The Search Shift Kit
Skills · Subagent · Command · PDF
.claude/the-search-shift-kit/zip
skills/06
├ ai-visibility-audit
├ answer-engine-brief
├ brand-query-defense
├ citation-monitor
├ schema-architect
├ zero-click-plan
agents/01
├ serp-analyst
commands/01
├ /ai-visibility
FIELD-GUIDE.pdf8pp
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 Search Shift Kit
Visibility when the click stops arriving
six skills·one subagent·one command·8-page guide
Your agent builds the question bank, scores the answers you paste from each engine the same way every month, and briefs the pages that get cited instead of clicked.
Executive summary
- The problem
- Organic clicks fall while the dashboard still reports rankings, and nobody can say whether the brand is named, cited or absent in the answers buyers now read. A spot check in one engine on one day gets reported as a trend.
- What it does
- Six skills and a serp-analyst subagent build a fixed bank of buyer questions, score pasted answers the same way every month, brief pages to be cited, write schema with no invented fields, and plan the next 90 days.
- Why take it
- When traffic falls, someone will ask whether search still works for you. This gives you a number that means the same thing every month, and a plan behind it.
For SEO leads, content strategists and marketers watching organic clicks fall while the answer stays on the results page.
In the first week you will
- 01Run /ai-visibility on your brand and category and get twenty to thirty buyer questions with the run instructions per engine
- 02Score the answers you paste back as mentioned, cited, recommended or absent, on a protocol that makes March comparable to January
- 03Write the next page with answer-engine-brief and add its JSON-LD with schema-architect, which fills no field you did not supply
Contents of the Kit
- 01Six installable agent skills: ai-visibility-audit, answer-engine-brief, schema-architect, brand-query-defense, zero-click-plan, citation-monitor
- 02The serp-analyst subagent: compares your page and a competitor page for the structural signals that decide who gets cited
- 03An /ai-visibility slash command that builds the prompt bank for any brand and category
- 04A prompt bank template of buyer questions by funnel stage, scored as mentioned, cited, recommended or absent
- 05An 8-page Field Guide on measuring visibility when clicks are no longer the metric
- 06Plugin manifest included: install as a Claude Code plugin or copy the folders
One skill, as it ships
SKILL.md
ai-visibility-audit
- Use when
- Use when a team needs a baseline of AI answer visibility, when organic clicks are falling and nobody knows whether the engines name the brand, or when planning content to earn citations. The skill does not query the engines; the user runs the prompts and pastes the answers back.
- Requires
- Brand name and a one-line description of what it sells · Category in the buyer's words · Market and language for the prompts · Pasted answers, one per prompt per engine
- Will not
- Never run, simulate or predict an engine's answer · Never infer a competitor's presence · No industry statistics about click loss or AI adoption anywhere in the output
- Returns
- AI Visibility Audit: {brand}
One of six skills in the kit · All of them install the same way
The contents, in full · six skills, one subagent, one command
- 01ai-visibility-auditBuilds a bank of twenty to thirty buyer questions from your category across the funnel, defines a scoring sheet (mentioned, cited, recommended, absent, and which competitors appear), and sets a monthly protocol so the number means the same thing in March as it did in January.
- 02answer-engine-briefA content brief written to be cited rather than clicked: entity-first structure, direct-answer paragraphs, claim plus source pairs, an FAQ block, freshness markers, author and organization signals. The writer executes; nothing is left to interpretation.
- 03schema-architectValid JSON-LD for Organization, Product, Article, FAQPage, HowTo and BreadcrumbList from facts you supply, with a validation checklist and one rule: no field is invented.
- 04brand-query-defenseThe queries you already own, held: the branded and navigational query set, the answer of record you want any engine to be able to give, how correctly each engine answers today, which surface it took that from, and the publication list that fixes what is wrong. A wrong answer carrying a citation ranks above an absent one.
- 05zero-click-planA 90-day plan for a site losing clicks: brand-query defense, owned-audience capture, snippet and AI Overview positioning, conversion of the clicks that remain, and the measurement changes that make the decline legible.
- 06citation-monitorA logging protocol and monthly report for where and how the brand is cited in AI answers, with a change log a client can read.
- 07serp-analyst (subagent)Fetches your URL and a competitor's and reports the structural differences that affect citability: answer-first paragraphs, question headings, schema present, dates, author.
- 08/ai-visibilityThe slash command that builds the prompt bank for any brand and category and opens the scoring.
The End of the Click makes the argument: search did not die, the click did, and the strategy that survives is the one that gets cited inside the answer. The Search Shift Kit is the working end of that argument. None of the tools query the answer engines for you; they do the repeatable part, so the results you paste in are read the same way in March as they were in January.
Pairs with
The End of the Click is the argument. This kit is the desk it gets executed from.
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 Search Shift Kit, $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.