event-measurement
Skill2 starsChanged 3 months agoMITView on GitHub
Use when the user says "did the event work", "event ROI", "event scorecard", "what did we get from the conference", "report on events". Builds the scorecard, computes cost per qualified meeting, compares formats across the portfolio, and reports at 30, 60, and 90 days. Writes workspace/measurement/. Owns the numbers. Not the process post-mortem on what to change next time, which is `event-retrospective`.
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-program-setupSkill
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 12
Before the event, setting up the instrumentation.
- Distinctive: line 15
When somebody asks whether to do it again
- Distinctive: line 84
Report at 30, 60, and 90: Never present the 30-day number as final
≈ “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 Measurement
Measure the event on qualified meetings and cost per qualified meeting. Report the same shape every time, including the times it looks bad.
When to use
- Before the event, setting up the instrumentation. This is the correct time
- At 30, 60, and 90 days after
- Annual planning, comparing formats across the portfolio
- When somebody asks whether to do it again
Inputs
- Reads:
workspace/events/<event>/budget.md,meetings.csv,followup/,workspace/program/charter.md - Needs from user: CRM access or the pipeline export, and the historic cost per meeting from other channels for comparison
Workflow
1. Define qualified before the event
In writing, strict enough to hurt:
A scheduled 1:1 with a C-level, Head-of, or Director-plus person at a company inside the ICP, that ends with a named next step and a date.
Adapt the seniority bar, keep the three properties: a named person, an ICP company, a next step with a date. A conversation that ends with "send me something" is not qualified, and counting it as one is how event programs lose credibility in year two.
2. Instrument before the event
Confirm you can read every number you plan to report:
- An event field on the account or contact record, not just a campaign
- The meeting tracker, with a qualified flag
- Cost lines captured as they are committed, not reconstructed later
- The room composition count: target accounts present
Instrumenting afterward means reconstructing from memory, and reconstruction always flatters.
3. Build the scorecard
EVENT <name> · <date> · <format> · Owner: <name>
COST Sponsorship $n | Travel $n | Staff days $n | Production $n | TOTAL $n
ROOM Attendance n | Target accounts present n (n%) | Senior ICP pool n
MEETINGS Pre-booked n | Held n | Qualified n ← graded on this
PROGRESSION Second meetings n | Opportunities n | Pipeline $n
EFFICIENCY Cost per qualified meeting $n | vs outbound cost per meeting n%
CONTENT Recap live? y/n | Assets produced n
RISK <what went wrong that will go wrong again if nothing changes>The efficiency line ends bad habits. Cost per qualified meeting against what a meeting costs from outbound is far harder to argue with than a feeling about the event.
4. Report at 30, 60, and 90
Event pipeline matures slowly. The 30-day number always looks bad, and teams that report only at 30 days talk themselves out of formats that were working.
| At | Report |
| T+30 | Meetings held, qualified, second meetings, cost per qualified meeting. Labeled explicitly as early |
| T+60 | Opportunities, pipeline value, meetings that went dark |
| T+90 | Pipeline still live, closed-won if any, final cost per opportunity, and the repeat decision |
5. Build the portfolio view
Once a few are done, the comparison across formats is the real output:
| Format | Events | Total cost | Qualified meetings | Cost per meeting | Pipeline | Repeat? |
This table usually shows something uncomfortable and useful: the expensive conference produced fewer qualified meetings than three dinners at a fraction of the cost, or the webinar program everyone dismissed produced the cheapest meetings in the portfolio.
6. Stop reporting the misleading metrics
Badge scans, registrations, impressions, "leads generated", cost per attendee, and social engagement on event posts. docs/metrics.md has the replacement for each. If a metric cannot change a decision, it does not belong on the scorecard.
7. Bring the risk line every time
One line, every report, on what went wrong and what it will cost if nothing changes. The program keeps its credibility by flagging its own problems before someone else finds them.
Output
- Writes:
workspace/measurement/<event>-scorecard.md, and the portfolio table inworkspace/measurement/portfolio.md - Prints: the scorecard, the cost per qualified meeting with the comparison, the repeat recommendation, and the risk line
Rules & quality bar
- Qualified is defined in writing before the event
- Instrumented before the event, never reconstructed after
- Cost per qualified meeting is the headline efficiency number
- Report at 30, 60, and 90. Never present the 30-day number as final
- Same scorecard shape every time so comparison is real
- No badge scans, registrations, or impressions as success metrics
- The risk line ships every time
- Never invent a number. Unavailable data is reported as unavailable
Related skills
- Reads:
event-budget,meeting-engine,event-followup - Feeds:
event-retrospective,event-program-setup(next year's budget split) - See also:
docs/metrics.md
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.

