace/events/<event>/meetings.csv, the format plan, the venue file - Needs from user: the published agenda if there is one, who is attending from your side, and travel times
Workflow
1. Cover every day, not just the main one
A run of show that starts at doors is missing the half where things go wrong:
- T-2 or T-1: rehearsal day. Final run of any talk against a timer. Materials arrival confirmed
- T-1: setup, side event, and the huddle
- T+0: the event
- T+0 evening: breakdown, shipping out, and the debrief
2. Anchor to real times, flag the placeholders
Use the published agenda where it exists. Where it does not, write placeholders and say so clearly at the top of the document, with a link to the live agenda and a note to replace them the day it posts. Everything relative (rehearsal before, buffer after, notes between meetings) holds regardless of what the final times are.
3. Build the setup block properly
Setup is where events are lost.
7:00am Setup opens. Banner up, table throw on, screen loop running,
collateral stocked, lead scanner tested in the app Owner: <name>
7:30am Meeting schedules confirmed. Everyone has their day on their phone Owner: <name>
7:45am Team position check. Who is where at doors Owner: <name>
8:00am DoorsSetup opens at the earliest permitted hour and you use it. A team arriving with the attendees is a team whose first hour is spent unpacking.
4. Put an owner on every single line
No line without a name. "The team" is not an owner. An unowned line becomes a problem at 7am on load-in day when everyone assumes someone else has it.
Name one owner of the day: the person who makes calls when something goes wrong, whose phone stays on, and whose number everyone has.
5. Build in the buffers people forget
- Travel time between venues, at the real time of day, in that city
- Fifteen minutes between meetings for notes. Back-to-back meetings with no gap produce no notes, and no notes produces bad follow-up
- A gap before any talk. A speaker walking on from a meeting is a speaker who is not ready
- Time to eat. People perform badly on no lunch, and nobody schedules it
6. Schedule the huddle the night before
Twenty minutes, team only:
- Tomorrow's schedule, per person
- Who owns which meeting and which guest
- The VIP list and who greets them
- Competitive and objection refresher
- Where to be at doors
The night before, never the morning of. The morning of an event has no spare time in it.
7. Write the breakdown block
- Nobody packs up early. The last hour, when the drinks come out, is the highest-quality hour of the day
- Return labels are already inside the boxes
- Same-day capture: every conversation gets a note before anyone sleeps
- A fifteen-minute debrief at the end of the day, while it is accurate
8. Distribute it as one page per person
Nobody reads a nine-page run of show on their phone between meetings. Each person gets their own day: their meetings, their sessions, their responsibilities, their locations. The master lives with the owner of the day.
Output
- Writes:
workspace/events/<event>/run-of-show.mdfromtemplates/run-of-show-template.md, plus per-person schedules - Prints: the full run of show, any line without an owner, and the placeholder times still needing confirmation
Rules & quality bar
- Every line has a named owner. No exceptions
- One named owner of the day, with a phone that stays on
- Covers rehearsal, setup, the event, and breakdown
- Placeholder times are flagged as placeholders with a link to the live agenda
- Buffers for travel, notes, and food are in the schedule
- The huddle is the night before
- Nobody packs up early
- Distributed as one page per person
Related skills
- Reads:
event-logistics,meeting-engine, the format skill - Pairs with:
staffing-and-briefing - Feeds:
event-followup(same-day notes)
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.

