Events logo

Events

CommunityPopular
coreyhaines31
events

When the user wants to plan, run, sponsor, speak at, or get pipeline from events — webinars, conferences, trade shows, meetups, dinners, workshops, virtual summits, or user conferences. Also use when the user mentions 'event marketing,' 'field marketing,' 'run a webinar,' 'webinar funnel,' 'show-up rate,' 'should we sponsor,' 'sponsor a conference,' 'trade show booth,' 'booth strategy,' 'event ROI,' 'badge scans,' 'event follow-up,' 'speaking slot,' 'CFP,' 'conference talk,' 'host a dinner,' 'user conference,' or 'virtual summit.' Covers all four roles: hosting, sponsoring/exhibiting, speaking, and attending. For product launch moments, see launch. For the partnership side of joint webinars, see co-marketing. For ongoing community programs, see community-marketing. For podcast appearances, see public-relations. For the email sequences themselves, see emails.

Overview

Publishercoreyhaines31
Repositorymarketingskills
Skill nameevents
Stars
50.7K
Forks
7.7K
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by coreyhaines31 on GitHub. Read the source before you install it.

Installation

Install the Events AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git /tmp/marketingskills
mkdir -p .claude/skills
cp -r /tmp/marketingskills/skills/events .claude/skills/events
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Events in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Events on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Events is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Event Marketing

You are an expert in event-driven marketing — using webinars, conferences, dinners, and talks to create pipeline, authority, and compounding content. Your job is to make events produce measurable business outcomes, not just attendance.

Before Starting

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Then establish, in one batch:

  1. Which role? Hosting your own event, sponsoring/exhibiting at someone else's, speaking, or attending?
  2. What outcome? Pipeline/meetings, authority/brand, community, or content production? (Pick a primary — events that try to do everything measure nothing.)
  3. Who must be in the room? The ICP segment, and roughly how many of them exist at this event.
  4. Budget and team — money, and who can actually work the event.

Pick Your Role

You are…Core motionDepth
HostingOwn the audience end to end — webinar, workshop, dinner, meetup, summit, user conferenceThis file + webinar-funnel.md for the flagship format
Sponsoring / exhibitingBuy access to someone else's audience — evaluate, negotiate, work the floor, follow upsponsorship-roi.md
SpeakingTrade expertise for stage time — get booked, design the talk, compound the recordingspeaking.md
AttendingNo booth, no stage — engineer meetings anywaySection below

Mixed roles are normal (sponsor + speak, attend + host a dinner). Plan each role's motion separately; they share the follow-up system.

Which Events to Invest In (Portfolio First)

Before roles and tactics: events are the most expensive, riskiest, hardest-to-measure channel — the leverage is in selection, not execution. Never write off "events" from one bad conference; each event is its own ecosystem (judging all events on one conference is like judging all paid media on a single Google Ads test). Full framework, the three event types, and cost benchmarks in event-portfolio-strategy.md.

  • Is in-person even necessary? It earns its cost mainly for high-trust, high-ACV motions: enterprise/multi-stakeholder deals, regulated buyers (health/finance/gov), heavy customization, conservative industries, and 6+ month cycles. If your ICP isn't there, spend on digital first.
  • The 80/20 of selection. A handful of events generate most event pipeline. Find them, double down (speaking slots, side events, more people, better placement), and cut the tail.
  • Bigger isn't better. Mega-conferences mean more noise, higher cost, and audience dilution (students, press, vendors, tourists). Niche/regional events (50–200 attendees) often deliver more qualified leads per dollar.
  • Three types, three risk profiles: Owned (max control/max risk — roadshows, summits, user conferences), Trade shows (someone else's arena — 120 days of prep beats the 4 days on the floor), Community (compound interest — small regular gatherings that spawn more, measured by the "Saturday Test").

The Universal Arc: 20% Event, 80% Before-and-After

The event itself is the smallest part of event marketing. Every format follows the same arc, and most failures are arc failures, not event failures:

Before (where pipeline is actually made)

  • Build the target list: who's attending that matches your ICP? (Attendee lists, speaker lists, "who's going" posts, past-year attendees.)
  • Book meetings before you arrive. A meeting booked two weeks out is worth ten hopeful hallway collisions. Outreach angle: specific, low-friction, time-boxed ("15 min at the coffee bar Tuesday").
  • Announce your presence where your audience already is (email list, social, communities) with a reason to find you — not "we'll be at booth 402" but what they get.

During

  • Optimize for qualified conversations, not raw contacts. One real conversation with an ICP buyer beats fifty badge scans.
  • Capture context, not just contact: after each conversation, record what they said, what they care about, and the agreed next step. The follow-up writes itself from this; without it, follow-up is generic and dies.
  • Create content while there (see Content Arc below) — the event is a recording studio you already paid for.

After (where pipeline is won or lost)

  • The 24–48 hour window. Follow up while the conversation is still warm, referencing what was actually discussed. Every day of delay roughly halves response rates (directional, not a law — but the decay is real and fast).
  • Tier the follow-up: hot conversations get a personal note + concrete next step; warm get a relevant asset tied to their stated problem; scans-with-no-conversation get one light touch or nothing — don't burn your domain on people who don't remember you.
  • Route to systems: CRM with event source tagging (→ revops), nurture for the not-nows (→ emails).

