Kai Sales Meeting Prep

Community

cgallic

kai-sales-meeting-prep

Prepare sales meetings from SDR replies, account dossiers, CRM notes, call notes, or transcripts. Produces account brief, buyer map, pain hypotheses, discovery questions, objection plan, meeting agenda, CRM handoff, follow-up email, and outcome memory. Use when "sales meeting prep", "prep this demo", "discovery call", "booked meeting", "SDR handoff", "post-call follow-up", "call notes", "sales transcript", or any request to prepare or follow up on sales development meetings.

Overview

Publisher	cgallic
Repository	`kai-cmo-harness`
Skill name	`kai-sales-meeting-prep`
Stars	61
Forks	8
Bundled files	Instructions only
Links	Skill source Repository Homepage

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 Sales Meeting Prep AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-sales-meeting-prep
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-sales-meeting-prep

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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-sales-meeting-prep .claude/skills/kai-sales-meeting-prep

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kai Sales Meeting Prep 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 Sales Meeting Prep 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 Sales Meeting Prep 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-sales-meeting-prep — Meeting Loop

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 one-page briefing a human seller can walk into a call with, built only from sourced signals: who the account is, what is known versus inferred versus missing, the pain hypotheses worth testing, the discovery questions that test them, the objections likely to land and the proof each one needs, and the next step being asked for. After the call, the same file carries the sourced outcome — commitments separated from assumptions — plus a follow-up draft, proposed CRM records, and memory candidates.

The load-bearing judgment is the known/inferred/missing split. A brief that presents an inference as a fact makes the seller confidently wrong in front of the buyer.

Done when

Work type internal-research — floor E2/C2/O0 (harness/eco-floors.yaml). Nothing in this skill leaves the workspace, so E tops out at approval of the exact file and there is no provider read-back.

E2 — the meeting file exists at its package path and satisfies harness/skill-contracts/sales-meeting-prep.yaml.
C2 — banned_word_check passes, and every extracted fact carries a prospect_said / seller_said / inferred / missing label.
O0 — no outcome obligation on the brief itself. Internal work of this type is SHIPPED-terminal.

Any live action the brief proposes is different work with a different floor: sending the follow-up email, mutating CRM, or booking calendar time each need explicit human approval first.

Constraints

No invented facts. Pain, budget, authority, timeline, competitor usage, and prior relationship are never assumed. Missing budget, authority, or timeline is missing_data, not negative proof — score it as absent only when the prospect clearly disqualified it.
Transcripts and call notes are source material, not verified product facts. Attribute a statement only when speaker and context are clear.
Label every hypothesis as a hypothesis. No promised outcome without source-backed proof.
No live mutation. CRM records, tasks, stage changes, and calendar actions are written as proposals with an Approval needed field. This skill does not touch CRM, sequencer, calendar, SMS, phone, or email systems.
One page unless the user asks for an enterprise dossier.
Post-call, separate prospect commitments from seller assumptions. A commitment the seller inferred is not a commitment.
Memory candidates stay candidates until a human approves promotion.

Meeting quality score (0–100) — the rubric, applied only to sourced components:

Component	Points
Fit	25
Pain clarity	20
Urgency	20
Authority or path to authority	15
Next-step specificity	10
Evidence completeness	10

Post-call extraction captures: pain stated, current workflow, trigger, desired outcome, decision process, stakeholders, timeline, budget signal, competitor or alternative, objection, commitment, next step. Follow-up actions carry owner, due date, approval needed, and a source line or note reference.

Context

Need	Load
Output structure, required fields, gate thresholds	`harness/skill-contracts/sales-meeting-prep.yaml`
Package schema, ledger fields, memory ledger shape	`harness/skill-contracts/sdr-package.yaml`
Account dossier, contact row, reply triage, source evidence	`workspace/sdr-operator/<package-slug>/`
Product context, offer, claim evidence	`MARKETING.md` (project root)
The reply that triggered the meeting	`/kai-sdr-reply-triage` output in the same package

Meeting types — pick one; it sets what the brief biases toward:

Type	Use when	Output bias
`first_discovery`	First call from SDR motion	Pain, urgency, owner, current process, next step
`demo_prep`	Prospect requested demo or walkthrough	Use case, proof, objections, tailored flow
`referral_intro`	Prospect routed to someone else	Context transfer, permission trail, concise ask
`revival_call`	Old opp or not-now reply returns	What changed, prior blocker, new trigger
`post_call_follow_up`	Notes or transcript available	Summary, commitments, next step, CRM update

Output goes to workspace/sdr-operator/<package-slug>/meetings/<meeting-id>.md. Same path as v1 — downstream tooling does not branch on version.

Escalate when

Account, contact, source, or reply context is missing and the brief would rest on assumption — write the gap, do not fill it.
The transcript conflicts with the account record on a fact the call depends on.
A proposed follow-up would make a claim no source supports.
The reply or call touches a regulated, legal, or sensitive matter.
The next step requires a CRM, calendar, or send action and no approver is named.

Frequently asked questions

What does the Kai Sales Meeting Prep AI skill do?

Why use Kai Sales Meeting Prep on TypingMind?

Because you install it once and use it with any model. Kai Sales Meeting Prep 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 Sales Meeting Prep 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-sales-meeting-prep. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kai Sales Meeting Prep?

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 Sales Meeting Prep?

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

Is the Kai Sales Meeting Prep 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

Everything Claude Code

affaan-m

CommunityPopular

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Discord User Post

Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots,…

Test Audit

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only…

Feishu Perm

Feishu collaborator and permission workflows. Activate when the user explicitly asks to inspect or change sharing, permissions, or collaborators.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

kai-sales-meeting-prep — Meeting Loop

Objective

Done when

Constraints

Context

Escalate when

Frequently asked questions

Related AI Skills

Set up your own AI workspace now