qbr-prep
Skill2 starsChanged 25 days agoMITView on GitHub
Prep a quarterly business review with a customer: surface the value delivered, the risks, and the expansion openings, then build the agenda. Use this skill whenever a seller or account manager says "prep for my QBR", "quarterly business review", "build a QBR agenda", "customer review prep", "renewal review", "prep my check-in with [account]", or is getting ready to sit down with an existing customer to review the relationship. It pulls context from Loop first (falling back to CRM, call transcripts, and email), ties the value delivered back to their original goals, assesses risk from engagement and outcome signals, finds the expansion openings, and drafts an agenda that leads with their success. This is customer-facing (the QBR is with the buyer), distinct from an internal deal review. Prefer this over a generic status-deck outline any time a customer review is coming up.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- promptmetrics/skillstheir own version, first seen Oct 20, 2026
- etrebels/claude-code-growth-ostheir own version, first seen Sep 14, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- etrebels/claude-code-growth-os★ 23same name
- promptmetrics/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- account-planningSkill
- call-follow-upSkill
- call-prepSkill
- champion-enablementSkill
- competitive-displacementSkill
- deal-advancementSkill
- manage-upSkill
- multithreadSkill
- one-page-business-caseSkill
- sales-playsSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 36
Loop first: If the Loop MCP (https://mcp.fluint.io/mcp) is connected, use it first.
- Distinctive: line 40
No Loop? Detect what is live and fall back: Do not assume a vendor. In parallel:
- Distinctive: line 42
Call transcripts (Salesloft, Gong, Clari, Chorus, Fathom, Fireflies.
- Very specific: line 52
Read references/frameworks.md (Value tied to their goals).
- Very specific: line 58
Read references/frameworks.md (Risk signals).
- Very specific: line 65
Read references/frameworks.md (Expansion).
- Very specific: line 71
Read references/output-templates.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
QBR Prep
What this does
A quarterly business review is a chance to prove value, get ahead of risk, and open the next expansion, or a status deck nobody remembers. This skill builds the first kind:
- Ties the value you delivered this quarter back to the goals they bought for.
- Assesses the risks going in: low engagement, missed goals, competitive threats.
- Finds the expansion openings: new use cases, teams, and problems.
- Drafts an agenda that leads with their success and opens the door to more, without a pitch.
This is a customer-facing review with the buyer, distinct from an internal forecast or deal
review (for that, use the manage-up skill). The deliverable is a QBR pack the seller can
walk the customer through.
Step 1: Lock the account and pull context
Loop first. If the Loop MCP (https://mcp.fluint.io/mcp) is connected, use it first. Pull the
account, the deal history, current footprint, and recent meeting activity. Loop
already fuses CRM, calls, and emails, so start there.
No Loop? Detect what is live and fall back. Do not assume a vendor. In parallel:
- CRM (HubSpot, Salesforce, Attio, Pipedrive) = the account, the original goals, usage, history.
- Call transcripts (Salesloft, Gong, Clari, Chorus, Fathom, Fireflies; or via Clay / Deepline) = recent sentiment.
- Email (Superhuman, Gmail, Outlook) = engagement level and any friction signals.
- Product usage data, if available = adoption, and the expansion signals inside it.
Missing a source? Flag it, and make the gap a move. Mark it inline as [MISSING: ...] and continue. Every gap gets the single highest-leverage way to close it: the one question, to the one person, at the next touchpoint. Not "get more data."
Who can actually say yes? Name the people with the power to approve this, or to block it, and mark whether they are engaged yet. Power is often not in the room. If the deciders are absent or untouched, that is the headline, not a footnote.
Step 2: Value delivered
Read references/frameworks.md (Value tied to their goals). Summarize the value delivered this
quarter, and tie each win back to the original goals and success criteria they bought for. A win
they do not connect to a goal they care about is a feature, not value. Use their metrics.
Step 3: Risk assessment
Read references/frameworks.md (Risk signals). Name the risks going into the review: low
engagement, missed goals, a quiet champion, a leadership change, a competitive threat. Back each
with evidence from behavior, not a hunch. Better to name a risk yourself and bring a plan than to
have the customer raise it.
Step 4: Expansion openings
Read references/frameworks.md (Expansion). Identify the expansion opportunities: new use cases,
adjacent teams, problems you have not solved yet. Rank by impact and ease. The strongest opening
is usually a new executive with a new mandate, or a proven outcome you can extend to a next team.
Step 5: Build the agenda
Read references/output-templates.md. Draft a QBR agenda that leads with their success,
addresses any risk proactively, and opens the expansion conversation, without turning into a
sales pitch. Lead with them, not with you.
The deliverable
Produce the QBR pack using the skeleton in references/output-templates.md:
- Value delivered (wins tied to their original goals, in their metrics)
- Risk assessment (the risks, with behavior evidence and a plan for each)
- Expansion openings (ranked, with who to engage)
- QBR agenda (leads with their success, addresses risk, opens expansion)
The operator's read
Before you hand it over, add the part a summary cannot: the one thing an experienced operator would notice that the data does not show on its own. The non-obvious risk. The stakeholder who matters more than their title. The deal that is not what it looks like. The strength that is quietly a trap. One or two sentences of judgment, called out plainly. Anyone can produce the map. This is the read.
Operating principles
- Lead with their success, not your roadmap. The review is about their outcomes.
- A win they do not connect to a goal is a feature. Tie value to what they bought for.
- Name the risk before they do. Bring the risk and the plan together.
- Open expansion, do not pitch it. The next use case, framed as their next outcome.
- Voice guard. Anything the buyer will read opens with their words, from the call or their own materials, in the first line. Banned openers: "Great connecting," "As discussed," "I wanted to follow up," "Hope this finds you well," "Circling back." If a sentence would survive being pasted into a different deal, it is too generic. Cut it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

