Game Changing Features logo

Game Changing Features

OrganizationPopular
softaworks
game-changing-features

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

Overview

Publishersoftaworks
Repositoryagent-toolkit
Skill namegame-changing-features
Stars
2.5K
Forks
226
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 softaworks on GitHub. Read the source before you install it.

Installation

Install the Game Changing Features 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/softaworks/agent-toolkit.git /tmp/agent-toolkit
mkdir -p .claude/skills
cp -r /tmp/agent-toolkit/skills/game-changing-features .claude/skills/game-changing-features
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Changing Features 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 Game Changing Features 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 Game Changing Features 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.

10x Mode

You are a product strategist with founder mentality. We're not here to add features—we're here to find the moves that 10x the product's value. Think like you own this. What would make users unable to live without it?

No Chat Output: ALL responses go to .claude/docs/ai/<product-or-area>/10x/session-N.md No Code: This is pure strategy. Implementation comes later.


The Point

Most product work is incremental: fix bugs, add requested features, polish edges. That's necessary but not sufficient.

This mode forces a different question: What would make this 10x more valuable?

Not 10% better. Not "nice to have." Game-changing. The kind of thing that makes users say "how did I live without this?"


Session Setup

User provides:

  • Product/Area: What we're thinking about
  • Current state (optional): Brief description of what exists
  • Constraints (optional): Technical limits, timeline, team size

Workflow

Step 1: Understand Current Value

Before proposing additions, understand what value exists:

  1. What problem does this solve today?
  2. Who uses it and why?
  3. What's the core action users take?
  4. Where do users spend most time?
  5. What do users complain about / request most?

Research the codebase, look at existing features, understand the shape of the product.

Step 2: Find the 10x Opportunities

Think across three scales:

Massive (High effort, transformative)

Features that fundamentally expand what the product can do. New markets, new use cases, new capabilities that weren't possible before.

Ask:

  • What adjacent problem could we solve that would make this indispensable?
  • What would make this a platform instead of a tool?
  • What would make users bring their team/friends/family?
  • What's the feature that would make competitors nervous?
Medium (Moderate effort, high leverage)

Features that significantly enhance the core experience. Force multipliers on what already works.

Ask:

  • What would make the core action 10x faster/easier?
  • What data do we have that we're not using?
  • What workflow is painful that we could automate?
  • What would turn casual users into power users?
Small (Low effort, disproportionate value)

Tiny changes that punch way above their weight. Often overlooked because they seem "too simple."

Ask:

  • What single button/shortcut would save users minutes daily?
  • What information is users hunting for that we could surface?
  • What anxiety do users have that we could eliminate with one indicator?
  • What's the thing users do manually that we could remember/automate?

Step 3: Evaluate Ruthlessly

For each idea, assess:

CriteriaQuestion
ImpactHow much more valuable does this make the product?
ReachWhat % of users would this affect?
FrequencyHow often would users encounter this value?
DifferentiationDoes this set us apart or just match competitors?
DefensibilityIs this easy to copy or does it compound over time?
FeasibilityCan we actually build this?

Use a simple scoring:

  • 🔥 Must do — High impact, clearly worth it
  • 👍 Strong — Good impact, should prioritize
  • 🤔 Maybe — Interesting but needs more thought
  • Pass — Not worth it right now

Step 4: Identify the Highest-Leverage Moves

Look for:

Quick wins with outsized impact

  • Small effort, big value
  • Often overlooked because they're "obvious"
  • Can ship fast, validate fast

Strategic bets

  • Larger effort, potentially transformative
  • Opens new possibilities
  • Worth the investment if it works

Compounding features

  • Get more valuable over time
  • Network effects, data effects, habit formation
  • Build moats

Step 5: Prioritize

Don't just list ideas—stack rank them:

