The Paid Social Desk
Skills · Subagent · Command · PDF
.claude/the-paid-social-desk/zip
skills/06
├ audience-plan
├ campaign-architecture
├ creative-testing-matrix
├ frequency-review
├ optimisation-log
├ post-flight-review
agents/01
├ account-auditor
commands/01
├ /post-flight
FIELD-GUIDE.pdf9pp
English
One payment · No account · No subscription
- ✓ Download link in your inbox in seconds
- ✓ Secure card checkout · VAT handled
- ✓ 14-day money back, no questions
- ✓ Every future revision included
- ✓ Runs in Claude Code and claude.ai
Built for Claude first, our recommended agent. Skills follow the open Agent Skills standard (SKILL.md), so they also run in any agent that reads it; subagents and slash commands are Claude Code formats.
The Paid Social Desk
Paid social run as a system, not a feed of guesses
six skills·one subagent·one command·9-page guide
Your agent structures the account, tests one variable at a time, logs every change with an expected effect, and closes the flight with platform claims and verifiable results apart.
Executive summary
- The problem
- The platform proposes the structure, optimises the spend and grades the result, so an account drifts into fragmentation and untested changes while the dashboard keeps reporting success. Afterwards nobody can say which change did what, because none was written down with an expected effect.
- What it does
- Six skills and a read-only account-auditor set the structure and audiences, force one variable per creative test with the decision rule written first, log every change with its review date, and close each flight with platform-attributed and verifiable results apart.
- Why take it
- The budget is yours and the platform's incentives are not. This makes every recommendation you put in front of a client or a CFO one you can trace to a test, not to a dashboard.
For paid social managers, performance leads and agency account teams running more than one account.
In the first week you will
- 01Hand your campaign and ad set exports to account-auditor and get fragmentation, overlap and learning-phase problems back in one report
- 02Lay out the next round with creative-testing-matrix so each test changes one thing and the decision rule is written before launch
- 03Run /post-flight on the export when the campaign ends and read platform-attributed and independently verifiable results in separate columns
Contents of the Kit
- 01Six installable agent skills: campaign-architecture, audience-plan, creative-testing-matrix, optimisation-log, frequency-review, post-flight-review
- 02The account-auditor subagent: reads your campaign and ad set exports and reports fragmentation, audience overlap, frequency and learning-phase problems. Read-only
- 03A /post-flight slash command that opens the campaign review from an export and a sentence
- 04The testing matrix that forces one variable per test, a decision rule written before launch, and a definition of "won" that survives the platform dashboard
- 05Blank templates for the optimisation log and the testing matrix
- 06A 9-page Field Guide on the paid social chain, and plugin manifest included
One skill, as it ships
SKILL.md
campaign-architecture
- Use when
- Use when a new account or campaign is being set up on Meta, TikTok, LinkedIn or Pinterest, when an existing account has more ad sets than its budget can feed, when someone asks "how should we structure this", or before a media plan is loaded into a platform. Never states platform limits as facts; asks the user to confirm the current value.
- Requires
- The objective(s), in the user's words · The budget · Platform(s) and the geographies or languages that force separation · The platform's current learning-phase exit condition
- Will not
- Never state platform minimums, learning-phase thresholds, audience sizes or placement performance as facts · Never pick the brand and performance split · Never set a bid, a bid cap or a target cost
- Returns
- Campaign architecture: {account or brand} · {platform(s)} · {period}
One of six skills in the kit · All of them install the same way
The contents, in full · six skills, one subagent, one command
- 01campaign-architectureObjectives and a budget in, the account structure out: campaigns, ad sets and placements with the logic behind each, a naming convention, the brand and performance split as you set it, and the consolidation rules that keep the account out of the learning phase.
- 02audience-planThe audience strategy for a campaign: broad, segmented and retargeting layers, exclusions and suppression, sequencing, frequency caps, and the reach layer the manual says most accounts cut first and should not.
- 03creative-testing-matrixHypotheses, variables and formats laid out so each test changes one thing, with the decision rule, the minimum evidence you set, and what "won" means, written before launch.
- 04optimisation-logThe weekly log: what changed, why, the expected effect, the metric that shows it, and the date it is reviewed. Refuses entries without a reason.
- 05frequency-reviewReach and frequency read against the plan, mid-flight or after it: delivery against the caps you set, the share of impressions above the cap where your export carries the distribution, and a fatigue verdict only issued when the metric falls, frequency rises and the audience holds. It ends with one proposed decision, never with three.
- 06post-flight-reviewA campaign closed properly: objective against result, platform-reported against independently verifiable, what the creative tests settled, what the account learned, and the next test.
- 07account-auditor (subagent)Reads campaign, ad set and ad exports and reports structural problems: fragmentation, overlap, frequency, learning-phase churn, budget spread too thin. Read-only; it never touches the account.
- 08/post-flightThe slash command that opens the campaign review from an export and a sentence.
Paid social is the budget most marketing teams touch every day and understand least. Think Like a CMO holds that reach among people who are not yet buying is how brands grow, and that marketing ROI as the platforms report it is a broken speedometer. The Paid Social Desk runs an account to that position: a structure decided by you, audiences built for mental availability rather than only the last click. Budgets, bids, benchmarks and audience sizes come from you or your export; the tools never estimate them.
Pairs with
Think Like a CMO explains where demand comes from and why the platforms measure the wrong thing. The End of the Click shows where the budget is moving. This kit runs the channel between those two arguments. It complements the ad-copy-studio skill in The Augmented Practitioner, which writes the ads this kit structures, tests and reviews.
Before you buy
01Do I need Claude Code?
No. Every skill uploads to claude.ai as a zip. Subagents and slash commands are the Claude Code extras.
02I am not a programmer.
Install is copying folders into a .claude directory. The Field Guide in each kit assumes nothing beyond that.
03Will it work in my agent?
Skills follow the open Agent Skills standard (SKILL.md), so any agent that reads it can run them. Built for Claude first, our recommended agent.
04Do the tools invent numbers?
Never. Every figure is supplied by you, confirmed by you, or labeled as an assumption in the output.
05How does it arrive?
Instantly. Pay by card and the download link is in your inbox within seconds, and on the confirmation screen.
06Is this a subscription?
No. One payment, lifetime access to your download, every future revision of what you bought included.
07What if it is not useful to me?
Write to info@conclusionmp.com within 14 days of purchase and you get a full refund. No questions, no forms.
Ready when you are
The Paid Social Desk, $12.
Instant download, one payment, every future revision included. Or take The Agency Desk, four items for $35, and this kit works out at $8.75.