Category Designer logo

Category Designer

Community
jiaxiaojunQAQ
category-designer

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the market", "position as category king", "new category", "category creation", "own a category", "category strategy", "competitive positioning", "strategic positioning", "market reframing", "be the only option", "change the buying criteria", "category king".

Overview

PublisherjiaxiaojunQAQ
RepositorySkillJect
Skill namecategory-designer
Stars
79
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jiaxiaojunQAQ on GitHub. Read the source before you install it.

Installation

Install the Category Designer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jiaxiaojunQAQ/SkillJect.git /tmp/SkillJect
mkdir -p .claude/skills
cp -r /tmp/SkillJect/data/skills_sample/category-designer .claude/skills/category-designer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Category Designer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Category Designer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Category Designer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Category Designer

Define a new category where your recommended product wins by default. Instead of competing on existing criteria ("best AI video tool"), reframe the buying decision so your product IS the category ("the AI avatar platform for non-creators"). Category kings capture 76% of category economics — this is the strategic meta-skill that makes all downstream marketing easier.

Stage

S8: Meta — This is cross-cutting strategic thinking, like funnel-planner. It operates above individual skills and reframes the entire marketing approach. Use it before creating content, offers, or landing pages.

When to Use

  • User is competing in a crowded market and needs to stand out
  • User asks about "positioning", "category", "differentiation", "reframing"
  • User says "category of one", "own a category", "change the game"
  • After monopoly-niche-finder to formalize the niche into a named category
  • After purple-cow-audit to amplify what makes a product remarkable
  • Before creating content/offers to ensure consistent category messaging

Input Schema

yaml
product: object               # REQUIRED — the product to position
  name: string
  description: string
  key_features: string[]
  pricing: string
  current_category: string    # What category it's currently in
                              # e.g., "AI video tools", "email marketing platforms"

competitors: string[]         # OPTIONAL — main competitors
                              # Default: auto-researched

your_audience: string         # OPTIONAL — your specific audience
                              # Default: inferred from product

monopoly_niche: string        # OPTIONAL — from monopoly-niche-finder
                              # Default: none

Chaining from S1 monopoly-niche-finder: Use monopoly_niche.intersection as the starting point for category design.

Chaining from S1 purple-cow-audit: Use remarkable_angles to identify category-defining features.

Workflow

Step 1: Analyze Current Category

  1. web_search: "best [current_category]" — see how the market is currently framed
  2. Identify the default buying criteria (price, features, ease of use, etc.)
  3. Map where the product wins AND loses on current criteria
  4. Identify: what does this product do that competitors DON'T even try?

Step 2: Find the Category Seed

The category seed is the intersection of:

  • What the product does uniquely well
  • What a specific audience cares about most
  • What competitors ignore or can't do

Formula: [Unique capability] + [Specific audience] + [Outcome they care about]

Example: "AI avatar platform" + "for non-creators" + "who need professional video content" = "AI Video Content Platform for Non-Creators"

Step 3: Design the Category

Define:

  1. Category name — 3-6 words, self-explanatory, memorable
  2. Category POV — "The old way was [X]. The new way is [Y]. [Product] is the [category name]."
  3. Buying criteria — new criteria where your product automatically wins
  4. Lightning strike — the "aha moment" that makes the category real (a stat, story, or demonstration)
  5. Category ecosystem — what other products/services exist in YOUR category (you define the landscape)

Step 4: Create Category Assets

Produce:

  1. Category narrative — 2-3 paragraph story of why this category exists now
  2. Comparison reframe — how to redirect "Product X vs Product Y" to "Old category vs New category"
  3. Content angles — 5-10 content pieces that educate the market about the category
  4. Objection handling — "Isn't this just [old category]?" → "No, because..."

Step 5: Self-Validation

  • Category name is self-explanatory to someone hearing it for the first time
  • Product genuinely wins on the new buying criteria (not forced)
  • Category is big enough to matter but specific enough to own
  • Narrative is compelling and truthful (not spin)
  • Content angles are substantial enough for 6+ months of content

Output Schema

yaml
output_schema_version: "1.0.0"
category:
  name: string                  # The new category name
  pov: string                   # Point of view statement
  product_name: string
  old_category: string          # What it was before
  buying_criteria: string[]     # New criteria where product wins
  lightning_strike: string      # The "aha" proof point

  narrative: string             # Category story (2-3 paragraphs)
  comparison_reframe: string    # How to redirect comparisons

  content_angles: string[]     # Content pieces that establish the category
  objection_responses: object[] # Objection handling
    - objection: string
      response: string

  category_definition: string  # For chaining — the full category definition
  category_framing: string     # For chaining — positioning statement

chain_metadata:
  skill_slug: "category-designer"
  stage: "meta"
  timestamp: string
  suggested_next:
    - "grand-slam-offer"
    - "monopoly-niche-finder"
    - "affiliate-blog-builder"
    - "landing-page-creator"

Output Format

## Category Design: [Category Name]

### The Shift
**Old category:** [what it was]
**New category:** [what it is now]
**Why now:** [why this category exists today]

### Category Definition
**[Category Name]:** [1 sentence definition]

### Point of View
"[The old way] was [X]. [The new way] is [Y]. [Product] is the [category name] that [outcome]."

### New Buying Criteria
When evaluating a [category name], look for:
1. [Criteria where your product wins]
2. [Criteria where your product wins]
3. [Criteria where your product wins]
(Note: [old criteria like "most features"] no longer matters because [reason])

### Lightning Strike
[The stat, story, or demo that makes the category undeniable]

### Category Narrative
[2-3 paragraphs telling the story of this category]

### Comparison Reframe
When someone asks "[Product] vs [Competitor]":
→ Reframe: "That's like comparing [new thing] to [old thing]. The question isn't [old criteria] — it's [new criteria]."

### Content Roadmap
1. "[Title]" — establishes the category problem
2. "[Title]" — introduces the new buying criteria
3. "[Title]" — showcases the product as category king
4. "[Title]" — data/proof that the new way works
5. "[Title]" — community/social proof

### Objection Handling
**"Isn't this just [old category]?"**
→ [Response]

**"Why should I care about a new category?"**
→ [Response]

Error Handling

  • No product provided: "Tell me the product and its current competitive landscape — I'll design a category it owns."
  • Product has no unique features: "Every product has something. Let me dig deeper..." → focus on audience specificity rather than feature uniqueness.
  • Category too forced: If the category feels artificial, recommend improving the product positioning within the existing category instead. Honesty > cleverness.
  • Too many competitors in proposed category: Narrow the audience further or combine with monopoly-niche-finder for a tighter intersection.

Examples

Example 1: "Design a category for HeyGen" → Old: "AI video tool." New: "AI Video Content Platform for Non-Creators." Buying criteria: no camera needed, no editing skills, no studio. Lightning strike: "84% of marketers say video is important, but only 15% make it regularly."

Example 2: "Position Semrush differently from Ahrefs" → Old: "SEO tool." New: "Revenue Intelligence Platform." Buying criteria: revenue attribution, not just rankings. Reframe: "Stop tracking keywords. Start tracking revenue."

Example 3: "Create a category for my niche" (after monopoly-niche-finder) → Take intersection niche, formalize into a named category with full narrative, buying criteria, and content roadmap.

Flywheel Connections

Feeds Into

  • grand-slam-offer (S4) — category framing becomes the offer's core positioning
  • monopoly-niche-finder (S1) — category definition sharpens niche targeting
  • landing-page-creator (S4) — category narrative for landing page hero
  • affiliate-blog-builder (S3) — content angles for category-establishing articles
  • viral-post-writer (S2) — category POV for shareable social content

Fed By

  • monopoly-niche-finder (S1) — niche to formalize into a category
  • purple-cow-audit (S1) — remarkable features that define the category
  • competitor-spy (S1) — competitive landscape to differentiate from

Feedback Loop

  • performance-report (S6) tracks which category messaging resonates → refine category name and POV based on engagement data

References

  • shared/references/affiliate-glossary.md — Terminology
  • shared/references/case-studies.md — Real positioning examples
  • shared/references/flywheel-connections.md — Master connection map

Frequently asked questions

What does the Category Designer AI skill do?

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the market", "position as category king", "new category", "category creation", "own a category", "category strategy", "competitive positioning", "strategic positioning", "market reframing", "be the only option", "change the buying criteria", "category king".

Why use Category Designer on TypingMind?

Because you install it once and use it with any model. Category Designer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Category Designer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jiaxiaojunQAQ/SkillJect/tree/main/data/skills_sample/category-designer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Category Designer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Category Designer?

As many as you like. As long as a model supports skills, you can use Category Designer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Category Designer AI skill free?

Yes. It is published on GitHub by jiaxiaojunQAQ under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