samber/dev-event-organizer-skills / skills/event-first-edition
event-first-edition
VerifiedLaunch the first edition of a tech event (conference, hackathon, large meetup) from zero - a minimum viable edition 1, scope discipline against the full vision, the first cross-organization team, the decision-to-doors-open reverse timeline, and a pre-mortem of first-edition-specific risks with written go/no-go dates. Use whenever asked to start a new conference or hackathon, plan a first edition, scope a minimum viable event, form a founding organizer team, or set a launch timeline for an event with no track record. Strategy layer for edition 1 only. Do NOT use to validate demand first - use samber/dev-event-organizer-skills@event-market-fit - or to grow an established event - use samber/dev-event-organizer-skills@event-growth-strategy.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 22.0 KB |
| evals/evals.json | config | 30.3 KB |
| references/first-edition-premortem.md | markdown | 4.7 KB |
| references/reverse-timelines.md | markdown | 8.0 KB |
| references/scope-and-appetite.md | markdown | 4.7 KB |
references/scope-and-appetite.md
View on GitHub# Scope, appetite, and the validation ladder
A first edition is structurally a product launch: one bet, no track record, a feedback loop that only closes at doors-open. The scope and validation mechanics below reflect this reality.
## MVP types mapped to first-edition shapes
| MVP type | First-edition transposition | When it fits |
| ------------------------------- | -------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| Concierge (manual service) | Organizer-run by hand: personal invites, spreadsheet registration, no ticketing platform | Testing whether people show up before building any infrastructure |
| Wizard of Oz (manual backend) | Advertise a feature not yet built (e.g. attendee matchmaking) and deliver it by hand for edition 1 | One differentiating promise, no budget to build it yet |
| Smoke test (signup, no product) | Waitlist/interest page before venue or date is locked | Belongs to `samber/dev-event-organizer-skills@event-market-fit` - demand validation, not edition sizing |
| Single feature | One core format only: talks, no workshops, no expo | The default single-focus tier |
| Piecemeal (existing tools) | Borrow an existing meetup's list, a free venue, an existing community's chat | The borrowed-edition tier |
What NOT to transpose: Lean Startup's growth-engine machinery (viral coefficient, CAC/LTV, cohort retention) measures sustained usage over time, which one edition cannot generate. That vocabulary belongs to `samber/dev-event-organizer-skills@event-growth-strategy`.
## The validation ladder as a spending gate
Evidence strength, weakest to strongest:
1. Opinion.
2. Stated interest.
3. Deposit or claimed ticket.
4. Actually shows up.
Require level 3 (real registrations) before committing spend beyond the Good budget tier. Committing Best-tier budget on levels 1-2 is premature scaling with a venue contract attached.
## Appetite, rabbit holes, no-gos
Set the appetite - organizer hours and money this launch is worth - before shaping the program. The appetite bounds the program, never the reverse. Then write down, explicitly:
- **Rabbit holes** likely to swallow a first-edition team: a custom mobile app, elaborate stage production, simultaneous livestream, a multi-city launch.
- **No-gos** for edition 1, named so nobody re-litigates them mid-planning.
Worked example (a 3-person team, one day/week each, launching a one-day community conference):
> Appetite: ~10 organizer-hours/week for 9 months, break-even budget at the Good tier.
> No-gos for edition 1: no international speakers, no second track, no livestream, no paid keynote, no expo hall.
> Rabbit hole watch: "let's just build a small talk-voting app" - use the ticketing platform's built-ins or a form.
"Underdo the competition": a first edition competing on breadth against a tenth-edition conference loses; competing on being sharply focused on one underserved audience doesn't. Half an event done well beats a thin version of everything a mature edition has.
Opinionated defaults, decide-don't-hedge: every axis left open (city, date, price, format) is a decision attendees and sponsors need someone to make with confidence. Pick the best default per question, ship it, revisit only on evidence.
## Good / Better / Best budget tiers (sourced: DevOpsDays organizing guide)
Plan three versions of the same event before selling a single ticket:
- **Good** - the bare-minimum viable version: no catered food, pared-down badges, no evening event.
- **Better** - adds the expected niceties.
- **Best** - real headroom: an extra sponsored evening activity, better catering.
Write downgrade dates into the timeline: Best → Better → Good, triggered by sponsorship revenue actually received by each date. DevOpsDays targets 80%+ of budget from sponsorship, so this decouples "will we run at all" from "did tickets sell fast" - a soft ticket signal downgrades the tier instead of forcing cancellation.
The tier mechanism is sourced; every specific downgrade date and revenue threshold is self-set per event. The full P&L behind the tiers: `samber/dev-event-organizer-skills@event-budget`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |