Kai Webinar logo

Kai Webinar

Community
cgallic
kai-webinar

Plan webinar and event marketing — topic selection, promotion strategy, content production, registration flow, and post-event follow-up sequences. Use when "webinar", "event marketing", "virtual event", "live event", "workshop", "online event", or any request to plan, promote, or produce a webinar or marketing event.

Overview

Publishercgallic
Repositorykai-cmo-harness
Skill namekai-webinar
Stars
61
Forks
8
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Kai Webinar 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.
    https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-webinar
  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/cgallic/kai-cmo-harness.git /tmp/kai-cmo-harness
mkdir -p .claude/skills
cp -r /tmp/kai-cmo-harness/harness/skills-v2/kai-webinar .claude/skills/kai-webinar
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kai Webinar 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 Kai Webinar 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 Kai Webinar 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.

/kai-webinar — an event with an audience in the room and a next step after it

Objective

A complete event marketing package the team can execute without writing anything else: registration page copy, the promotion sequence that fills the seats, the event content structure, and the follow-up that converts attendees and no-shows. The deliverable is the whole arc — a webinar with registrations and no follow-up is a cost, not a campaign.

Registration targets are set from the show rate, not from signups. Budget 40–50% show rate when sizing the goal.

Done when

Work type campaign — floor E5/C3/O4 (harness/eco-floors.yaml), contract harness/skill-contracts/campaign.yaml. A campaign is composite: it is CLOSED only when every child asset is CLOSED and the campaign-level threshold is met. One unsent reminder keeps it open.

  • E5 — every asset reached its target and was read back: the registration page returns 200 with the approved copy, the ESP reports each send against the approved segment, the social posts return permalinks that match.
  • C3 — four_us_score at 10/16 for emails and 12/16 for the registration page, banned_word_check clean, zero AI slop, and a named non-producer read the package end to end.
  • O4 — registrations, show rate, and the post-event next-step conversion clear thresholds declared before promotion opened. Metrics window 45 days.

Assets stay drafts until a human approves them. This skill does not send, publish, or schedule anything.

Constraints

  • Read MARKETING.md from the project root before asking the user anything. If it does not exist, build it from the codebase — CLAUDE.md, README.md, PROJECT.md, package.json, landing pages, email/ad/analytics config — using the template from /kai-email-system, and confirm the draft. Do not open with discovery questions the repo can answer.
  • Know these before planning: event type (webinar, workshop, panel, AMA, demo, conference talk), goal (lead gen, nurture, launch, thought leadership, retention), persona, topic candidates, speakers, platform, date and timezone, registration target, and what happens after the event. Anything MARKETING.md answers is not a question.
  • Score the topic before producing anything. Three tests: audience pain relevance (does it solve a real problem?), competitive differentiation (can only we teach this?), lead quality potential (will the right people show up?). A topic that fails differentiation produces a webinar nobody remembers.
  • Registration headlines promise a result, not a subject. "Learn How to X" becomes "Walk Away With a Working X".
  • Harness writing rules apply to every asset: conditions after the main clause, instructions start with verbs, short sentences, bold the answer. No banned words, no AI slop.
  • Subject lines under 50 characters, no spam triggers. Exactly one clear next step per asset.
  • Gate failures get named fixes. Max 2 auto-retry cycles; after that, surface the specific failures to a human.
  • No live-channel mutation. Nothing is sent, posted, or published without human approval.

Context

NeedLoad
Event and webinar mechanicsknowledge/playbooks/event-webinar-marketing.md
Persona selectionknowledge/personas/_persona-index.md
Product, ICP, voice, channelsMARKETING.md (project root)
Email format contractharness/skill-contracts/email-lifecycle.yaml
Registration/landing page contractharness/skill-contracts/landing-page.yaml
Gatespython scripts/quality_gates/four_us_score.py <file> · banned_word_check.py <file>

Promotion timeline — the 4-week standard, worth carrying inline because it sets the asset count:

WeekMoveAssets
1AnnounceEmail to list, social posts, partner outreach
2BuildBlog or content teaser, speaker spotlights
3PushReminder emails, social proof (registrant count), urgency
4FinalLast-chance emails, day-of reminders at 1 hour and 15 minutes

Email sequence — confirmation with calendar invite, 1-week reminder with agenda preview, day-before with prep instructions, 1-hour reminder, post-event replay plus resources for attendees, post-event "you missed this" for no-shows, then a 3–5 email nurture.

Registration page carries headline, value props, speaker bios, agenda, and CTA. Event content plan covers structure, key points, transitions, audience interaction moments, plus slides, handouts, worksheets, and resource lists.

Output goes to workspace/ as webinar-[topic-slug]-YYYY-MM-DD.md: strategy brief, registration page copy, promotion emails, social calendar, event content outline, post-event sequence, dated promotion timeline, and the gate pass/fail summary.

Escalate when

  • The registration target implies a list or audience size the brand does not have, and paid promotion would be needed to close the gap.
  • The topic cannot pass the differentiation test with the brand's actual expertise.
  • Speakers are external and their bios, claims, or likeness rights are unconfirmed.
  • The date leaves less than the promotion timeline requires.
  • Any asset would need to send or publish before a human has approved it.

Frequently asked questions

What does the Kai Webinar AI skill do?

Plan webinar and event marketing — topic selection, promotion strategy, content production, registration flow, and post-event follow-up sequences. Use when "webinar", "event marketing", "virtual event", "live event", "workshop", "online event", or any request to plan, promote, or produce a webinar or marketing event.

Why use Kai Webinar on TypingMind?

Because you install it once and use it with any model. Kai Webinar 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 Kai Webinar in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-webinar. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kai Webinar?

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 Kai Webinar?

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

Is the Kai Webinar AI skill free?

It is published on GitHub by cgallic. Check the repository for licensing terms. 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 👇