Renewal Prep logo

Renewal Prep

Community
davekilleen
renewal-prep

Use when preparing an evidence-backed brief for an upcoming customer renewal from contract, ARR, dated outcomes, usage, and risk evidence. Not for health scoring; use health-score.

Overview

Publisherdavekilleen
RepositoryDex
Skill namerenewal-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 Renewal 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/customer-success/renewal-prep .claude/skills/renewal-prep
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Renewal 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 Renewal 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 Renewal 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.

When to use

Use for a named account and upcoming renewal when the requester needs a traceable summary of contract terms, ARR, value delivered, risk, unknowns, and preparation questions. Confirm the account identity, renewal scope, and as-of date before gathering evidence.

Do not use this skill to renew or terminate a contract, set pricing, promise commitments, approve strategy, update CRM, or communicate with the customer. Not for health scoring, legal contract interpretation, or a commercial decision made on behalf of a human authority.

Inputs and source discipline

  1. Record account identity, contract/order form and amendments, renewal date/term, ARR or other commercial measure, currency, source dates, date checked, and explicit as-of date. Prefer the latest signed contract and amendments, then billing/ARR evidence, then CRM facts, then dated customer-success notes and customer communication. Cite every source; never invent a missing date, value, owner, or term.
  2. Keep contract value, billed ARR, estimated value, usage, support events, and outcomes in separate fields. Reconcile units, currency, period, and account identity before comparing. Treat a CRM field as a lead to evidence, not proof when it conflicts with a signed source.
  3. For value delivered, collect each dated outcome with its source, date, and relationship to the product. Do not turn activity, a positive sentiment, or an unverified claim into an outcome or ROI metric.

Method

  1. Work read-only and build an evidence ledger for contract/ARR/renewal facts, adoption and support context, and dated outcomes. State whether each item is observed, inferred, or a recommendation.
  2. Verify the renewal date, term, notice conditions, and ARR from cited contract or billing evidence. Calculate any time-to-renewal only from the supplied reference date and state the date basis; if dates conflict, show the contradiction rather than selecting one silently.
  3. Separate risk from unknown: call something a risk only when dated evidence shows a concern, exposure, or likelihood of an adverse renewal outcome; call it unknown when the evidence needed to assess it is missing, stale, or contradictory. Do not infer risk from silence alone.
  4. Present pricing, commitments, packaging, strategy, and customer communication as options and approval questions. Include expansion ideas only when need and fit are sourced; never invent a value or imply that a recommendation is approved.

Truth and uncertainty rules

Use observed for a contract fact, ARR value, or dated outcome directly supported by a source, inferred for an interpretation, unknown for missing evidence, stale for evidence outside the relevant period or freshness, and contradictory when credible sources disagree. State confidence and its basis. Never invent dates, metrics, owners, intent, money, percentages, causes, status, or evidence. Recommendations are not human decisions.

Output contract

Return a renewal brief containing:

  • account, contract/order form/amendment citations, ARR and currency, renewal date/term, as-of, source dates, and confidence;
  • a value-delivered ledger of dated outcomes with evidence, plus clearly marked unknown ROI or unsupported claims;
  • adoption/support context, risks with evidence, and unknowns kept in separate sections;
  • pricing, commitments, strategy approval, and customer communication questions explicitly marked for human authorization;
  • non-binding options and next checks with an owner only when that owner is sourced; and
  • a source register, stale inputs, unresolved contradictions, and a clear list of evidence not found. Do not present the brief as an approved renewal plan.

Safety and write boundaries

Remain read-only by default. Do not edit contracts, billing, ARR, CRM, pricing, commitments, or customer records, and do not send customer communication. If a write, export, pricing change, commercial action, or other communication is requested, preview the exact target, content, audience, and side effects; redact secrets or unapproved personal/confidential content; wait for explicit confirm from the authorized human owner; then perform only that approved action.

Verification and recovery

Read back the contract, latest amendment, ARR evidence, renewal dates, and every cited dated outcome. Reconcile ARR and currency to the contract/billing basis, check date arithmetic and account identity, and fail closed when a check cannot be completed. If a source read fails or evidence conflicts, preserve the brief, mark the affected conclusion unknown or blocked, record the failure, and rerun after refresh. Never silently resolve a contract contradiction or promote an inferred risk to fact.

Frequently asked questions

What does the Renewal Prep AI skill do?

Use when preparing an evidence-backed brief for an upcoming customer renewal from contract, ARR, dated outcomes, usage, and risk evidence. Not for health scoring; use health-score.

Why use Renewal Prep on TypingMind?

Because you install it once and use it with any model. Renewal 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 Renewal 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/customer-success/renewal-prep. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Renewal 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 Renewal Prep?

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

Is the Renewal 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 👇