Kai Podcast logo

Kai Podcast

Community
cgallic
kai-podcast

Launch a podcast or plan podcast guest strategy — format, content planning, episode production, guest outreach, and distribution. Use when "podcast", "start a podcast", "podcast marketing", "podcast guest", "podcast strategy", "be a podcast guest", "launch a show", or any request related to podcast creation or guest appearances.

Overview

Publishercgallic
Repositorykai-cmo-harness
Skill namekai-podcast
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 Podcast 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-podcast
  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-podcast .claude/skills/kai-podcast
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kai Podcast 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 Podcast 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 Podcast 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 root note: knowledge/, harness/, and scripts/ paths in this skill live in the Kai install, not the user's project. Resolve them against the first ancestor directory of this SKILL.md that contains a knowledge/ folder (the Kai plugin root, ~/.claude/kai, or the kai-cmo-harness repo). MARKETING.md, memory/, and any output files live in the current project. If a referenced scripts/ command is not available in this install, say so, skip it, and continue with the file-based guidance — never fabricate its output.

Objective

A podcast operation the user can start next week — either their own show (Host mode) or a booked-guest pipeline (Guest mode). Host mode ends with a show concept, ten mapped episodes, a production and distribution workflow, and the templates that keep every episode consistent. Guest mode ends with a speaker one-sheet, a real target-show list, and pitches specific enough that a host replies.

Pick the mode before anything else. Host and Guest share almost no assets.

Done when

Work type strategy-plan — floor E3/C3/O1 (harness/eco-floors.yaml). The package is a plan, not a live channel, so E tops out at approval of the exact bytes.

  • E3 — a named human approved the delivered package at workspace/podcast-[host|guest]-YYYY-MM-DD.md.
  • C3 — banned_word_check clean, zero AI slop (every sentence earns its place), Four U's at 12/16 for show descriptions and episode outlines and 10/16 for pitch emails, and a non-author read the package end to end. Max 2 retry cycles, each naming the specific failing dimension.
  • O1 — the plan names its metric with a baseline, a threshold, a window, and an owner: episodes published and downloads per episode (Host), or pitches sent, booking rate, and appearances aired (Guest).

Two floors this skill does not own: an episode actually published is blog-post-class published content, and a pitch email actually sent is cold-email (E5/C4/O3). Neither is SHIPPED by this skill.

Constraints

  • Read MARKETING.md from the project root first. 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 ask the user what the product is.
  • Know these seven things before planning: mode (Host or Guest); goal (awareness, thought leadership, lead gen, networking, backlinks); target persona; topic territory and unique angle; existing assets that prove expertise; commitment level (cadence for Host, appearances per month for Guest); equipment and editing capability.
  • Ingest before deriving. Given an RSS feed, episode URL, transcript, raw audio, or show notes, record it in workspace/podcast/_ingest-log.md first: source locator, permission status (owned / guest-approved / public citation / internal review / unknown), episode metadata (title, guest, publish date, runtime, canonical URL), transcript status (provided / generated / partial / missing / low confidence), and repurpose candidates (quotes, stories, objections, frameworks, clip timestamps).
  • Source locations are preserved for every quote, claim, and clip candidate. Public RSS metadata is for planning only — it never implies a host or guest endorses anything.
  • No fabricated authority. Ideas from a transcript are attributed to the speaker who said them or kept as internal notes. Never present transcript material as the user's own expertise.
  • Approval before anything leaves the workspace — show notes, clips, outreach, and guest quotes all require human sign-off. This skill drafts.
  • Pitch specificity is a hard rule. A pitch that does not reference the specific show — an episode, a recurring theme, the host's stated interest — fails regardless of its Four U's score. Generic pitches are the reason guest outreach dies.
  • Guest pitches are cold outreach. Sender identity, opt-out, and consent basis follow harness/references/cold-email-rules.md before any send.
  • Format targets: show description under 600 characters for directories; 20–45 min interview episodes, 10–20 min solo; 3–5 candidate show names with availability checked; 20–50 target shows for Guest mode.

Context

NeedLoad
Show format, production, distribution mechanicsknowledge/channels/podcast.md
Launch strategy, guest booking, promotionknowledge/playbooks/podcast-marketing.md
Which persona the show is forknowledge/personas/_persona-index.md
Rules for mining third-party audio, video, or transcriptsharness/references/transcript-video-research-rules.md
Cold outreach compliance for host pitchesharness/references/cold-email-rules.md
Product, ICP, voice, current channelsMARKETING.md (project root)
Turning one episode into channel assets/kai-repurpose

Host package: show concept (name, format, length, angle), first ten episode outlines, production workflow, distribution plan (Apple, Spotify, YouTube, RSS, website embed), promotion plan (social clips, email, cross-promotion, guest sharing), episode template, show notes template, interview question set.

Guest package: speaker one-sheet (bio, three signature topics, audience value, past appearances), target show list with rationale, three pitch variants sized to different shows, talking points per topic, post-appearance follow-up, and a tracking structure covering shows pitched, status, air dates, and results.

Output goes to workspace/ as podcast-[host|guest]-YYYY-MM-DD.md. Ingest notes go to workspace/podcast/_ingest-log.md. Same paths as v1.

Escalate when

  • Permission status for a transcript, clip, or guest quote is unknown and the asset is needed.
  • The user wants a guest quote or host endorsement published without written approval.
  • The claimed expertise behind a signature topic is not supported by any existing asset.
  • Cadence commitment does not match available production capacity — a show that dies at episode four is worse than no show.
  • A pitch would require claiming an experience or result the user does not have.

Frequently asked questions

What does the Kai Podcast AI skill do?

Launch a podcast or plan podcast guest strategy — format, content planning, episode production, guest outreach, and distribution. Use when "podcast", "start a podcast", "podcast marketing", "podcast guest", "podcast strategy", "be a podcast guest", "launch a show", or any request related to podcast creation or guest appearances.

Why use Kai Podcast on TypingMind?

Because you install it once and use it with any model. Kai Podcast 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 Podcast 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-podcast. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kai Podcast?

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 Podcast?

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

Is the Kai Podcast 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 👇