agentleFS
guerrilla2799guerrilla2799/event-and-scale-os/skills/virtual-events/SKILL.md

virtual-events

Skill2 starsChanged 3 months agoMITView on GitHub

Use when the user says "webinar", "virtual roundtable", "online event", "virtual briefing", "digital event", "nobody shows up to our webinars". Designs the virtual tier without the registration vanity: virtual roundtables for depth, webinars for reach, and honest metrics for both. Writes workspace/events/<event>/virtual-plan.md.

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
  1. Distinctive:

    No slides beyond a single framing slide

    line 37
  2. Distinctive:

    Start on time: Do not wait for stragglers, it punishes the punctual

    line 63

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Virtual Events

The scalable tier. Cheap, fast, and worth running when you are honest about what each format produces, which is not what most teams report.

When to use

  • Target accounts will not travel, or are spread across regions
  • Testing a topic cheaply before building a physical event around it
  • Mid-funnel coverage between in-person touches
  • A customer education or adoption motion

Inputs

  • Reads: workspace/audience/target-list.csv, workspace/program/charter.md, workspace/program/stack.md
  • Needs from user: the objective, the audience, the presenter, and the promotion channels available

Workflow

1. Pick the right virtual format

They are not interchangeable and they produce very different things.

FormatSizeProducesNext-meeting rate
Virtual roundtable8 to 12, cameras on, everyone speaksReal relationships, genuine insight25 to 40%
WebinarUnlimited, one to manyReach, content, mid-funnel coverage2 to 5%
Virtual executive briefing3 to 6 people from one accountAccount depth without travelVery high, and it is really a meeting
Customer training or office hoursAnyAdoption and retentionn/a, different objective

The virtual roundtable is the under-used one. It is a dinner without the dinner: same size, same doctrine, same rules about who speaks and who does not, at a small fraction of the cost. For accounts that will not travel, it is the best format available.

2. For virtual roundtables, keep the dinner doctrine

  • 8 to 12 people, cameras on, stated as an expectation in the invitation
  • No slides beyond a single framing slide
  • An opening round where everyone speaks in the first ten minutes. This is what makes the rest work
  • A moderator whose job is pulling in the quiet ones
  • 60 minutes, not 90. Virtual attention is shorter
  • Chatham House Rule if candor matters, stated out loud

3. For webinars, fix the topic before fixing the promotion

Most webinar problems are topic problems. The test: would someone give up an hour for this if it had no vendor attached?

  • A specific, contested, useful subject beats a category overview every time
  • A guest with independent credibility outperforms your own people
  • A number in the title, referring to real data you have, outperforms an adjective
  • "How we built X" beats "the future of X"
  • A product demo with a question mark on the end is not a topic

4. Promote for the right registrations, not the most

The metric that matters is target accounts registered, then attended. A webinar with 400 registrations and 6 target accounts is worse than one with 60 registrations and 25 target accounts.

  • Direct invitations from account owners to named target accounts, first
  • Email to the relevant segment, second
  • Social and paid, last
  • Partner or guest promotion, which is frequently the highest yield line

5. Run it properly

  • Rehearse the technology with the actual presenter on the actual platform. Not a quick check
  • A host who is not the presenter to run Q&A, watch chat, and handle problems
  • Start on time. Do not wait for stragglers, it punishes the punctual
  • Seed two or three questions so the Q&A does not open with silence
  • End on time. Overrunning loses the recording audience too

6. Report honestly

ReportNot
Target accounts registered and attendedTotal registrations
Attendance rate, with 35 to 50% understood as normalA high attendance rate presented as a topic win, when it usually means a good list
Percentage who watched more than halfTime on page
Meetings booked"Leads generated"
On-demand views over 90 daysNothing, which is what most teams report

Above 55% attendance usually means you invited people who already knew you, which is fine and worth knowing.

7. Use the recording as the actual asset

Most of a webinar's value is created after it. Plan before you record: clips, a written summary, a gated on-demand version, a follow-up sequence to non-attendees with the recording. A webinar used once was overpriced even at zero cost, because the time was the cost.

Output

  • Writes: workspace/events/<event>/virtual-plan.md with the format choice, topic, promotion plan, run sheet, and the content plan for the recording
  • Prints: the format recommendation, the topic test result, the promotion sequence, target-account registration position, and the reporting shape

Rules & quality bar

  • Format matched to objective. A webinar will not build a relationship
  • Virtual roundtables keep the dinner doctrine. Cameras on, opening round, no slides
  • Fix the topic before the promotion
  • Target accounts registered is the metric. Total registrations is not reported as success
  • Rehearse on the real platform with the real presenter
  • Start and end on time
  • The recording plan exists before the recording

Related skills

  • Reads: audience-machine, event-program-setup
  • Pairs with: event-content (the recording assets), event-followup
  • See also: docs/metrics.md for virtual benchmarks

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.