The Stripped Claims

Every template on this site started as someone's sales pitch. This page collects the claims that didn't survive the rebuild — the unverifiable numbers, the guaranteed outcomes, the "this one prompt changes everything" framing — and why we cut each one.

✂ Stripped from the source

This pack is original, but the career-advice genre it sits beside is built on things we refuse to publish. No salary figures or "market rates" from an AI — pay is local and current, our training data is neither, and a confident wrong number loses you the room; every relevant skill sends you to real sources instead. No invented achievements or metrics to strengthen a case. No scripts for manipulating a manager, no fake competing offers, no leverage plays. No statements about employment law, notice, or your rights — those vary by country and contract, so we tell you what to check and who to ask. And no promises: a well-built case can still get a no, because budgets and decisions aren't yours to control. What the loop guarantees is that you'll know where you stand and have the evidence to act on it.

Claude + Codex Model Router

Ship a Landing Page

✂ Stripped from the source

This was rebuilt from a pack of eight "elite web architect" prompts drowning in invented jargon: "Asymmetric-Yield Semantic Skeleton", "Prestige-Identity Fluid Grid", "Pattern-Interrupt", "Humanized-Velocity Value Engine", "Skeptic-Filter Trust Shield". None of the coined names mean anything — they're the exact "rename a normal thing to sound proprietary" move this library exists to undo. Stripped: the manufactured terminology, the "immediate visual authority", "forces immediate interaction", "dissolving visitor skepticism", "ultra-premium launch" puffery, and "eliminate layout shift in 30 minutes" style promises. Also dropped from the original eight: two prompts that were pure conversion theater (a "proof-of-concept matrix that forces interaction" and a vague "3 interactive script layouts") with no real technique under them, and one that was just "write landing copy" — already covered by the content skills. What survived is five genuine front-end tasks. The techniques under them (semantic HTML, clamp() fluid type, Grid/Flexbox, dark-mode custom properties, Core Web Vitals) are current, verifiable best practice — not secrets, just craft.

The AI Video Pipeline

✂ Stripped from the source

The source sold this as a "money machine" that "replaces an entire video production company" for "$0 — no excuses." Stripped: the free tiers are real but constrained, and a pipeline is not revenue. Every prompt in the source claimed "20+ years of experience" for the AI's persona — fake credentials, removed; the instructions work without the costume. The guide's tool claim was already stale on arrival ("Cinema Studio 2.5" — the current release is 3.0), which is why this rebuild names features instead of versions. The monetization sections (faceless-channel ad revenue, "your first $1") were dropped from this workflow: earning from video is covered honestly by the Sell Something Pack; ad-revenue projections for new channels are lottery math we don't republish.

Build a Deck

✂ Stripped from the source

The source pack was genuinely good — rare enough to say so — and most of it survived the rebuild intact. What we cut: the "charge $2,000+ per project" credential flourish that framed the whole thing as a way to look like an expensive designer, and the "so it doesn't look AI-generated" hype that promised the output would pass as human-made work. The skills stand on what they actually do — clearer structure, one point per slide, honest charts — without the money and status framing. We also merged the source's two separate review prompts (brand consistency and design critique) into a single Polish Pass, because running one focused review beats running two that overlap. Every skill here is still marked tested: no until the deck it builds has been run for real.

Getting Good Care

✂ Stripped from the source

Health is the category where an invented answer does the most damage, so this pack is defined as much by what its skills refuse to do. None of them will suggest what might be wrong with you, name a possible condition, or rule anything in or out. None will tell you whether a result is good, bad, normal, or serious — reference ranges depend on the lab, the method, and the person. None will give risk percentages, success rates, or recovery times, because those depend on you and your clinician and a plausible-sounding number could change a decision that matters enormously; every skill sends you to ask for their figures, for someone in your situation. None recommends treatments, tests, or doses. None will ever suggest delaying or avoiding care, and each is built to stop and say "seek help now" rather than help you prepare for later, if what you describe sounds urgent. If you push any of these skills for "just your best guess", it is built to decline and tell you that is precisely what the appointment is for. That refusal is the feature.

Learn a Hard Thing

✂ Stripped from the source

This pack is original, and what it leaves out is deliberate. No learning styles — matching study to a "visual" or "auditory" type isn't supported by the evidence and we won't build on it. No invented study statistics, optimal hours, or "it takes N weeks" claims. No predicting what's on an exam and no fabricated past papers "in the style of" a real one — get the genuine materials or know you're guessing. No AI-written work to hand in: every relevant skill declines it, both because of the obvious risk and because it skips the exact process you're trying to build. And no pretending the AI is a trustworthy source of fact. Every skill in this pack is built to flag uncertainty, mark what it added from outside your text, and name what to verify — because the failure mode isn't an AI that refuses to answer, it's one that answers smoothly and slightly wrong, and you only find out much later.

The Paper Shield

The Paper Trail

Saying the Hard Thing

✂ Stripped from the source

This pack is original, but the genre it sits in is full of things we deliberately left out. No scripts to perform — every skill writes in your words and tells you to change anything that isn't you. No tactics, no leverage, no techniques for "winning" a conversation with someone you love; the aim is being understood and hearing them, which is a different goal with different words. No invented excuses for declining. No claims about what the other person thinks or feels — every skill hears one side and says so, and pushes back when you state their motives as fact. No therapy: these are preparation tools, not treatment, and where someone describes fear, control, or being hurt, every relevant skill is built to name it and point toward real support rather than coach better phrasing. And no promises. A well-prepared conversation can still go badly, because the other person gets a say — that is the point of talking to them.

The Stripped Claims

The Sell Something Pipeline

The Solo Strategy Stack

The Job Application Pipeline

The Work Year

Claude + Codex Model Router

Ship a Landing Page

The AI Video Pipeline

Build a Deck

Getting Good Care

Learn a Hard Thing

The Paper Shield

The Paper Trail

Saying the Hard Thing

The Claude Setup

The Weekly Planning Loop

The AI Safety Setup