← ALL PLAYBOOKS
── PLAYBOOK · FOUNDATIONS
✓ APPROVED

Build your operator system

Every session starts cold and nothing you learn sticks. Give your work memory and a closed loop. Already run run-your-gtm-on-github? You already have context-pack, decision-log, and session-closeout, skip to runbook-builder and closed-loop.

[ BUILT GTM ]

Build your operator system

Solvethe problem worth solving
Problem · 01Foundations

Every session starts cold and nothing you learn sticks.

Give your work memory and a closed loop. Already run run-your-gtm-on-github? You already have context-pack, decision-log, and session-closeout, skip to runbook-builder and closed-loop.

Stackthe workflow, box by box
Claude01
Turn a cold start into a warm one with one doc.
Warm-start a new teammate or a major handoff with one deep orientation doc, refreshed periodically, not every session.
Connect to analyze
AI
Claude02
Stop re-litigating decisions you already made.
Stop re-litigating decisions you already made.
Connect to analyze
AI
Claude03
Turn a workflow in your head into a runbook anyone can run.
Turn a workflow in your head into a runbook.
Connect to analyze
AI
Claude04
Close out a session without leaving it half-shipped.
Close today's session clean and leave a lightweight per-session note, the small delta on top of the periodic context pack.
Connect to analyze
AI
Claude05
Close the gap between a correction and it happening again.
Turn every correction into a lasting improvement.
Connect to analyze
AI
Splithow control passes: agents branch left, humans right
HUMAN + AI, IN THE LOOP
How control passes.
AgentsHuman
Agent01
Turn a cold start into a warm one with one doc.
Claude runs it.
Agent02
Stop re-litigating decisions you already made.
Claude runs it.
Agent03
Turn a workflow in your head into a runbook anyone can run.
Claude runs it.
Agent04
Close out a session without leaving it half-shipped.
Claude runs it.
Agent05
Close the gap between a correction and it happening again.
Claude runs it.
The skills run the work. You stay in the loop on the calls that need judgment.
Outputwhat the workflow produces
OUTPUT · 01

A context pack

OUTPUT · 02

A decision log

OUTPUT · 03

Runbooks

OUTPUT · 04

A safe closeout

Outcomethe result it drives
OUTCOME · 01

The 7th analyst

The meta-analyst and closed loop that make a system compound.

Built GTM
── 01 / WHY RUN IT
RUN THIS AND YOU CAN
A context pack
A decision log
A safe closeout
A system that improves itself
── 02 / THE RUN, STEP BY STEP

The workflow that solves it, one step at a time.

Each step is the plain question you are already asking. The skills answer them in order, one handing its receipt to the next.

1✓ TESTED
Turn a cold start into a warm one with one doc.

A single pack that tells a new session or teammate what the project is, where things live, what's decided, and the next move.

YOU GETThe five-question frame, a where-things-live map, a decisions digest, and one next move.
OPEN THE SKILL →
2✓ TESTED
Stop re-litigating decisions you already made.

A running log where each entry captures the decision, the context, the options, the why, and when to revisit.

YOU GETThe five-field entry, searchable records, and revisit triggers.
OPEN THE SKILL →
3✓ TESTED
Turn a workflow in your head into a runbook anyone can run.

A step-by-step SOP for a repeated process, who does what, when, and how, with named failure points and a check on every step.

YOU GETThe full who-what-when-how capture, stranger-followable steps, and a check per step.
OPEN THE SKILL →
4✓ TESTED
Close out a session without leaving it half-shipped.

Verifies every change is committed, pushed, and green, confirms it is live, updates the notes, and hands back a summary with a rollback path.

YOU GETThe done-check, the live verify, the next-session note, and the rollback.
OPEN THE SKILL →
5✓ TESTED
Close the gap between a correction and it happening again.

Scans a session for corrections, approvals, and validated patterns, then proposes exact edits to your skills and docs. Nothing applied until you approve.

YOU GETThe session scan, high vs medium confidence, and a per-edit approval gate.
OPEN THE SKILL →
WHERE YOU LAND

A context pack, a decision log, runbooks, a safe closeout, and a system that improves itself.

