Coding

Commerce Content Generator

Convert an evidence-backed product brief into channel-ready commerce copy with claim-safety notes.

What it does

Turn a product brief, audience, evidence, channel, and conversion goal into platform-specific commerce copy. Generate Xiaohongshu notes, Douyin scripts, live-selling flows, marketplace listings, ads, Moments posts, or Zhihu evaluations. Drafts use supplied facts, label assumptions, and include quality notes on risky claims and missing evidence.

When to use it

  • Launching one product across Xiaohongshu and Douyin
  • Building marketplace titles, bullets, and detail pages
  • Preparing live-selling scripts and objection responses
  • Creating A/B ad angles and CTA options

The skill document

Content Generator

Create platform-ready commerce content without inventing unsupported claims.

Workflow

  1. Capture the product brief:
    • product name, category, price or price range
    • target audience and use scenario
    • benefits, differentiators, proof points, limitations
    • platform, tone, length, conversion goal
    • forbidden claims or regulated categories
  2. If the brief is thin, ask for the missing business-critical facts. If the user wants speed, continue with explicit assumptions and mark 待补充证据.
  3. Select the right output pack:
    • Xiaohongshu: personal discovery note, practical list, comparison note
    • Douyin: short-video hook, spoken script, captions, CTA
    • Live selling: opening, demo flow, objections, close
    • Moments: concise social recommendation
    • Zhihu: rational evaluation and purchase advice
    • Marketplace: title, bullets, detail-page sections
    • Ads: A/B angle variants and CTA options
  4. Draft using only user-provided facts or clearly labeled assumptions.
  5. Run a quality pass before final output: evidence, platform fit, claim safety, specificity, and next data needed.

Deterministic Pack Generator

When the user wants a structured first draft, batch variants, or repeatable output, use:

node scripts/generate_content_pack.js --input product.json --format markdown

The input JSON can include:

{
  "name": "HydraGlow Cream",
  "category": "美妆",
  "price": "299",
  "audience": "commuters with dry skin",
  "scenario": "winter office skincare",
  "benefits": ["light texture", "long-lasting moisture"],
  "evidence": ["user test: 8-hour office day"],
  "limitations": ["not a medical treatment"],
  "tone": "calm and trustworthy",
  "platforms": ["xiaohongshu", "douyin", "marketplace"]
}

Read references/platform-playbook.md when platform details matter. Read references/quality-checklist.md before publishing, reviewing risky copy, or handling health, finance, legal, children, food, supplements, or high-priced products.

Output Contract

For user-facing answers, prefer this shape:

  • Brief: product, audience, goal, assumptions.
  • Content: platform-specific drafts.
  • Quality Notes: unsupported claims, risky phrases, missing evidence.
  • Next Iteration: what data would improve conversion or trust.

Do not claim guaranteed outcomes, medical effects, investment returns, legal compliance, official endorsement, scarcity, or comparative superiority unless the user supplied reliable evidence.

Questions people ask

What information should I provide?
Provide the product name, category, price, audience, use scenario, benefits, differentiators, proof points, limitations, platform, tone, length, conversion goal, and any forbidden claims. If critical facts are missing, the workflow asks for them or marks assumptions as `待补充证据` when speed is preferred.
Which channels and content formats are supported?
Supported packs cover Xiaohongshu, Douyin, live selling, Moments, Zhihu, marketplaces, and ads. Outputs can include discovery or comparison notes, hooks, spoken scripts, captions, CTAs, objection handling, titles, bullets, detail-page sections, and A/B angles.
How does it prevent unsupported marketing claims?
It drafts only from user-provided facts or clearly labeled assumptions, then checks evidence, platform fit, claim safety, specificity, and missing data. Guaranteed outcomes and sensitive claims are excluded unless reliable evidence was supplied.

Related skills

Video Generation

Create scripted, voiced, scored, and edited videos up to four minutes from a single prompt.

299 installs24 stars

Baoyu Comic

Create educational comics with structured storyboards, reusable prompts, batch-rendered pages, and PDF output.

136 installs1 stars

YouTube Video

Create YouTube videos, Shorts, thumbnails, and scripts from structured prompts through CellCog.

102 installs11 stars

Baoyu Xhs Images

Convert complex content into a consistent raster card series with selectable styles, layouts, and palettes.

123 installs2 stars

Comic Generator

Turn structured story prompts into sequential comic art with consistent characters, layouts, and visual flow.

110 installs3 stars