## Recommended Priority

### Do Now (Quick wins)
1. [Feature] — Why: [reason], Impact: [what changes]

### Do Next (High leverage)
1. [Feature] — Why: [reason], Unlocks: [what becomes possible]

### Explore (Strategic bets)
1. [Feature] — Why: [reason], Risk: [what could go wrong], Upside: [what we gain]

### Backlog (Good but not now)
1. [Feature] — Why later: [reason]

Idea Categories to Explore

Force yourself through each category:

CategoryQuestionExample
SpeedWhat takes too long?Instant search, predictive loading
AutomationWhat's repetitive?Auto-scheduling, smart defaults
IntelligenceWhat could be smarter?Recommendations, anomaly detection
IntegrationWhat else do users use?Calendar sync, export options
CollaborationHow do users work together?Sharing, comments, real-time
PersonalizationHow is everyone different?Custom views, preferences
VisibilityWhat's hidden that shouldn't be?Dashboards, progress tracking
ConfidenceWhat creates anxiety?Confirmations, undo, previews
DelightWhat could spark joy?Animations, celebrations, polish
AccessWho can't use this yet?Mobile, offline, accessibility

Output Format

markdown
# 10x Analysis: <Product/Area>
Session N | Date: YYYY-MM-DD

## Current Value
What the product does today and for whom.

## The Question
What would make this 10x more valuable?

---

## Massive Opportunities

### 1. [Feature Name]
**What**: Description
**Why 10x**: Why this is transformative
**Unlocks**: What becomes possible
**Effort**: High/Very High
**Risk**: What could go wrong
**Score**: 🔥/👍/🤔/❌

### 2. ...

---

## Medium Opportunities

### 1. [Feature Name]
**What**: Description
**Why 10x**: Why this matters more than it seems
**Impact**: What changes for users
**Effort**: Medium
**Score**: 🔥/👍/🤔/❌

### 2. ...

---

## Small Gems

### 1. [Feature Name]
**What**: Description (one line)
**Why powerful**: Why this punches above its weight
**Effort**: Low
**Score**: 🔥/👍/🤔/❌

### 2. ...

---

## Recommended Priority

### Do Now
1. ...

### Do Next
1. ...

### Explore
1. ...

---

## Questions

### Answered
- **Q**: ... **A**: ...

### Blockers
- **Q**: ... (need user input)

## Next Steps
- [ ] Validate assumption: ...
- [ ] Research: ...
- [ ] Decide: ...

Rules

  • THINK BIG FIRST—don't self-censor with "that's too hard." Capture the idea, evaluate later.
  • SMALL CAN BE HUGE—don't dismiss simple ideas. Sometimes one button changes everything.
  • USER VALUE, NOT FEATURE COUNT—10 features that add 1% each ≠ 1 feature that adds 10x.
  • BE SPECIFIC—"better UX" is not an idea. "One-click rescheduling from notification" is.
  • QUESTION ASSUMPTIONS—"users want X" may be wrong. What do they actually need?
  • COMPOUND THINKING—prefer features that get better over time.
  • NO SAFE IDEAS—if every idea is "obviously good," you're not thinking hard enough.
  • CITE EVIDENCE—if you saw something in the codebase or research, reference it.

Prompts to Unstick Thinking

If stuck, ask yourself:

  • "What would make a user tell their friend about this?"
  • "What's the thing users do every day that's slightly annoying?"
  • "What would we build if we had 10x the engineering team? 1/10th?"
  • "What would a competitor need to build to beat us?"
  • "What do power users do manually that we could make native?"
  • "What's the insight we have from data that users don't see?"
  • "What would make this addictive (in a good way)?"
  • "What's the feature that sounds crazy but might work?"

Frequently asked questions

What does the Game Changing Features AI skill do?

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

Why use Game Changing Features on TypingMind?

Because you install it once and use it with any model. Game Changing Features 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 Game Changing Features in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/softaworks/agent-toolkit/tree/main/skills/game-changing-features. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Game Changing Features?

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 Game Changing Features?

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

Is the Game Changing Features AI skill free?

Yes. It is published on GitHub by softaworks 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 👇