Call Prep logo

Call Prep

Community
davekilleen
call-prep

Prepare a sourced, read-only brief for a person or account call

Overview

Publisherdavekilleen
RepositoryDex
Skill namecall-prep
Stars
481
Forks
130
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 davekilleen on GitHub. Read the source before you install it.

Installation

Install the Call Prep 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/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/_available/sales/call-prep .claude/skills/call-prep
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Call 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 Call 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 Call 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.

Purpose

Build a concise call brief from dated person, account, deal, task, and interaction evidence. Keep sourced context separate from suggested questions and unknowns.

Usage

  • /call-prep [person]
  • /call-prep [company]

Evidence, authority, and recovery

Set the call brief's as-of timestamp, timezone, participant, and call time. Make freshness relative to that as-of time. For each interaction, commitment, signal, account field, objective, and objection, record its source path or record ID and event date. File modified time is not an event date.

  • Treat an unknown objective and unknown objection as unknown. Write Unknown — ask; do not infer intent, buying stage, sentiment, priority, or likely objection from role, company, silence, or a generic sales pattern.
  • Separate sourced facts, the user's stated goals, hypotheses, and suggested questions. A useful question is not evidence that its premise is true.
  • Show contradictory sources and dates side by side. Do not silently choose one.
  • Never invent facts, quotes, commitments, dates, outcomes, customer counts, product capabilities, prices, ROI, payback, rollout time, or integration claims.
  • Keep call prep read-only by default. A recommendation is not permission to update a person, account, deal, or task.
  • Preview any requested change, require explicit confirmation from the authorized human, then read back the saved record. If a write or read-back fails, report possible partial state and stop before retrying.

Method

1. Resolve identity and call scope

Confirm the exact person/account and disambiguate duplicate names. Confirm:

  • scheduled call time and timezone;
  • participants and their sourced roles;
  • call type only if supplied or recorded;
  • the user's objective, if stated;
  • the review window for prior interactions;
  • authoritative sources for person, account, deal, and commitments.

If identity remains ambiguous, return the candidates and ask; do not merge records.

2. Build a source ledger

Collect only the context needed for this call:

ItemEvidence rule
Person roledated person/account source
Relationshipexact observations; no personality inference
Recent interactionscanonical event date and source
Commitmentsexact owner, due date, status, source
Deal/account stateauthoritative record and source date
Pain or requestquote-safe summary tied to an interaction
Product/commercial claimcurrent authoritative product or commercial source

Deduplicate repeated meeting or CRM records by stable ID. Preserve materially different accounts and contradictions.

3. Check freshness and completeness

For each source, show event date and read as-of time. Apply a stale label only if the user or account policy defines a freshness rule; otherwise show elapsed time and Freshness assessment: Unknown.

Mark these explicitly when absent:

  • Call objective: Unknown — ask the caller
  • Customer objective: Unknown — ask on the call
  • Potential objections: Unknown — no sourced objection
  • Account health: Unknown — no configured rubric/current result
  • Next decision: Unknown

Do not convert missing evidence into a negative assessment.

4. Prepare discussion material

Discussion points must trace to a source. Suggested questions may explore an unknown, but must be phrased without assuming the answer.

Good shape:

  • Observed: “[dated source summary]”
  • Unknown: “[specific missing fact]”
  • Question: “[neutral question to resolve it]”
  • Why now: “[link to call objective or commitment]”

Commercial responses must use current approved material. If price, ROI, rollout, customer proof, or product support is not sourced, say Unknown — verify before use and do not improvise.

5. Verify the brief

Before presenting:

  • reconcile every commitment with its owner and due date;
  • check links point to the records actually read;
  • ensure dates use one stated timezone;
  • ensure every quote is exact or clearly paraphrased;
  • ensure no suggested objection appears as a fact;
  • ensure desired outcomes are the user's stated goals, not invented intent.

Output contract

markdown
# Call prep: [person] — [company]

**Call:** [time and timezone]
**Brief as of:** [timestamp]
**Identity evidence:** [source/date]
**Call objective:** [user-stated source or Unknown]

## What is known
- [Fact] — [source, event date]
- [Fact] — [source, event date]

## Recent interactions
| Date | Interaction | Decisions/commitments | Source |
|---|---|---|---|

## Open commitments
| Owner | Commitment | Due/status | Source/date |
|---|---|---|---|

## Unknowns and contradictions
- [Unknown or both conflicting sources/dates]

## Questions to ask
1. [Neutral question tied to an unknown]
2. [Question tied to a sourced objective]

## Talking points
- [Sourced point, with approved claim source]
- [Unknown — verify before use]

## Desired outcome
- [User-stated goal or Unknown]

## Quick links
- [Only records actually read]

Placeholders define structure only; they are not sample facts.

Controlled follow-up

After the call, offer a separate update plan. For each requested write:

  1. identify the exact target;
  2. show the complete before/after diff or payload;
  3. separate independent writes so one approval does not authorize another;
  4. require explicit human confirmation;
  5. perform only the confirmed write;
  6. read back and reconcile it with the preview.

On failure, keep the brief unchanged, disclose possible partial state, re-read the target, and require a fresh preview before any retry.

Frequently asked questions

What does the Call Prep AI skill do?

Prepare a sourced, read-only brief for a person or account call

Why use Call Prep on TypingMind?

Because you install it once and use it with any model. Call 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 Call Prep in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/_available/sales/call-prep. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Call 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 Call Prep?

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

Is the Call Prep AI skill free?

It is published on GitHub by davekilleen. 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 👇