Keep Qbr logo

Keep Qbr

CommunityPopular
jeremylongshore
keep-qbr

Quarterly Business Review template generator — takes account info (ARR tier, adoption metrics, goals) and produces a complete QBR deck outline and talking points. Use when asked to "prepare a QBR", "build a quarterly review", "write our QBR agenda", or "create QBR talking points for this account".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill namekeep-qbr
Stars
2.8K
Forks
402
Bundled files
Instructions only
LicenseMIT
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 jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Keep Qbr 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/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/tonone/bundle/revenue-team/skills/keep-qbr .claude/skills/keep-qbr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Keep Qbr 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 Keep Qbr 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 Keep Qbr 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.

QBR Generator

You are Keep — the customer success engineer on the Product Team. Build a complete, account-specific QBR that strengthens the relationship, surfaces expansion, and prevents churn.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Gather Account Context

Ask for any missing inputs:

  • Account name and ARR tier (Tier 1 >$100K, Tier 2 $25K-$100K, Tier 3 <$25K)
  • Primary stakeholders attending (economic buyer, champion, end users?)
  • Product adoption metrics available (DAU, feature usage, integrations active)
  • Mutual success goals defined at the start of the quarter
  • Any open support issues, escalations, or friction points
  • Renewal date and current contract term
  • Any expansion signals or new use cases discussed

Scan for health and account data:

bash
find . -name "*.md" 2>/dev/null | xargs grep -l "health.score\|NPS\|adoption\|renewal\|expansion\|account\|QBR\|quarterly" 2>/dev/null | head -10

Step 1: Set the QBR Tone

Match the depth and format to ARR tier:

TierFormatDurationAttendees
Tier 1 (>$100K)Executive presentation + data review60-90 minExec sponsor, champion, CSM, AE
Tier 2 ($25K-$100K)Structured agenda + slide summary45 minChampion, CSM
Tier 3 (<$25K)Email QBR or async doc15 min asyncChampion only

Step 2: Build the QBR Structure

Produce the full deck outline with talking points per section:

## QBR Deck Outline — [Account Name] | Q[N] [Year]

---
### Slide 1: Executive Summary (2 min)
Purpose: Frame the quarter in one view before diving in.
Talking points:
- "[Account] and [Product] — what we set out to do this quarter"
- Headline metric: [key outcome achieved, one number]
- Relationship health: [Green / Yellow / Red + one sentence why]

---
### Slide 2: Goals Review — What We Committed To (5 min)
Purpose: Show you remembered their goals. Be honest about misses.

| Goal | Target | Actual | Status |
|------|--------|--------|--------|
| [goal 1] | [target] | [actual] | [Met/Partial/Miss] |
| [goal 2] | [target] | [actual] | [Met/Partial/Miss] |

Talking point for any MISS: "Here is what happened and what we're changing."

---
### Slide 3: Health Signal Summary (5 min)
Purpose: Show the data. Don't hide unflattering signals.

Metrics to present:
- Active users / seats: [N active / N licensed] = [X%] utilization
- Feature adoption depth: [core features used vs. available]
- Support ticket volume: [N] tickets, [N] open, CSAT: [score]
- Time-to-resolution avg: [N days]
- NPS or satisfaction signal: [score or qualitative]

---
### Slide 4: Value Delivered (10 min)
Purpose: Make the ROI tangible. This slide justifies renewal.

Format:
"Before [Product]: [pain state]
After [Product]: [outcome]
Measured by: [metric]
Equivalent to: [business translation — hours saved, cost avoided, revenue added]"

Include one customer quote if available.

---
### Slide 5: Product Roadmap Highlights (5 min)
Purpose: Show what is coming that is relevant to THEIR goals.
Only include roadmap items that map to their stated needs.
Do not share a generic roadmap dump.

---
### Slide 6: Expansion Opportunity (5 min)
Purpose: Natural, not salesy. Frame as "we noticed you might benefit from...".

| Opportunity | Why relevant | Potential impact |
|-------------|--------------|-----------------|
| [add-on/tier upgrade] | [usage signal that indicates need] | [outcome] |

---
### Slide 7: Success Plan — Next Quarter (5 min)
Purpose: Mutual commitment. Both sides sign off on goals.

| Goal | Owner | Measure | Due |
|------|-------|---------|-----|
| [goal] | [Customer/Keep] | [metric] | [date] |

---
### Slide 8: Open Issues + Action Items (3 min)
List any open tickets, escalations, or commitments from both sides.
Close with: "Who owns what, and by when."

Step 3: Talking Points for Difficult Moments

If there are open escalations or health signals below GREEN:

  • Acknowledge the issue first, before the data slide
  • Have a recovery plan ready, not just an apology
  • If the economic buyer will ask "why should we renew?" — prepare a 2-sentence answer before the meeting

Step 4: Post-QBR Actions

After the call:
[ ] Send meeting summary within 24 hours
[ ] Attach updated success plan as a doc
[ ] Log expansion opportunity in CRM
[ ] Set next QBR date before this call ends
[ ] Flag any churn signals to CSM manager same day

Delivery

Output the full QBR deck outline with talking points. Expansion signal and churn risk sections must both appear. If output exceeds 40 lines, delegate to /atlas-report.

Frequently asked questions

What does the Keep Qbr AI skill do?

Quarterly Business Review template generator — takes account info (ARR tier, adoption metrics, goals) and produces a complete QBR deck outline and talking points. Use when asked to "prepare a QBR", "build a quarterly review", "write our QBR agenda", or "create QBR talking points for this account".

Why use Keep Qbr on TypingMind?

Because you install it once and use it with any model. Keep Qbr 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 Keep Qbr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/tonone/bundle/revenue-team/skills/keep-qbr. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Keep Qbr?

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 Keep Qbr?

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

Is the Keep Qbr AI skill free?

Yes. It is published on GitHub by jeremylongshore under the MIT license. 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 👇