The Content Desk
Skills · Subagent · Command · PDF
.claude/the-content-desk/zip
skills/06
├ claims-register
├ content-audit
├ content-qa
├ editorial-calendar
├ original-data-plan
├ repurposing-chain
agents/01
├ archive-reader
commands/01
├ /calendar
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 Content Desk
The editorial system that earns the citation
six skills·one subagent·one command·9-page guide
Your agent holds one list of every claim the brand makes in public, plans the quarter from the positions behind them, and checks each draft against both before it ships.
Executive summary
- The problem
- The same claim appears in a blog post, a newsletter and a sales deck with three different numbers, and one of them has no source anyone can find. Nobody notices until an answer engine, a journalist or a customer compares them, and the brand is quoted contradicting itself.
- What it does
- claims-register keeps one sourced list every channel quotes, editorial-calendar plans the quarter from positions rather than keywords, content-qa returns every unsourced claim as a fix, and the archive-reader subagent maps what you have already published.
- Why take it
- When search ends on the results page, a citation goes to claims that hold up. One register means nothing ships that the organization cannot support.
For content leads, editors and marketing teams publishing into an answer engine that resolves the query on the results page.
In the first week you will
- 01Build the claims register in the first session so content, email and sales quote one sourced list instead of three
- 02Run /calendar on the positions the brand holds and get a quarter of pieces, each with its question, its citation target and its owner
- 03Run content-qa on the next draft and get the unsourced claims and the numbers without a source back as a list of fixes
Contents of the Kit
- 01Six installable agent skills: claims-register, editorial-calendar, original-data-plan, repurposing-chain, content-qa, content-audit
- 02The archive-reader subagent: reads the existing content folder and reports the topics covered, the claims made and the gaps between them. Read-only
- 03A /calendar slash command that plans a quarter from the positions the brand holds
- 04A claims register that gives content and email one list of what the brand says in public, each claim with its source, so nothing ships unsourced
- 05Blank templates for the claims register and the editorial calendar
- 06A 9-page Field Guide on running content as a system, and plugin manifest included
One skill, as it ships
SKILL.md
claims-register
- Use when
- Use when a team needs one list of what the organization says about itself and its market, when a page, deck or newsletter carries a claim nobody can trace, when an archive-reader report lists numbers without a source, or when content and email must say the same thing. Never softens an unsourced claim into a safer sentence; it returns it as unsourced.
- Requires
- Material to extract claims from · The source for each claim, as the user knows it
- Will not
- Never invent a source, a sample size, a date or an owner · The skill does not assume a claim was checked because it was published · Retired rows are never deleted
- Returns
- Claims register: {organization} · updated {date} · {new register / n rows added, n changed}
One of six skills in the kit · All of them install the same way
The contents, in full · six skills, one subagent, one command
- 01claims-registerEvery claim the brand makes in public, one row each: the claim, its source, the date it was last verified, who owns it, where it appears, and its status (supported, external, aging, unsourced, retired). The list content and email both draw from.
- 02editorial-calendarA quarter of content from the positions the brand holds: each piece with the position it argues, the question it answers, the citation target (which query, which engine, which competitor currently holds it), the format, the owner and the date. Refuses a calendar built from keywords alone.
- 03original-data-planWhat the organization could publish that nobody else has (its own numbers, its own survey, its own observations), how to collect it, the sample it needs, how to present it so it can be cited, and the claims it would add to the register.
- 04repurposing-chainOne source piece into the formats the plan needs, each with its own job, its own audience and its own call to action: the newsletter issue, the short post, the talk outline, the sales one-pager. Names what should not be repurposed.
- 05content-qaA draft against the house position, the claims register and the no-invented-numbers rule: unsourced claims, claims that contradict the register, numbers without a source, expert input that is asserted rather than shown. Returns the list of fixes with the line each applies to.
- 06content-auditWhat exists, what is cited, what still earns traffic, what is out of date and what is dead weight, from your inventory export, your analytics and the citation-monitor's log. Produces the keep, update, merge and retire list with a reason per row.
- 07archive-reader (subagent)Reads the existing content folder and reports the topics covered, the claims made and where, the positions taken, the numbers quoted without a source, and the gaps against the positions the brand says it holds. Read-only, with the file named for each finding.
- 08/calendarPlans a quarter from the positions the brand holds and the citation each piece should earn. Given a list of keywords with no position behind them it stops and asks for the positions, and it estimates no search volume, traffic or citation odds.
The End of the Click measures what happens when the answer engine resolves the query on the results page: most searches end without a click, and the pages that keep their traffic are the ones the engines cite. The Search Shift Kit handles one page for one query. The Content Desk works one level up, on the editorial system that decides what gets written, from which positions and with which claims. A claim without a source is returned as unsourced, not softened into a safer sentence, and a statistic the organization did not measure is marked as external and cited to where it came from.
Pairs with
The End of the Click is the argument: the citation is the currency, earned with original work a machine can corroborate. The Search Shift Kit wins one page at a time; this kit runs the system that produces the pages. The Email Engine and its newsletter-issue skill are the last link in the repurposing chain, and both kits read from the same claims register.
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 Content Desk, $12.
Instant download, one payment, every future revision included. Or take The Growth Desk, five items for $39, and this kit works out at $7.80.