phonepe-visual-ui-craft
Universal visual-first UI architecture and audit engine inspired by PhonePe's hyper-intuitive, zero-literacy interface standard.
Skill by hemanth17r
Chalk Labs
Need help deploying phonepe-visual-ui-craft?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hemanth17r-phonepe-visual-ui-craft
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/phonepe-visual-ui-craft
What's inside
- Skill name
phonepe-visual-ui-craft- Description
- Universal visual-first UI architecture and audit engine inspired by PhonePe's hyper-intuitive, zero-literacy interface standard. Audits any web or mobile screen and refactors text-heavy cognitive friction into instant, semantic icon-anchored action tiles with 1-2 supporting words. Trigger when asked for "phonepe ui", "phonepe style", "phonepe audit", "icon first ui", "visual first ui", "too much reading", "make it visual like phonepe", "zero literacy ui", or when auditing interfaces for visual recognition over reading.
- License
- MIT
- Instructions
- 118 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Universal Visual-First UI Craft & Audit Standard (PhonePe Archetype)
## 1. The Core Philosophy: Visual Cognition Over Reading
Amateur interfaces force users to read sentences, parse syntax, and deduce action targets.
**PhonePe achieved rapid scale across 500M+ users across diverse languages and literacy levels because it eliminated the cognitive reading layer:**
> **"The human brain decodes visual metaphors in under 100ms. Reading requires an active, fatiguing translation cycle (Text → Syntax → Mental Image → Intent). Anchor the action in a universal real-world icon; use text only as a minimal 1–2 word stabilizer."**
### The Cognitive Hierarchy
```
[ 1. PHYSICAL ICON ANCHOR ] ──► Instant optical recognition (<100ms)
│
[ 2. STABILIZER LABEL ] ──► 1–2 words maximum; eliminates ambiguity
│
[ 3. PHYSICAL FEEDBACK ] ──► Spring press scale; tactile reassurance
```
---
## 2. The 4 Invariants of the PhonePe Action Tile
Every primary action, navigation target, or category in a visual-first interface must adhere to these 4 invariants:
### Invariant 1: Physical Metaphor Over Abstract Geometry
* ❌ **Anti-Pattern**: Using generic abstract shapes (hexagons, random diamonds, meaningless decorative circles).
* ✅ **Standard**: Ground icons in tangible real-world physical objects:
- Banking/Treasury → Classical bank pillar facade
- People/Transfers → Human silhouette or contact book
- Payments/Passbook → Physical wallet or physical receipt/ledger
- Location/Hive → Physical directional compass or street pin
- Tasks/Operations → Physical lightning bolt or toolpack
### Invariant 2: High-Contrast Tactile Container
* Every icon lives in an intentional tactile housing:
- Mobile: `w-12 h-12` to `w-14 h-14` rounded squircle (`rounded-2xl`) or perfect circle (`rounded-full`).
- Palette: Subtle tinted background (5–10% opacity of brand accent) with high-contrast glyph.
- Active state: Physical spring scale (`active:scale-95`).
### Invariant 3: The 1–2 Word Microcopy Stabilizer
* Never display naked, cryptic icons without supporting labels (causes guessing).
* Never display verbose phrases. Text must be strictly 1–2 words:
- ❌ *"Send money to mobile contact"* → ✅ **`To Mobile`**
- ❌ *"Check your bank account balance"* → ✅ **`Check Balance`**
- ❌ *"Transfer to bank account or UPI ID"* → ✅ **`To Bank`**
- ❌ *"Click here to view operations"* → ✅ **`Operations`**
- ❌ *"Add external proof and skills"* → ✅ **`Add Socials`**
### Invariant 4: Vertical Center-Aligned Grid Rhythms
* Action tiles are structured vertically: **Icon Top, Label Bottom**.
* Rendered in rigid, predictable grids (strictly 4-column on mobile, or 2-column split cards), never jagged horizontal wraps.
---
## 3. The 5 Visual-First Audit Traps (The Scythe Pass)
Whenever auditing any interface against this standard, search for and eliminate these 5 flaws:
### Trap 1: The Paragraph Card
* ❌ **Flaw**: A card containing 2–3 sentences explaining what a feature does before offering a link.
* ✅ **Fix**: Delete the paragraph. Replace with an icon-anchored tactile tile or a 3-tile grid with 1-word action triggers.
### Trap 2: The Naked Cryptic Glyph
* ❌ **Flaw**: Standalone icons in headers or rows with no text, leaving users guessing whether an icon means "history", "clock", or "activity".
* ✅ **Fix**: Pair the icon with a 1-word label directly underneath or to the right.
### Trap 3: The Verbose Action Button
* ❌ **Flaw**: Rectangular buttons crammed with instructional prose (*"Submit Verification Request"*).
* ✅ **Fix**: Icon + 1–2 words: `[ShieldCheck Icon] Verify`.
### Trap 4: Text-Only Filter Rows
* ❌ **Flaw**: Rows of plain text pill filters that look like boring documentation tags.
* ✅ **Fix**: Prefix each filter with its physical semantic glyph (`[★] 4.8+`, `[Compass] My Hive`, `[Zap] Instant`).