EVERY STEP, TESTED AND PASSED
EVAL RESULTPASS4/4 dimensions
HOW WE EVAL →
Skills resolve
Structure + proof
Example chat
Quality judge
  • All 5 chained skills resolve to real, scored skills.
  • Has a problem, an outcome, 2+ steps, and proof from a real build.
  • Ships an example chat showing the play run in Claude.
  • Reads in plain operator voice, grounded in a real build.
Last eval run 2026-08-05
DEEP EVAL · PASS
THE STANDARD →

We did not just check the structure. A judge read this play against the full text of every skill it chains (composition), then ran it on a real scenario end to end (simulated). It passed both. Test scenario: Morgan, a RevOps operator, is tired of cold-starting every session and wants memory plus a closed loop.

── 03 / SEE IT RUN

Watch the skills answer in order.

Describe your situation in plain language. The right skill fires on its own and hands its receipt to the next.

EXAMPLE CHATMorgan, RevOps Operator, running the loop in one sitting
M
Every time I start a session with Claude it's cold and I re-explain everything. Fix the starting point.
S
Step 1· Context Pack
I built one pack that tells any new session what the project is, where things live, what's already decided, and the single next move. Cold start becomes a warm one.
Receipt
One pack: the project, a where-things-live map, decisions, and the next move.
M
We keep re-arguing decisions we already made. How do I stop that?
S
Step 2· Decision Log
Here's a running log where each entry captures the decision, the context, the options, the why, and when to revisit, so it's searchable instead of re-litigated.
Receipt
Running log, five fields per entry, searchable, with revisit triggers.
M
There's a process only I know how to run. Make it something anyone can follow.
S
Step 3· Runbook Builder
I turned the workflow in your head into a step-by-step SOP: who does what, when, and how, with the failure points named and a check on every step.
Receipt
Stranger-followable SOP, a check per step, and failure points named.
M
I'm wrapping for the day. Close it out cleanly so nothing's half-shipped.
S
Step 4· Session Closeout
I verified every change is committed, pushed, and green, confirmed it's live, updated the next-session note, and left you a rollback path if anything looks off tomorrow.
Receipt
Committed, pushed, green, live confirmed, notes updated with a rollback path.
M
I corrected you three times today. Make sure those actually stick.
S
Step 5· Closed Loop
I scanned the session for corrections, approvals, and patterns that held, then drafted exact edits to your skills and docs. Nothing changes until you approve each one.
Receipt
4 exact edits proposed to skills and docs, held for your approval.
── 04 / SEE IT IN PRODUCTION

Before you run it, I ran it for real.

This workflow is genericized from a real build. Here is the number it moved, and what I actually did.

THE BUILD · AI-NATIVE THESIS
The 7th Analyst
0.775 AUC
a won account outranks a lost one, on the model the loop rebuilt
1.5x lift
94% of the model Warm-plus accounts are wins, vs a 62% base rate
7 versions
each caught a flaw the last one shipped, by the loop not a customer
0 of 60
lost accounts that reached the top tier, the top of the funnel stays clean
WHAT I DID
01
Give every analyst an audit trail. Each agent logs what it decided and why, every override, every missing field, every enrichment miss. The exhaust of the system becomes its memory.
02
Build the seventh analyst to read them. A meta-analyst reads the other six's audit trails and turns each mistake into a training signal: a rule tightened, a gap flagged, a pattern learned.
03
Close the loop. The corrections feed back into the system, so the next run is better than the last. That is the difference between a tool and a system that improves itself.

AI-native is not how many agents you have. It is whether one of them watches the others and turns their mistakes into improvements. Build the analyst that reads the audit trail. That is the one that compounds.

Dig into the full build
05 / INSTALL THE WHOLE PLAYBOOK

One plugin. 5 skills, bundled.

The whole playbook installs as a single plugin in Claude Code, no copy-pasting 5 times. Or grab any single step above. It runs on what you paste; connect your stack to go live.

OR KICK IT OFF IN CHAT
Here is my situation: [describe your workflow or account in a sentence or two]. Walk me through Build your operator system step by step, and run each skill as we go.
── GET THE NEXT PLAYBOOK

One runnable workflow a week. Free.