onboarding-handoff
Skill23 starsChanged 2 months agoMITView on GitHub
Run the Won→onboarding handoff — the seam most teams drop. Trigger when a deal is marked won/closed-won, when the user says "we won X", "hand this off to onboarding", "kick off the new customer", or "onboarding checklist".
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- account-healthSkill
- calendar-followupSkill
- churn-saveSkill
- cold-outreachSkill
- content-repurposeSkill
- event-to-pipelineSkill
- example-skillSkill
- expansion-signalSkill
- follow-upSkill
- inbox-digestSkill
- lead-qualifySkill
- marketing-feedbackSkill
- meeting-prepSkill
- product-signalSkill
- qbr-prepSkill
- retention-feedbackSkill
- status-updateSkill
- support-signalSkill
- triageSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Very specific: line 16
Open the row: Create the account in ops/customers.md at stage Onboarding, with the value hypothesis, the ARR, the first adoption signal to …
- Distinctive: line 18
Don't invent commitments the deal didn't contain.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Onboarding Handoff (Won → onboarding)
The handoff most teams never define: a signed deal drops silently into a customer-success void, the value the buyer was sold gets lost, and the renewal clock starts late. This is handoff H3 in docs/operating-model.md — made concrete as a 48-hour checklist that turns a won deal into the first row of the account book.
From the won deal (point me at the row in ops/pipeline.md, or paste the deal context):
- Carry the value hypothesis forward. Write down, in one line, what the customer bought this to do — in their words, from discovery. This becomes the value hypothesis in
ops/customers.md, and the thing every adoption check is measured against. Lose it here and onboarding optimizes for activity, not value. - Set the date markers. Record the renewal date, the contract value (ARR — the number the book rolls up to NRR), and note the day-60 renewal-motion trigger (not day-85). Set a first-expansion check date too — the moment to look for a second team or use case.
- Identify the power user / champion. Name who will actually use it and who sponsors it internally. A single-threaded account is a churn risk before it's even live — if there's only one name, that's the first gap to close.
- Write the first adoption milestone. One concrete, dated outcome that proves value is landing (the first workflow live, the first cross-system answer, the first report shipped). Vague onboarding has no finish line.
- Open the row. Create the account in
ops/customers.mdat stage Onboarding, with the value hypothesis, the ARR, the first adoption signal to watch, the renewal date, an owner, and the next step. Offer to log the handoff inops/daily-log.md.
Don't invent commitments the deal didn't contain. Bring your own onboarding playbook; this carries the deal's context across the seam so nothing drops.
Depth
- quick: open the
ops/customers.mdrow with value hypothesis, renewal date, and owner. - standard: the full 48-hour checklist above.
- deep: + a single-threading risk read and the first two adoption milestones with dates.
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.

