event-program-setup
Skill2 starsChanged 3 months agoMITView on GitHub
Run this first, before any other Event & Scale OS skill. Use when the user says "plan our events for the year", "event strategy", "set up an events program", "how much should we spend on events", "which events should we do". Interviews the user on objective, budget, formats, team capacity, and constraints, checks whether events are the right investment at all, and writes workspace/program/charter.md plus stack.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-retrospectiveSkill
- event-selectionSkill
- executive-dinnerSkill
- invite-motionSkill
- meeting-engineSkill
- owned-eventSkill
- roundtable-and-salonSkill
- run-of-showSkill
- 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
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Very specific: line 14
Before event-selection on any specific event.
- Distinctive: line 15
After a bad year, when the portfolio needs rebuilding rather than tweaking
- Distinctive: line 34
Ask all of this at once, then wait.
- Distinctive: line 64
Do not allocate evenly. Start from the objective:
- Distinctive: line 80
Write down now, while it is unemotional:
- Distinctive: line 91
Every answer the user could not give, with an owner and a date.
- Distinctive: line 106
Read by: every other skill
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Event Program Setup
Establish the portfolio charter every other skill reads: what events are for at this company, how the budget splits across formats, what the team can actually staff, and what is off the table.
When to use
- Annual or half-year event planning
- A new client engagement or a new role where events are part of the remit
- Before
event-selectionon any specific event. That skill routes back here if the charter is missing - After a bad year, when the portfolio needs rebuilding rather than tweaking
Inputs
- Reads:
workspace/program/charter.mdif it exists (updates rather than overwrites) - Needs from user: the interview below, in one batch. Do not guess any of it
Workflow
1. Readiness check, before anything else
Events are expensive per person reached. Run these and say plainly when the answer is no.
| Question | If no |
| Is the deal size high enough to justify a high cost per attendee? | Recommend digital demand generation instead. Events at low deal sizes rarely return |
| Is there a sales team to work the meetings? | An event with no seller is a brand exercise. Say so and price it as one |
| Can the target list be named, or is it "people in the industry"? | Fix the target list first. Run audience-machine as a standalone project |
| Is there a person who owns event execution? | Events fail on unowned details. Without a named owner, recommend one format at most |
2. Interview, in one batch
Ask all of this at once, then wait.
Objective
- What is the primary objective for events this year? (New logos in a segment, executive relationships at named accounts, customer retention and expansion, category authority, product launch)
- What number makes this a success, by when?
- Which of those objectives is not the goal, so we can say no to things later?
Segment and audience
- Who has to be in the room? Titles, seniority, industries, company size
- How many named target accounts exist, and does that list exist today?
- Are these people who travel, or people who do not?
Formats and capacity
- Which formats has the team run before, and how did they go?
- How many events can this team genuinely execute in a year without everything else stopping?
- Who executes: a dedicated event person, a marketer part-time, an agency?
- Are executives available for stages and dinners, and for how many days a year? Get this in writing
Budget
- Total event budget for the year
- What is already committed and cannot be moved
- Is there a travel budget separate from the program budget, and who owns it?
Constraints
- Industries or accounts with gifting, hospitality, or entertainment restrictions
- Brand, legal, or compliance rules on hosting and on stages
- Regions with data or invitation restrictions
- What failed before, and what everyone believes about why
3. Split the budget across formats
Do not allocate evenly. Start from the objective:
| If the objective is | Weight toward |
| Executive relationships at named accounts | Dinners and private roundtables. Frequently the whole budget |
| New logos in a defined segment | Conferences where that segment congregates, plus dinners around them |
| Category authority | Stages and an owned event, with content as a first-class output |
| Customer retention and expansion | Owned customer events, suites at industry conferences, executive business reviews |
| Coverage of accounts that will not travel | Virtual roundtables and webinars |
Then reserve two lines most teams forget: an opportunistic reserve of roughly 10 to 15% for an event that appears mid-year, and follow-up capacity, which is time rather than money but has to be planned or the pipeline evaporates.
4. Set the annual calendar
Plot the events under consideration against the countdown in docs/lifecycle.md. The output that matters is where two events collide: two things at T-4 weeks in the same fortnight will both be under-run. Space them or drop one.
5. Set the standing rules
Write down now, while it is unemotional:
- The minimum pre-booked meeting count below which you do not sponsor
- The sponsorship scoring rule (stage, transferable seats, meetings as the metric)
- The date by which an executive tier-one invite list must exist, and what happens if it does not
- Who can approve a sponsorship, and above what number
6. Write the files
workspace/program/charter.mdfromtemplates/event-charter-template.mdworkspace/program/stack.mdfrom the tool answers
7. Name the open questions
Every answer the user could not give, with an owner and a date. Do not fill them with assumptions.
Output
- Writes:
workspace/program/charter.md,workspace/program/stack.md - Prints: the readiness verdict, the objective, the budget split by format with reasoning, the calendar collisions, and the standing rules
Rules & quality bar
- One primary objective. Rank the rest and put them in "later"
- Say no when the readiness check fails. Recommending an event program to a company that cannot staff it wastes a year
- Executive time is confirmed in writing, in days per year, before any format that depends on it goes in the plan
- Standing rules are written before the first event, because they are impossible to set fairly once a specific opportunity is on the table
- Never invent the numbers. Budget, deal size, and capacity come from the user or are marked unknown
Related skills
- Hands off to:
event-selectionfor any specific event,audience-machinefor the target list - Read by: every other skill
- See also:
docs/formats.mdfor format economics,docs/lifecycle.mdfor the countdown
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.