game-changing-features
Skill0 starsChanged 4 months agoMITView on GitHub
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'.
7 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- Ivan-propio/claude-skillsword for word, first seen Nov 16, 2026
- Samueladewole/claude-skillsword for word, first seen Oct 13, 2026
- openstatusHQ/data-table-filtersedited, first seen Oct 8, 2026
- nbirkner/digital-brainedited, first seen Apr 12, 2026
- FelipeAngeli/skillsword for word, first seen Apr 10, 2026
- uts58/my-random-skillsword for word, first seen Feb 23, 2026
Used with
Projects with it also use web-design-guidelines.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillweb-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 4
- FelipeAngeli/skills★ 2100% same
- Ivan-propio/claude-skills★ 0100% same
- Samueladewole/claude-skills★ 0100% same
- uts58/my-random-skills★ 0100% same
Edited · 3
- openstatusHQ/data-table-filters★ 2.3k100% same
- wpank/ai★ 1158% same
- nbirkner/digital-brain★ 041% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository121 other files it gives its agents.
- agent-md-refactorSkill
- backend-to-frontend-handoff-docsSkill
- c4-architectureSkill
- codexSkill
- command-creatorSkill
- commit-workSkill
- crafting-effective-readmesSkill
- daily-meeting-updateSkill
- database-schema-designerSkill
- datadog-cliSkill
- dependency-updaterSkill
- agency-brand-guardianSkill
- design-system-starterSkill
- agency-ui-designerSkill
- agency-ux-researcherSkill
- difficult-workplace-conversationsSkill
- domain-name-brainstormerSkill
- draw-ioSkill
- agency-ai-data-remediation-engineerSkill
- agency-ai-engineerSkill
- agency-api-platform-engineerSkill
- agency-autonomous-optimization-architectSkill
- agency-backend-architectSkill
- agency-cms-developerSkill
- agency-codebase-onboarding-engineerSkill
- agency-code-reviewerSkill
- agency-database-optimizerSkill
- agency-database-reliability-engineerSkill
- agency-data-engineerSkill
- agency-data-visualization-engineerSkill
- agency-desktop-app-engineerSkill
- agency-devops-automatorSkill
- agency-drupal-performance-engineerSkill
- agency-drupal-shopping-cart-engineerSkill
- agency-email-intelligence-engineerSkill
- agency-embedded-firmware-engineerSkill
- agency-feishu-integration-developerSkill
- agency-filament-optimization-specialistSkill
- agency-finops-engineerSkill
- agency-frontend-developerSkill
- agency-gaussdb-expert-engineerSkill
- agency-git-workflow-masterSkill
- agency-internationalization-engineerSkill
- agency-identity-access-engineerSkill
- agency-incident-response-commanderSkill
- agency-iot-fleet-engineerSkill
- agency-it-service-managerSkill
- agency-llm-post-training-engineerSkill
- agency-minimal-change-engineerSkill
- agency-mobile-app-builderSkill
- agency-mobile-release-engineerSkill
- agency-multi-agent-systems-architectSkill
- agency-network-engineerSkill
- agency-orgscript-engineerSkill
- agency-payments-billing-engineerSkill
- agency-privacy-engineerSkill
- agency-prompt-engineerSkill
- agency-rag-pipeline-engineerSkill
- agency-rapid-prototyperSkill
- agency-realtime-collaboration-engineerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. 5 are common, 0 are distinctive, and 0 are very specific to this project.
5
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 21
Not 10% better. Not "nice to have." Game-changing.
- Common: line 38
Before proposing additions, understand what value exists:
- Common: line 92
Use a simple scoring:
- Common: line 119
Don't just list ideas—stack rank them:
- Common: line 255
If stuck, ask yourself:
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.mdNo 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:
- What problem does this solve today?
- Who uses it and why?
- What's the core action users take?
- Where do users spend most time?
- 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:
| Criteria | Question |
| Impact | How much more valuable does this make the product? |
| Reach | What % of users would this affect? |
| Frequency | How often would users encounter this value? |
| Differentiation | Does this set us apart or just match competitors? |
| Defensibility | Is this easy to copy or does it compound over time? |
| Feasibility | Can 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:
| Category | Question | Example |
| Speed | What takes too long? | Instant search, predictive loading |
| Automation | What's repetitive? | Auto-scheduling, smart defaults |
| Intelligence | What could be smarter? | Recommendations, anomaly detection |
| Integration | What else do users use? | Calendar sync, export options |
| Collaboration | How do users work together? | Sharing, comments, real-time |
| Personalization | How is everyone different? | Custom views, preferences |
| Visibility | What's hidden that shouldn't be? | Dashboards, progress tracking |
| Confidence | What creates anxiety? | Confirmations, undo, previews |
| Delight | What could spark joy? | Animations, celebrations, polish |
| Access | Who can't use this yet? | Mobile, offline, accessibility |
Output Format
# 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?"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

