Keep reps making the calls that matter.
Marks the points where a rep owns the judgment, who to pursue, the relationship, the message, and gives the workflow an owner and a weekly check so it lasts.
In plain English: “Where do reps stay in control?”
Inside: The points a rep controls, the owner handoff, and the review rhythm that keeps it running.
Install it in one line, or paste it in.
~/.claude/skills/ and runs automatically when it is relevant.Connect your context. Set it to your motion.
Everything the skill does, in full.
Hands the redesigned workflow to a human who owns it, with the four threads that keep it from falling apart. Cutting the drag is not the finish line. A workflow with no owner and no rhythm tears again in a month.
- 11. Name the human judgment. The calls in this workflow that need context, judgment, or the relationship. That is what the person keeps.
- Thread 1, context. Write the shared brain for this one workflow: the ICP, the rules, the definitions, the messaging. The human and the AI pull from the same source, or the AI guesses confidently.
- Thread 2, tooling. Stand up the one automation that runs the drag. One workflow, not the whole stack.
- Thread 3, ownership. Put one name on the workflow. They own the human judgment and the system's output. No orphan workflows.
- Thread 4, rhythm. Set the recurring review where the owner checks the output and fixes drift. On the calendar, weekly or biweekly. A standing review, not a Slack channel.
- Cutting the drag and walking away. No owner means it tears again.
- Keeping the judgment with a doc nobody keeps current. Context rots.
- Reviewing in a Slack thread instead of a standing meeting. Drift wins.
[one owner, one context doc, one running automation, one recurring review, on one workflow]
Repeat the loop on the next most expensive workflow. The Sales Operator. Receipts only.
Where an operator takes this next.
The handoff is step one. Here is where an operator takes it once the manual version proves out.
You handed off the judgment once, now the system checks that it's still being kept.
Use a scheduled Claude task to generate the biweekly review agenda from the last two weeks of routing exceptions, so the owner walks in with the drift already surfaced.
Flag the context doc in Slack if it hasn't been touched in 60 days, so nobody's running rules that quietly went stale.
Log each workflow's owner and last-review date in a Notion or Airtable table, so "no orphan workflows" is a fact you can check, not a hope.
One skill is the on-ramp.
A single skill does one job. Chained into a playbook, or run as a full build, it becomes a system. Here is where this one plugs in.