coreyhaines31/marketingskills / skills/events
events
VerifiedWhen the user wants to plan, run, sponsor, or speak at events, or asks whether an event or booth is worth the money: webinars, conferences, booths, meetups, show-up rates, and follow-up into pipeline. For launches, see launch. For joint webinars, see co-marketing. For community programs, see community-marketing. For podcasts, see public-relations. For event emails, see emails.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.4 KB |
| evals/evals.json | config | 10.9 KB |
| references/event-portfolio-strategy.md | markdown | 7.8 KB |
| references/speaking.md | markdown | 5.2 KB |
| references/sponsorship-roi.md | markdown | 6.1 KB |
| references/webinar-funnel.md | markdown | 8.0 KB |
references/speaking.md
View on GitHub# Speaking — Get Booked, Design the Talk, Compound the Recording
Speaking is the highest-leverage event role per dollar: stage time confers borrowed authority no booth can buy, and the recording compounds for years — including in AI answers. Treat it as three separate jobs: getting booked, designing a talk that lands, and harvesting the asset.
## Getting Booked (CFPs and pitches)
Organizers optimize for their audience's experience, not your reach. Pitch accordingly:
- **Pitch the audience takeaway, not your company.** A CFP that reads like a case study of the *attendee's* problem gets accepted; a product story gets filtered. Your product can appear as evidence inside the talk, never as its subject.
- **Title formula**: specific outcome + specific audience + a tension or number. "How we cut CAC 40% by killing our best channel" beats "Rethinking Growth."
- **The abstract carries three things**: the problem as the audience feels it, the specific things they'll walk away knowing (2–3, concrete), and why *you* — the proof you've actually done it (numbers, scars). Keep it under 150 words; organizers skim hundreds.
- **Track and ladder**: local meetups → niche conference tracks → main stages. Recordings of small talks are your CFP portfolio for bigger ones. Podcast appearances feed the same ladder (→ **public-relations** podcast prep — same evidence discipline, same context file).
- Off-cycle path: many events fill panels and replacement slots late — a short note to organizers with a tight topic + proof of speaking ability lands surprisingly often.
## Designing the Talk: Outline First, Then Feelings
A talk is a journey you take the room on, not a document you read at them. Two passes:
**Pass 1 — the outline.** Before slides, lock four things (write them down; mush here becomes mush on stage):
1. **Who this is for** — one person, their situation, what they already believe walking in
2. **The Monday takeaway** — what they can *do or decide* on a specific next day; a talk without one is content, not a talk
3. **What you get** — your win (pipeline, credibility, hiring) so the close can carry it without a swerve
4. **The blocks** — each with a point and a proof (a story or a number). No proof, no block.
**Pass 2 — storyboard the feeling.** Map how the room should *feel* beat by beat — a beat is a change in energy or emotion, not a slide heading. A 20-minute talk is usually 5–8 beats. For each beat, name:
- **Energy** — the room, in directable words: quiet lean-in, rising unease, laugh-release, peak, still
- **Feel** — the emotion in the audience's own mouth: "that's me," "wait, we're the problem," "I can try this Monday"
- **The hit** — the one thing this beat must land, in one sentence
Then check the journey: does the sequence of feelings *earn* the Monday takeaway, or is the takeaway merely stated at the end? If a load-bearing block produces no feeling change, cut or merge it — two blocks that feel the same are one beat. If the close needs a feeling that never appeared, the outline isn't done. One well-placed contrarian take stands out most on stages that have converged on a consensus.
*(This outline → emotional-storyboard method is distilled from Knowatoa's `talk-storyboard` and `presentation-outline` skills — [ai-visibility-skills](https://github.com/Knowatoa/ai-visibility-skills), MIT, credited.)*
## The Recording Is the Real Audience
The room holds 200 people for 25 minutes; the recording works for years. Design for both at once:
- **Talks get transcribed, and transcripts get crawled and cited by AI assistants** — the same compounding as podcast guesting. Say the important things in liftable form: your company name next to your category ("we build X, the Y for Z"), numbers spoken aloud rather than gestured at on a slide, and your quotable one-liner delivered *on a beat the room will feel* — the sentence you want quoted needs to sit where the energy peaks, or it dies in the transcript too (→ **ai-seo**'s text-layer logic).
- **Slides are not the asset.** Anything that exists only visually (the key number, the framework name) doesn't exist for the transcript, the podcast version, or the attendee retelling it — speak it.
- **Get the recording.** Confirm before accepting the slot that you'll receive it and may republish. If the event doesn't record, record your own re-delivery of the talk within a week while it's tight.
## Around the Talk
- **Before**: post the *why this topic now* angle; invite specific people to your session; make plans to meet the other speakers — speaker-to-speaker is the strongest networking lane at any event.
- **During**: end with one clear, low-friction pointer (a memorable URL to the slides + a related asset — which doubles as a lead magnet, → **lead-magnets**). Q&A questions are content research; note every one.
- **After**: publish the recording + a written version of the talk (→ **content-strategy**), clip the peak beats (→ **video**), follow up with everyone who asked a question or approached you — same 24–48h window as every event motion, and these are the warmest leads an event produces.
- Roll the talk forward: the same core talk, sharpened by each delivery's Q&A, can run a full conference season. Retire it when the Q&A stops surprising you.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |