business-review
Skill2 starsChanged 3 months agoMITView on GitHub
Use when the user says "QBR", "EBR", "should I run a QBR", "prep the business review", "build the review deck", "what should I present to [account]", or "exec review next week". Produces a run-or-send-async verdict, then a slide-by-slide narrative with the decision or ask on slide 1, headline numbers in the customer's language, and a champion pre-brief. Not for deciding if the account will renew (use renewal-risk) or for a 15-minute exec slot (use exec-conversation).
3 other projects use a version of this.
Adopted by
Most recently taken up by
- relaticle/relaticletheir own version, first seen Oct 31, 2026
- alamops/skillstheir own version, first seen Oct 19, 2026
- Relaticle/relaticletheir own version, first seen Oct 8, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- relaticle/relaticle★ 1.8ksame name
- Relaticle/relaticle★ 1.8ksame name
- alamops/skills★ 53same 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 repository54 other files it gives its agents.
- account-contextSkill
- account-planSkill
- account-reviewSkill
- adoption-planSkill
- advocacy-askSkill
- book-reviewSkill
- book-triageSkill
- call-prepSkill
- call-recapSkill
- champion-lossSkill
- churn-postmortemSkill
- coachingSkill
- commitmentsSkill
- coverage-modelSkill
- csm-hiringSkill
- csm-rampSkill
- csql-motionSkill
- cs-scorecardSkill
- cs-startSkill
- customer-updateSkill
- day-planSkill
- email-criticSkill
- escalationSkill
- exec-conversationSkill
- expansion-caseSkill
- expansion-scanSkill
- handoffSkill
- hard-conversationSkill
- health-scoreSkill
- internal-askSkill
- invoice-chaseSkill
- mutual-action-planSkill
- nrr-narrativeSkill
- offboardingSkill
- onboarding-planSkill
- one-pagerSkill
- playbook-builderSkill
- portfolio-reviewSkill
- price-increaseSkill
- renewal-forecastSkill
- renewal-negotiationSkill
- renewal-riskSkill
- renewal-runwaySkill
- sales-handoffSkill
- save-planSkill
- stakeholder-mapSkill
- status-updateSkill
- survey-follow-upSkill
- team-rollupSkill
- usage-emailSkill
- value-ledgerSkill
- voice-of-customerSkill
- what-do-i-oweSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
If the user gave the account, the meeting date and who will attend, go straight to "Do this".
- Distinctive: line 25
Run the gate first: Check the "do not run" list in Rules.
- Distinctive: line 35
Use this skeleton. Draft only.
- Very specific: line 57
If the verdict is SEND ASYNC, replace the slides with a written-report outline (the ask, three numbers, one problem, one decision, a reply …
- Distinctive: line 68
Data without context gets skipped: Every chart answers "so what, and what do you want me to do".
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Business Review
A slide-by-slide story for a review that ends in a decision, or a clear call that this account should get a written report instead.
Start here
If the user gave the account, the meeting date and who will attend, go straight to "Do this".
Otherwise ask for these in ONE message, then proceed with whatever comes back:
- Account, review date, and who is invited (is the person who signs coming)
- The goal the customer stated at purchase or last review
- Anything open or sore since the last review
Usage data, last deck and ticket history are a bonus. If an "Account context" block exists in the conversation, use it for the value metric and segment.
Do this
- Run the gate first. Check the "do not run" list in Rules. If any applies, the verdict is SEND ASYNC or DELAY, and you draft the written report outline instead of a deck.
- Write the ask and the belief. One line for what you need the customer to decide, do or fund. One sentence for what they must leave believing. Everything that serves neither goes to the appendix.
- Pick 3 or 4 headline numbers in their outcome language, not yours. Each needs a baseline, a source, the all-in cost on their side, and a conservative attribution stated out loud. Mark each
said,seenorinferred. Activity metrics (logins, seats) go to the appendix. - Write the slides as full-sentence headlines. Slide 1 is the decision or ask. Then their goals restated, progress with the numbers, what is not working (raised by you first), and the recommendation. Three to five themes, one hour, roughly one third presenting.
- Shape for the room. Executive: where we are against your goal, what I recommend, what I need. Champion: ammunition and no surprises. Users: workflow and what is coming.
- Pre-brief the champion about 48 hours ahead: walk through the numbers, ask what they want from the meeting, offer them the slot to present their own result, send a one-page pre-read.
- Draft the 24 hour follow-up: decisions, owners, dates, next meeting booked before anyone left.
Output
Use this skeleton. Draft only; the user sends anything.
BUSINESS REVIEW: [Account] | [date] | [attendees]
Verdict: RUN / SEND ASYNC / DELAY. Reason: [one line]
Ask (slide 1): [decision, action or funding needed]
They leave believing: [one sentence]
Slides (60 min, about 20 presenting)
1. [Headline as a full sentence: the ask] - [minutes]
2. [Headline] - evidence: [number, baseline, source, tag] - [minutes]
Appendix, not presented: [activity data, ticket recap]
Champion pre-brief: [what to walk through, what to ask, who presents]
Raise before they do: [the thing that is not working]
Follow-up draft: [3 lines]
What I could not check
- [gap, marked (assumed, confirm) inline]If the verdict is SEND ASYNC, replace the slides with a written-report outline (the ask, three numbers, one problem, one decision, a reply date) and offer a 15-minute call if they want one. A filled example is in examples/sample.md.
Rules
- Do not run a review when there is no value baseline yet (run a success-planning session), an escalation is live (run the repair call), the decision maker will not attend and reaching them was the point, nothing changed since the last one, or the customer skipped the previous two. Cadence is not a reason: a review held to satisfy a calendar spends scarce access and teaches them the format is optional.
- Send an async report to accounts where a meeting costs more than it returns. Low contract value, stable operations and a user who never opens the deck are common cases. Ask the customer which they prefer.
- The ask goes first. Executives decide in the first five minutes whether to stay engaged, and a meeting with no ask only informs.
- Activity is not value. Logins prove the mechanism runs. A finance team forwards only a number it can rebuild: baseline, full cost, stated attribution.
- When value cannot be measured, have the champion say it themselves, record executive testimony, net it against their effort, or name the gap and propose instrumentation as the ask. Do not pad with benchmarks.
- Never surprise the champion in front of their boss. They stop advocating, and the sponsor you need next year is gone.
- Do not disguise an expansion pitch as a review. Customers forgive the ask and punish the disguise.
- Data without context gets skipped. Every chart answers "so what, and what do you want me to do".
Related (only if installed)
expansion-case if the review earns an ask for more scope. one-pager for the leave-behind. exec-conversation for a short executive slot.
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.

