Benali Ops / Paxus CPA / onboard-client
Paxus CPA · Skills Library · Cowork

The /onboard-client skill

One command builds a client's context bundle: the folder of structured knowledge that lets every AI skill do client-specific work correctly. The skill does the research; you review and clarify.

What it produces

A context bundle in the client's shared drive

A .agents folder of small markdown files, organized into seven groups (identity, engagement, staffing, books, access, annual, living context). Every fact carries a citation to where it came from. Skills load only the files their task needs: coding work reads the coding rules, meeting prep reads the client profile. The Mary Abbott bundle is the working example of the finished product.

What goes in

  • Knowledge, not state. The things systems can't tell you: coding judgment, client quirks, review focus areas, who unblocks what.
  • Pointers, not copies. Contact details stay in Financial Cents; the bundle stores where to look.
  • Citations on everything. Every claim traces to a document, an export, or a named person and date.

What stays out

  • Live state. Bank-feed status, cleanup progress, open items: those live in QBO and Financial Cents and get checked at runtime.
  • Credential values. Never passwords, tokens, or full account numbers. Pointers to Cloud Protect and the FC vault only.
  • Guesses. A field with no source stays TBD and becomes a question. A gap is better than a wrong answer an agent trusts.
How it works

You answer two questions. It does the rest.

01
You

Point it at the client

Run /onboard-client in Cowork. It asks for the client's exact legal name and their shared drive folder, plus anything you already have on hand (a kickoff transcript, documents). That's the whole setup. It also confirms the folder is firm-internal before it will put internal information there.

02
The skill

Researches on its own

Read-only recon before it asks you anything substantive: it inventories the client's Drive folder (engagement letter, client intro, policies, budgets, saved exports), pulls the Financial Cents record (contacts, portal users, team, recurring projects, checklists, budgeted hours), and uses the firm's read-only QBO connection where one is set up. Everything it reads becomes a cited source.

03
You

Confirm the picture

It shows you what it established: the entities, the service scope, the headline facts per group, each with its source. You confirm or correct in one pass. Your corrections become sources too.

04
The skill

Fills the bundle

It copies the firm template into .agents/ and fills every file the research and your answers support. Nonprofit and entity-type rules apply per entity. Anything unsupported stays TBD with an honest status: scaffold (untouched), partial (gaps remain), active (complete and confirmed).

05
You

Answer the gap report

What's left is the short list research can't answer: materiality judgment, client quirks, escalation paths. Questions arrive batched by who can answer them (controller, lead, client contact). Answer live, or take the formatted list away and send it.

06
The skill

Validates before it's done

A deterministic validator checks the whole bundle: structure, links, statuses, no leftover placeholders, no credential-shaped values, the firm contract unmodified. It ends with a one-line receipt: N active, N partial, N scaffold, N open questions.

Hard bounds

What it will never do

The autonomy is bounded on purpose. These rules are built into the skill and checked by its validator.

Research is read-only

It never moves, renames, edits, or deletes anything it finds in Drive or Financial Cents. Its only writes are the .agents bundle itself, its own backups, and two operator-gated extras.

No new logins, ever

It uses only connections already on your machine. A portal name or credential found in a document is a pointer to record, never an invitation to log in.

No credential values

Passwords, tokens, and full account numbers never enter the bundle. Nicknames and last-four only, plus where the real credential lives.

No guessing

Every statement traces to a real source. Conflicting sources get both positions recorded. Unknown means TBD, not invented.

Safe re-runs

On an existing bundle it works on a staged copy with a timestamped backup, shows you a full diff, and applies only after you approve. Confirmed content is never regressed.

Sources are data

Instructions embedded inside a transcript, PDF, or export are ignored and flagged. Only you direct the skill.

Using it effectively

Getting the most out of a run

Record the intake conversation

The single best input is a transcript. Get the pod on a call, run through the client conversationally, record it, and hand the transcript to the skill. It reads verbatim answers far better than notes.

Pick a client you know well first

For practice, choose an account whose books you could describe from memory. You'll immediately see what the research got right and what it missed, which builds trust in the tool fast.

Tidy the Drive folder first (five minutes)

The research is only as good as what's findable. If the engagement letter or client intro is sitting in someone's email instead of the client folder, drop it in before running.

Correct, don't gather

Your job in the findings review is judgment: "that's the old treasurer," "we switched card platforms last month." Let the skill chase documents and exports; you supply what's in your head.

Don't force answers

If you don't know, say so. TBD plus a gap-report question beats a guess: agents will trust whatever the bundle says.

Re-run when things change

New treasurer, new bank, amended engagement: run /onboard-client again on the same client. Update mode merges the new facts, keeps history, and logs every change.

Send the gap report the same day

The open questions are freshest right after a run. Ask the skill to format them as an email or FC task and get them to the right person while context is warm.

Read two files before you sign off

"Working with this client" and "Review focus areas" carry the most judgment. Have the pod lead fact-check those two by hand; everything else is verifiable against sources.

Common questions

Before you ask

What do I literally type to start?

In Cowork (or Claude Code) run /onboard-client. It takes it from there: two locating questions, then research. Nothing to prepare beyond knowing which client and where their Drive folder is.

Can it break anything in Drive or Financial Cents?

No. Research is read-only: it cannot move, edit, or delete anything it finds. The only thing it creates is the .agents folder (and, if you use the older project skills, a small local pointer folder it offers to set up).

What if Financial Cents isn't connected on my machine?

The skill degrades gracefully: the items it would have pulled from FC become quick confirmation questions instead. Everything else works the same.

What does it do with a client that has multiple entities?

It builds one books folder per entity, because books are per-entity in QBO, and applies each entity's own rules (a nonprofit entity gets nonprofit treatment even when a sibling is an S-corp). Groups like identity and staffing stay engagement-level.

The bundle already exists. Is re-running safe?

Yes, that's update mode: it backs up the current bundle with a timestamp, builds the merged result on a staged copy, shows you a complete diff, and applies only after you approve. Confirmed content is never overwritten back to template text.

What are the status labels on each file?

scaffold means untouched template, partial means real content with gaps or unresolved conflicts, active means complete and confirmed. The wrap-up line counts them so you know exactly how done the bundle is.

Where do I see what a finished bundle looks like?

The Mary Abbott Children's House bundle: browse the folder tree and open any file. Start with the Agent contract and Client-critical rules to see how agents are told to behave inside it.

Something about the skill itself is wrong or annoying. Who do I tell?

Answer the two feedback questions at the end of a run (it asks every time), and flag it to your reviewer. Skill changes go through the skills-library review process, so fixes reach everyone's Cowork on the next sync.