ucsandman/claude-skills / marketing
marketing
VerifiedUse when the user wants the complete marketing asset suite for a product in one run — "/marketing", "build all the marketing assets", "generate everything for the launch", "all the animations and brand assets for X". Not for a single asset (use that asset's own skill) and not for launch copywriting alone (use /launch).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 21.4 KB |
| references/campaign-evidence.md | markdown | 5.6 KB |
| references/hook-formulas.md | markdown | 3.5 KB |
references/hook-formulas.md
View on GitHub# Hook formulas and CTA rules for brief synthesis
Adapted from Corey Haines' marketingskills (github.com/coreyhaines31/marketingskills,
MIT): `social` and `copywriting` skills. Read this when synthesizing `brief.json`
(hook.headline, hook.altHeadlines, cta, social.*) so hook A/B variants compare
STRATEGIES, not three phrasings of the same idea.
## The rule for altHeadlines
`hook.altHeadlines` gets up to two alternates (render-hook-variants caps at 3 total).
Draw the headline and each alternate from a DIFFERENT category below, and record the
category names in `hook.strategies` (index-aligned with [headline, ...altHeadlines]) —
the storyboard, hook picker, and Mission Control variant radio all display them.
A/B between two curiosity hooks teaches nothing; curiosity vs value vs contrarian does.
## Hook categories (with the source's formula lines)
**Curiosity** (open a specific gap the video then closes):
- "I was wrong about [common belief]."
- "The real reason [outcome] happens isn't what you think."
- "[Impressive result], and it only took [surprisingly short time]."
**Story** (arc compressed to one line):
- "Last week, [unexpected thing] happened."
- "I almost [big mistake/failure]."
- "3 years ago, I [past state]. Today, [current state]."
**Value** (the outcome, minus the pain):
- "How to [desirable outcome] (without [common pain])"
- "[Number] [things] that [outcome]"
- "Stop [common mistake]. Do this instead:"
**Contrarian** (bold claim the demo backs up):
- "Unpopular opinion: [bold statement]"
- "[Common advice] is wrong. Here's why:"
- "I stopped [common practice] and [positive result]."
**Landing-style headline formulas** (from the copywriting skill, good for the
launch video's hook act and OG statics):
- "{Achieve outcome} without {pain point}"
- "The {category} for {audience}"
- "Never {unpleasant event} again"
- "{Question highlighting the main pain point}"
Ground every bracket fill in the brief's `audience.painPoints`,
`customerLanguage.use`, and `switchingForces` sections; a formula filled with
generic praise is worse than no formula.
## Vertical/short-form: the 3-second rule
The first second of a 9:16 clip needs three hooks at once:
`[VISUAL HOOK] + [VERBAL HOOK] + [TEXT OVERLAY]`. In this pipeline that means the
hook act's first frames already show the product moving (visual), the `hook`-act
narration line opens with the problem or result (verbal), and the headline text is
on screen (overlay). Tutorial-shaped demos show the END RESULT first.
## CTA formula
`[Action Verb] + [What They Get] + [Qualifier if needed]`
- Weak (lint-copy WARNs on these): Submit, Sign Up, Learn More, Click Here, Get Started
- Strong: "Start Free Trial", "See [Product] in Action", "Create Your First [Thing]",
"Simulate your first trade free"
The CTA says what they GET, not what to do. End-card and `brief.cta` both follow it;
`switchingForces.anxiety` tells you which reassurance the qualifier should carry
(free, no signup, local-only, etc.).
## Style rules the linter cannot fully check
- Specificity over vagueness: "Cut weekly reporting from 4 hours to 15 minutes"
beats "Save time on your workflow". Every number needs a `proofPoints` source.
- Customer language over company language: mirror `customerLanguage.use` verbatim;
never emit `customerLanguage.avoid` words.
- Active over passive, confident over qualified, one idea per act.
- Honest over sensational: a fabricated stat or testimonial is a hard stop
(trust and legal liability), never a style tradeoff.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |