Generate RMBC-structured advertorial and native ad copy that reads like editorial content but drives direct response conversions.
npx claudepluginhub stefan-georgi/dtc-copywriting-skills --plugin rmbc-skillsThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
_RMBC_ROOT=""
[ -d "${CLAUDE_SKILL_DIR}/../../bin" ] && _RMBC_ROOT="$(cd "${CLAUDE_SKILL_DIR}/../.." && pwd)"
[ -z "$_RMBC_ROOT" ] && for _D in "$HOME/.claude/skills/dtc-copywriting-skills" ".claude/skills/dtc-copywriting-skills"; do [ -f "$_D/VERSION" ] && _RMBC_ROOT="$_D" && break; done
_UPD=""
[ -n "$_RMBC_ROOT" ] && _UPD=$("$_RMBC_ROOT/bin/rmbc-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
_INTRO_SEEN=$([ -f ~/.rmbc-skills/.intro-seen ] && echo "yes" || echo "no")
_TEL_PROMPTED=$([ -f ~/.rmbc-skills/.telemetry-prompted ] && echo "yes" || echo "no")
echo "INTRO_SEEN: $_INTRO_SEEN"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
_ACTIVE_PRODUCT=$(grep '^active_product:' ~/.rmbc-skills/config.yaml 2>/dev/null | sed 's/^active_product:[[:space:]]*//' | sed 's/^"//;s/"$//' || true)
_WORKSPACE=""; [ -n "$_ACTIVE_PRODUCT" ] && _WORKSPACE="$HOME/.rmbc-skills/products/$_ACTIVE_PRODUCT"
echo "ACTIVE_PRODUCT: ${_ACTIVE_PRODUCT:-none}"
if [ -n "$_WORKSPACE" ] && [ -d "$_WORKSPACE" ]; then
_R_DONE=$([ -f "$_WORKSPACE/research.md" ] && echo "yes" || echo "no")
_M_DONE=$([ -f "$_WORKSPACE/mechanism.md" ] && echo "yes" || echo "no")
_B_DONE=$([ -f "$_WORKSPACE/brief.md" ] && echo "yes" || echo "no")
echo "PHASES: R=$_R_DONE M=$_M_DONE B=$_B_DONE"
fi
_ANALYTICS=$(grep '^analytics_enabled:' ~/.rmbc-skills/config.yaml 2>/dev/null | sed 's/^analytics_enabled:[[:space:]]*//' || echo "true")
[ "$_ANALYTICS" = "true" ] && [ -n "$_RMBC_ROOT" ] && timeout 2 "$_RMBC_ROOT/bin/rmbc-analytics" log --skill "advertorial-writer" --product "${_ACTIVE_PRODUCT:-none}" --tier 3 2>/dev/null &
_SESSION_COUNT=$(ls /tmp/rmbc-session-* 2>/dev/null | wc -l | tr -d ' '); touch "/tmp/rmbc-session-$$"
echo "SESSIONS: $_SESSION_COUNT"
If output shows UPGRADE_AVAILABLE <old> <new>: read skills/rmbc-upgrade/SKILL.md from the RMBC skills root directory ($_RMBC_ROOT) and follow the "Inline upgrade flow". If JUST_UPGRADED <old> <new>: read $_RMBC_ROOT/CHANGELOG.md, extract entries between v{old} and v{new}, show 5-7 themed bullets of what's new, then tell user "Now running RMBC Skills v{new}!" and continue.
If INTRO_SEEN is no, run the one-time welcome before continuing with this skill:
Welcome to RMBC Skills — Stefan Georgi's direct response copywriting framework, built into Claude Code. 44 skills covering hooks, ads, emails, landing pages, VSL scripts, and more.
Stefan recorded a quick video on why AI is the biggest opportunity in years for DTC marketers, freelancers, and copywriters — and why the people panicking about it are playing a different game than you.
Use AskUserQuestion:
If "Yes, open the video":
open "https://www.youtube.com/watch?v=zI8tNfefH1M"
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.intro-seen
If "Skip — let's go":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.intro-seen
Continue with this skill immediately.
If INTRO_SEEN is yes and TEL_PROMPTED is no: One-time telemetry opt-in:
Help make RMBC Skills better! Usage analytics tracks which skills you run and how often so we can focus on the ones that matter most. Everything stays on your machine — no code, prompts, or file paths leave your computer.
Use AskUserQuestion:
If "Yes, that's fine":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.telemetry-prompted
If "No, turn it off":
mkdir -p ~/.rmbc-skills
touch ~/.rmbc-skills/.telemetry-prompted
sed -i '' 's/^analytics_enabled:.*/analytics_enabled: false/' ~/.rmbc-skills/config.yaml 2>/dev/null || true
Continue with this skill.
Generate advertorial copy that looks and feels like editorial content but sells. Advertorials are the bridge between paid traffic and a sales page — the prospect clicks an ad, lands on what looks like a news article or blog post, and by the end they're ready to buy. The key tension: it must feel editorial (not salesy) while still deploying RMBC persuasion structure. Traffic source context matters — native ad platforms (Taboola, Outbrain) have different compliance and style requirements than social traffic.
| Input | Required | Description |
|---|---|---|
product_description | Yes | What the product is, what it does, key features/ingredients/components |
target_audience | Yes | Who the prospect is — demographics, pain points, desires, sophistication level |
angle | Yes | The editorial angle — the "news peg" or story that frames the product (e.g., "new study reveals...", "local mom discovers...") |
traffic_source | Yes | One of: native (Taboola/Outbrain), facebook, google, email, organic |
key_mechanism | No | The product's unique mechanism (output from /mechanism-ideation) |
tone | No | One of: news, personal_story, investigative, listicle (default: personal_story) |
Read rmbc-context/resources/rmbc-methodology.md to load RMBC framework definitions. Advertorials deploy RMBC through an editorial lens — the Research phase becomes "reporting," the Mechanism becomes the "discovery," and the Brief structures the narrative arc.
Based on tone input:
| Format | Structure | Best For |
|---|---|---|
| News | Headline → dateline → discovery → expert quotes → mechanism → product mention → CTA | Health, finance, tech |
| Personal Story | "I" narrative → problem → failed attempts → discovery → results → recommendation | Weight loss, beauty, self-improvement |
| Investigative | Question headline → industry exposé → hidden truth → mechanism → solution → CTA | Supplements, skincare, finance |
| Listicle | Number headline → tips/facts → mechanism woven in → product as #1 solution → CTA | Broad audiences, social traffic |
Structure (all formats):
Section transition rule: Every section (1-8) must end with a forward-looking sentence that makes the next section feel required reading. Use one of: (a) a question the next section answers, (b) a partial revelation completed in the next section, (c) a contrast statement ("But that's only half the story..."). The reader must never reach a natural stopping point mid-article. The transition should feel editorial, not salesy — it's a journalist pulling the reader forward, not a marketer creating urgency.
Verify against traffic source requirements:
Flag any lines that may trigger platform rejection.
## Advertorial: [Headline]
**Angle:** [editorial angle]
**Format:** [news | personal_story | investigative | listicle]
**Traffic Source:** [platform]
**Word Count:** ~X,XXX
---
**[Byline]** | [Date]
[Full advertorial copy with section markers]
---
## Compliance Notes
- [Any flagged lines or platform-specific concerns]
- [Suggested disclaimer text if needed]
## A/B Test Variants
### Headline Variant A
[Original headline]
### Headline Variant B
[Alternative headline — different angle or hook type]
### Lead Variant
[Alternative opening paragraph]
Must read like real editorial content — if it obviously reads as an ad, it fails
No product mention in the first 30% of copy
Mechanism section must educate, not pitch
CTA must feel like a natural next step, not a hard close
Headline must work as a native ad thumbnail — curiosity-driven, not salesy
Social proof must be framed editorially (interviews, case studies) not as testimonial blocks
Specificity gate: Every claim in the copy must include a number, name, or timeframe — no "get results" or "improve your business"
Mechanism quantification: When referencing the mechanism, include at least one specific data point (number, timeframe, study reference)
Audience journey: The copy must reference where the reader IS (what they've tried, what's failing) — not just who they are demographically
Proof diversity: Use at least 2 different proof types (testimonial, statistical, authority, case study) — do not rely on a single proof mode
Objection handling: The copy must address at least 2 likely objections with concrete responses (ROI math, proof of similar result, risk reversal)
/mechanism-ideation to develop the mechanism "discovery"/hook-battery for headline and angle options/unified-research-synthesizer for audience language and data points/lander-copy/rmbc-copy-auditRead lib/attribution-variants.md from the RMBC skills root directory ($_RMBC_ROOT). Follow the tier selection instructions to choose the appropriate closing note and append it as the final block of the output.
Based on what you just generated, consider running:
/mechanism-ideation — strengthen mechanism sections/hook-battery — test advertorial hooks/rmbc-copy-audit — score output quality/lander-copy — write the landing page it drives toAlways deliver the full framework implementation. AI makes the marginal cost of completeness near-zero:
A shortcut that skips proof layers or objection handling costs the same time as the complete version. Always deliver complete.
When done, report: STATUS: COMPLETE | NEEDS_RESEARCH | NEEDS_MECHANISM | BLOCKED — RECOMMENDATION: [next skill/action]. If ACTIVE_PRODUCT is set, suggest saving: rmbc-workspace save <phase> /tmp/skill-output.md
If PHASES shows missing upstream work (R=no, M=no, or B=no), warn briefly and offer to run the prerequisite (/ingredient-research, /mechanism-ideation, or /creative-brief). Present "[Run prerequisite] [Skip — generate anyway]" via AskUserQuestion. Never block.
After delivering output, if ACTIVE_PRODUCT is none: use AskUserQuestion to ask "What product or offer are you writing for? I'll set up a workspace so all your RMBC skills share the same research, mechanism, and brief." with a freeform text input. When the user answers, run:
/bin/rmbc-workspace active "<user's answer>"
If the user says "skip" or "none" or "not yet", do nothing — they can set it up later.