Your task list, sorted by what only you can do.
An audit of the last two weeks of your own work that sorts tasks into hand off now, hand off with a guide, keep, and stop, then writes three handoff notes.
Most people know they should delegate more. They do not, because delegating a vague area of responsibility is hard, and explaining one task feels slower than doing it. So the list stays on their desk.
Delegation Audit works at the level of single tasks. It asks whether each one recurs, needs your judgment, and what a mistake would cost. Then it picks the three handoffs that return the most hours and writes each one with a done-definition, decision limits, and a check date.
What it produces.
- →Your task list sorted into four groups
- →Three chosen handoffs with hours returned
- →A handoff note for each: owner, done-definition, what they may decide
- →A short list of tasks to stop altogether
- ✦Founders who are the bottleneck in their own company
- ✦Executives with a new assistant or hire and nothing clear to hand over
- ✦Anyone who says they should delegate more and cannot say what
- →delegation-audit.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →delegation-audit-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
What it does with a real question.
I run a 12-person design agency and I'm working 60-hour weeks, mostly on invoicing, scheduling client calls, and reformatting proposals. My new operations assistant, Priya, started March 3 and has almost nothing assigned yet. Can you help me audit my task list and pick what to hand her this month?
Hand Priya three tasks, not an area of responsibility. Your three big time sinks, invoicing, call scheduling and proposal reformatting, are all recurring and steps-based, which is exactly what separates a handoff from a judgment call. None of them needs your taste or your client relationships. "I'm the only one who knows how" is knowledge, and knowledge can be written down in an afternoon.
The mistake costs differ, though, and that should set the order. Scheduling is low risk: a double-booked call is embarrassing but fixable, so give it to her this week. Proposal reformatting is also low risk, but she needs one finished example from you to learn what "good" looks like, so hand it over with that sample attached. Invoicing is medium risk, because a missed invoice delays cash. Let her prepare invoices while you approve the first month's batch, then release the approval step once the pattern holds.
For scheduling, the note to Priya reads something like: "Book every client call within one business day of my yes. You may reschedule once if the client asks, without checking with me. Done means a calendar invite sent and the client confirmed. I'll look at it Friday." Write the same four parts for the other two: who owns it, what done means, what she may decide alone, and when you check.
Your next move: send that scheduling note today, start Priya on March 3's inbox of pending calls, and block 30 minutes tomorrow to record the proposal example.
The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude gives general advice about delegation. This starts from your actual two weeks of work, separates knowledge from judgment, and ends with three handoffs you can start this month.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.