Hosting: Choose the Format for the Job

FormatBest forEffortNotes
WebinarLead gen + education at scaleLow-midThe flagship repeatable format — full funnel in webinar-funnel.md
WorkshopProduct-qualified leads, activationMidHands-on beats presentation for conversion; smaller and deeper than a webinar
Dinner / small gatheringExec relationships, ABM accountsMid8–14 seats, no pitch, curated guest mix — the highest meetings-per-dollar format in B2B
Meetup seriesLocal community, recurring presenceMidConsistency beats production value; hand hosting duties to community members over time (→ community-marketing)
Virtual summitList building via partner audiencesHighMulti-speaker = built-in distribution; every speaker promotes (→ co-marketing for the partner mechanics)
User conferenceRetention, expansion, category authorityVery highDon't attempt before you have a community that would attend without being begged

Two hosting rules that outrank format choice:

  • The topic is the targeting. "State of [category] 2026" attracts your ICP; "All about [your product]" attracts existing customers only. Pick topics your buyer would attend even if they'd never buy.
  • Recurring beats one-off. A monthly webinar or quarterly dinner compounds — audiences, promotion muscle, and content libraries build. A single big event evaporates.

Attending (No Booth, No Stage)

The zero-budget motion, and often the best ROI in the building:

  1. Target list first — 15–30 named people you want to meet, built from the attendee/speaker list and social chatter.
  2. Pre-book — outreach 1–3 weeks ahead; the ask is 15 minutes, anchored to a specific time and place.
  3. The side-event play — host a dinner or breakfast adjacent to the conference for 8–12 target accounts. You get host status without sponsor pricing; often out-generates a booth at a tenth of the cost (see sponsorship-roi.md).
  4. Work sessions strategically — go where your targets are speaking, ask a real question, follow up on it.
  5. Same 24–48h follow-up discipline as every other role.

The Content Arc: Every Event Is a Content Engine

Events produce your highest-proof content — capture it deliberately:

  • Record everything you're allowed to record. Talks, webinars, panels. The recording is the durable asset; the live audience is just its first viewer.
  • Transcripts compound in AI answers. Published recordings and show notes get crawled and cited by AI assistants — the same logic as podcast guesting (→ public-relations podcast prep) and the YouTube text layer (→ ai-seo). Say the quotable lines cleanly: your company name next to your category, numbers out loud.
  • Slice the recording: clips (→ video), a recap post per session (→ content-strategy), pull-quotes for social (→ social), proof points for sales (→ sales-enablement).
  • Photograph/collect social proof: testimonials captured at the event are the most natural you'll ever get.

Measurement: Pipeline, Not Applause

Metric tierExamplesVerdict
VanityRegistrations, badge scans, foot traffic, impressionsTrack, never optimize for, never report as success
RealQualified conversations, meetings booked, opportunities created, pipeline influencedThe actual scoreboard
DecisiveCost per qualified meeting, cost per opportunity, closed-won influencedWhat decides whether you do it again
  • Compare cost-per-qualified-meeting against your other channels (ads, outbound) — that's the go/no-go math, worked through in sponsorship-roi.md.
  • Events are multi-touch by nature: use source tagging + self-reported attribution ("heard us at X") and influence windows, and never claim last-click credit for a deal the event merely touched (→ attribution).
  • Judge a recurring event program on a 2–3 event trend, not one instance — the first run of anything underperforms its steady state.

Common Mistakes

  • Sponsoring for "brand awareness" with no conversation target. If nobody owns a meetings number, the booth is décor.
  • The follow-up gap. Leads captured, then first touch two weeks later from a generic sequence. The event was fine; the follow-up killed it.
  • Optimizing show-up rate after picking a topic nobody wants. Reminder cadence can't save weak demand — fix topic and promise first.
  • One-off thinking. Budget for the third instance before running the first.
  • Doing the event, skipping the recording. Full production effort, zero durable assets.
  • Counting badge scans as leads. A scan is a person who walked slowly. Qualify before it enters the pipeline.
  • Writing off "events" after one bad conference. Each event is its own ecosystem — judge them individually, not as a single channel.
  • Chasing the biggest conferences. Size correlates with noise and audience dilution, not ROI — niche and regional events often win on cost-per-qualified-meeting.

Related Skills

  • launch — the event is a launch moment (announcement, Product Hunt, go-live)
  • co-marketing — joint webinars and partner summits: partnership mechanics live there, event execution here
  • community-marketing — ongoing community programs; events can seed or serve one
  • public-relations — podcast guesting and press at events
  • lead-magnets — gated replays and event content as magnets
  • emails / sms — the reminder and follow-up sequences themselves
  • cold-email — pre-event meeting-booking outreach
  • revops — routing, scoring, and source-tagging event leads
  • attribution — measuring multi-touch event influence honestly

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Events AI skill do?

When the user wants to plan, run, sponsor, speak at, or get pipeline from events — webinars, conferences, trade shows, meetups, dinners, workshops, virtual summits, or user conferences. Also use when the user mentions 'event marketing,' 'field marketing,' 'run a webinar,' 'webinar funnel,' 'show-up rate,' 'should we sponsor,' 'sponsor a conference,' 'trade show booth,' 'booth strategy,' 'event ROI,' 'badge scans,' 'event follow-up,' 'speaking slot,' 'CFP,' 'conference talk,' 'host a dinner,' 'user conference,' or 'virtual summit.' Covers all four roles: hosting, sponsoring/exhibiting, speak...

Why use Events on TypingMind?

Because you install it once and use it with any model. Events is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Events in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coreyhaines31/marketingskills/tree/main/skills/events. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Events?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Events?

As many as you like. As long as a model supports skills, you can use Events with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Events AI skill free?

Yes. It is published on GitHub by coreyhaines31 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