### Trap 5: Asymmetric Visual Weights
* ❌ **Flaw**: Mixing disparate icon sizes, stroke weights, or container radiuses on the same screen.
* ✅ **Fix**: Standardize icon bounding box (`w-5 h-5` stroke `[2.2]`), container bounds (`w-12 h-12`), and font sizes (`text-[11px]` font-bold).
---
## 4. The Standard Audit Deliverable Protocol
When triggered on any file, screen, or component, output the audit strictly using this 4-field dense format per item:
```markdown
### Visual Audit: [Screen/Component Name]
#### Item [N]: [Element Name]
- **Current Cognitive Friction**: [Exact sentence/text or broken visual layout causing cognitive reading delay]
- **Physical Metaphor**: [Physical icon chosen + rationale why it maps to mental memory]
- **Compressed Stabilizer**: [1–2 word replacement label]
- **Tactile Tile Transformation**: [Exact JSX/Tailwind snippet showing the icon container + vertical label layout]
```
---
## 5. Reference Archetype (JSX Blueprint)
```jsx
// Universal PhonePe Action Tile (React + Tailwind)
<button
type="button"
onClick={handleAction}
className="flex flex-col items-center justify-center p-2 group active:scale-95 transition-all cursor-pointer text-center"
>
{/* Tactile Icon Housing */}
<div className="w-12 h-12 rounded-2xl bg-primary/10 text-primary border border-primary/20 flex items-center justify-center mb-1.5 shadow-2xs group-hover:bg-primary/20 transition-colors">
<Building2 className="w-6 h-6 stroke-[2.2]" />
</div>
{/* 1-2 Word Stabilizer Label */}
<span className="text-[11px] font-black text-slate-800 leading-tight tracking-tight line-clamp-1">
To Bank
</span>
</button>
```From hemanth17r/ahr-workflow, MIT.
More from hemanth17r/ahr-workflow
- 0.645score
ground-up-engineering-protocol
hemanth17r
Universal architectural standard for autonomous coding agents to build any software system from scratch.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
grounded-founder-outreach
hemanth17r
Generates personalized, grounded, high-conviction founder outreach messages and application notes across all platforms (Wellfound, Y Combinator Work at a…
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
autonomous-division-of-labor
hemanth17r
Enforces maximum agent ownership and strict division of labor for setups, installations, and multi-device workflows.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
adversarial-mechanism-design
hemanth17r
Universal mechanism design, reverse game theory, incentive engineering, and adversarial bad-actor defense standard for ANY product, platform, or marketplace.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-db-resilience
hemanth17r
Universal database concurrency, production lock safety, and operational resilience standard.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-product-ux
hemanth17r
Universal product design, cognitive psychology, microcopy economy, and UX architecture standard (Apple, Google, Stripe level).
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-ui-craft
hemanth17r
Universal cognitive psychology and craftsmanship standard for high-conviction UI (Apple, Google, Linear, Stripe level).
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
blackbox-logic-flow-audit
hemanth17r
Universal programmatic black-box logic, wiring, and state flow verification standard across ANY software project.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-db-craft
hemanth17r
Universal database architecture and performance standard adapted from Big Tech for lean systems.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
feynman-intuitive-explainer
hemanth17r
Translates complex technical jargon, engineering architecture, and mathematical concepts into crystal-clear, intuitive real-world analogies (The Feynman…
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
fluid-tactile-motion
hemanth17r
Universal spring motion physics, tactile micro-interactions, and optimistic UI architecture standard (Apple iOS, Linear, LinkedIn level).
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
idea-reality-check
hemanth17r
Conducts a ruthless prior-art investigation, package shortcut check, and competitive reality check on technical tools, packages, or architectural proposals…
SkillAFreshness: A★ 22Claude Code +9
Signals
- Stars
- 22
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hemanth17r/ahr-workflow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from hemanth17r
- 0.645score
adversarial-mechanism-design
hemanth17r
Universal mechanism design, reverse game theory, incentive engineering, and adversarial bad-actor defense standard for ANY product, platform, or marketplace.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-product-ux
hemanth17r
Universal product design, cognitive psychology, microcopy economy, and UX architecture standard (Apple, Google, Stripe level).
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
autonomous-division-of-labor
hemanth17r
Enforces maximum agent ownership and strict division of labor for setups, installations, and multi-device workflows.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-db-craft
hemanth17r
Universal database architecture and performance standard adapted from Big Tech for lean systems.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-db-resilience
hemanth17r
Universal database concurrency, production lock safety, and operational resilience standard.
SkillAFreshness: A★ 22Claude Code +9 - 0.645score
big-tech-ui-craft
hemanth17r
Universal cognitive psychology and craftsmanship standard for high-conviction UI (Apple, Google, Linear, Stripe level).
SkillAFreshness: A★ 22Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get phonepe-visual-ui-craft running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
phonepe-visual-ui-craft skill. Agent Mart. https://agentmart.dev/skills/hemanth17r-phonepe-visual-ui-craft (last updated 2026-10-24)