Your AI workforce.

Pick a play · Use the AI skills Annual · Quarterly · Monthly · Weekly

Pick a play, follow the playbook, use the AI skills that power each step. Plays are 12-month commitments, adjusted quarterly, reported monthly, executed weekly via sprints.

Plays
0across 4 outcomes
AI skills
0live + planned
Cadence
Annual · Quarterly · Monthly · Weekly
Last edited
—
01 — Run a client's month

Adjust quarterly. Report monthly. Execute weekly.

Running a play this month? The step-by-step checklists live in the Playbook.

Open the Playbook →

The portal reads from a markdown library. Every play in §02 is a real .md file in /playbooks/: edit the file, refresh the page, the change is live. Same for skills in §03. The whole set ships as one installable Claude Code plugin (claude plugin marketplace add), git-backed, so the team installs once instead of symlinking skills in one by one.

19
Plays
Seven for Attract, four each for Convert, Close, and Customer
4
Outcomes
Attract · Convert · Close · Customer. Pick one per quarter.
4
Tiers
Base $2,000 / 0 plays · Foundation $3,500 / 1 · Growth $7,000 / 3 · Scale $15,000+ / 5

Quarterly · Adjust

The AM and client commit one outcome. The pod picks the plays.

  1. Run the diagnostic from the Team Brief and commit one outcome: Attract, Convert, Close, or Customer.
  2. Pick plays from the library below (§02). Tier sets the count: Foundation 1, Growth 3, Scale 5. Base runs none.
  3. At day 90 / 180 / 270, read the quarter's numbers against each play's "What done looks like." Working plays stay, stalled plays rotate. Check capacity with PM first (pod-load calculator).
  4. Save the commit to 02-Strategy/outcome-Q[n].md. PM builds the schedule in Teamwork.
  5. Baseline the numbers the monthly report will track.

Stack · Team Brief · Play library · pod-load · HubSpot · 02-Strategy

Weekly · Execute

The PM runs sprint planning. The pod works the plays.

  1. PM runs sprint planning against the quarter's committed plays.
  2. Each play's step-by-step lives in the Playbook monthly checklists. Check items off as they ship.
  3. Run the AI skill for the step (§03 below). A hook lints the output automatically the moment it's written, so check the draft against bb-house-style for the judgment calls before anything ships.
  4. Stay inside the hours envelope (~15–20 hrs per play). The quota is the deliverable line.
  5. Anything on the play's "Escalate to AM when" list fires? Flag it same day. Clients around $20K/mo also get a weekly sprint debrief.

Stack · Playbook · Teamwork · client folder · Claude

Monthly · Report

The PM builds the report. The AM hosts the review.

  1. PM pulls the month's numbers from 04-Reports, HubSpot, and GA4.
  2. Grade each play against its "What done looks like" line on the play card. That line is the pass or fail.
  3. Draft with the reporting skills in §03: status-report-writer for the update, sprint-recap for call notes, qbr-prep-kit at quarter end.
  4. AM hosts the monthly review and walks the client through the outcome metric.
  5. File the report in 04-Reports so the quarterly review has receipts.

Stack · 04-Reports · HubSpot · GA4 · §03 skills

Annually · Plan + renew

Every client has a next-annual-plan date in Agency Backpack.

  1. Check the client's next-annual-plan date in Agency Backpack. Drafting starts two months ahead.
  2. Draft the next 12-month plan with the twelve-month-plan skill (§03): four quarters, one outcome each, plays per tier.
  3. Bring the draft to the extended marketing meeting, where the other team challenges it like a competing agency.
  4. Present to the client. The agreement renews for 12 months alongside the new plan.
  5. Update Agency Backpack with the new plan dates and HubSpot with the renewal.

Stack · Agency Backpack · 02-Strategy · Team Brief · HubSpot

02 — The playbooks

Nineteen plays, one way to run them.

Nineteen plays organized into four outcomes: Attract, Convert, Close, and Customer. Each quarter the AM and client commit to one outcome and run tier-allocated plays against it.

How play counts map to packages · SEO fundamentals, hosting, and maintenance included in every tier
03 — The skills that power them

AI workforce.

Each playbook step calls a specific AI skill. Live skills are ready today. Planned skills are coming in waves 2 and 3.

04 — How we sound

Voice rules.

Every BB skill enforces these. If output violates one, the skill needs fixing.

Sound like an operator, not a marketer.

Thoughtful operator talking to a peer. Not a vendor. Not a guru.

Never em-dashes.

Use a regular dash with spaces ( - ) or a comma.

Plain language, active voice.

Default to short. Vary length only for rhythm.

No marketing fluff openers.

"In today's fast-paced world." "I hope this email finds you well." Banned.

No invented statistics.

Use [TK: source needed]. Never fabricate.

Specific tools.

HubSpot, SearchAtlas, Replit, Claude. Not "a CRM."

Real frameworks only.

StoryBrand, EOS, Working Genius, PEACE Sound Bites.

End with what comes next.

Every deliverable closes with one bolded Next: line.

Honest beats confident.

"I don't know" beats a confident hallucination.

05 — How this works

Setup + FAQ.

Where files live, how to use this, what to do when something is wrong.

Where do client files live?

Every client gets a standard folder structure. The playbooks all reference these paths.

/BB Clients/[Name]/
├── 00 — Brand           design system, voice, logo (Claude Project)
├── 01 — Calls           Granola exports + Doc summaries
├── 02 — Strategy        12-month plan, QBRs
├── 03 — Plays/[PlayName]/  drafts/, final/, live-assets.md
├── 04 — Reports         monthly performance, QBRs
├── 05 — Sprints         recaps, weekly outputs
└── 99 — Archive

Plus: Granola folder per client (named the same), Claude.ai Project per client (brand assets + voice loaded as Project Knowledge).

How do I update a playbook?

The playbook content lives in markdown files at bb-operations/playbooks/. One .md file per play. Edit the file, save, refresh this portal — changes appear immediately. The portal is just a visual front end for the markdown library.

If you add a new play, also add an entry to playbooks/index.json so the portal picks it up.

What's a "play" and how does it map to a sprint?

A play is a 12-month commitment we make to a client. Base runs 0 plays (fundamentals only), Foundation runs 1 at a time, Growth runs 3, Scale runs 5.

A sprint is the weekly execution unit (prep → meeting → execute → async). Each play moves forward a few sprints per quarter. The playbook tells you what each quarter's sprints should ship.

How do I use the AI skills?

Install the BB skills plugin once (claude plugin marketplace add) and every skill in §03 auto-loads in Claude Code. No plugin yet? Open the skill card in §03, copy the prompt, and paste into your Claude tool of choice: Claude.ai (with a Project for repeated use) or a one-off message. A hook lints every draft for voice mechanics automatically as it's written; check bb-house-style for the judgment calls before sending to a client.

I want a planned skill prioritized.

Tell Jay or Brandon in #ai-workforce. Skills with willing human owners (you'd sit for the 30-min interview + review the first 5 outputs) ship faster.

What if a play needs to be adjusted mid-year?

That's the point of quarterly review. Each playbook has "Adjustment triggers" — specific conditions that say "if this happens, do that." End of quarter, the AM + CM read the triggers, decide, and the change goes into /02 — Strategy/ as the year-plan revision.

What if the output is wrong?

Send Jay (or post in #ai-workforce): the skill name, the input you gave, the wrong output, what you'd have written instead. Most "wrong" is missing context — usually a one-paragraph fix to the prompt.