A brief that answers the questions before the subcontractor asks.
A two-page brief for handing part of a project to another freelancer: finished state, context, decision limits, checkpoints, and terms.
Daily check-ins with a subcontractor usually mean the brief was thin. They ask what done looks like, who the client is, and what they can decide alone. Or they stop asking, guess, and hand back work that missed.
Subcontractor Brief writes the goal and a checkable finished state, trims the client context to what matters, and separates decisions they own from decisions they escalate. It sets one or two checkpoints, states fee and payment, and then tests the brief by reading it as the person starting Monday.
What it produces.
- →A goal and a finished-state checklist
- →A trimmed client context paragraph
- →Two lists: decide yourself, and ask first
- →Checkpoints, terms, and a what-to-do-if-blocked line
- ✦Freelancers handing overflow work to another freelancer
- ✦Small studios using subcontractors for part of a client project
- ✦Anyone tired of answering the same questions every day
- →subcontractor-brief.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →subcontractor-brief-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 small brand design studio and need to hand the packaging illustration for a client's 12-SKU tea line to Dana, a freelance illustrator I haven't used before. Final art is due March 14, the budget is $4,800 flat, and the client's art director, Priya, approves at two checkpoints. I'd like Dana to work independently.
Decide who talks to Priya before anything else. Your brief should say Dana never contacts the client, and that all feedback comes to you in one consolidated round. With a first-time illustrator and a client art director approving at two checkpoints, the real risk is not Dana's skill. It is Priya's comments reaching Dana unfiltered, contradicting each other, and quietly expanding scope on a flat fee.
Dana can only work independently if the brief answers her questions in advance. Define done for all 12 SKUs: file format, resolution, color mode, layered files, naming convention, and delivery folder. Give her a trimmed client paragraph: the tea brand's audience, tone, one thing to avoid, and the existing assets. Leave out the client's pricing and internal politics.
Then draw the decision line. Dana decides composition, technique, and tools. She asks you first about changing the palette, altering the brand's core claims, adding SKUs, or contacting Priya.
Set the checkpoints yourself rather than inheriting Priya's: a rough pass on three SKUs as a style test, then the full set. Because Dana is untested, pay in stages tied to those points, and say how many revision rounds the $4,800 covers.
Next move: write the finished-state checklist first, then add the escalation line: "If you're blocked or will miss March 14, tell me by noon the day before." Put the agreement in writing, and check classification rules where you work.
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 writes a task description. This Playbook produces the decision boundaries, finished-state checklist, and checkpoint schedule that let the subcontractor work alone, then reads the brief back as the recipient to find the question you missed.
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.