Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add varunk130/ai-ux-skill-library --skill ai-conversation-architectgit clone --depth 1 https://github.com/varunk130/ai-ux-skill-libraryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-conversation-architect)<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-conversation-architect"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-conversation-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-conversation-architect"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-conversation-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01971 |
| Opus 5 | $0.00028 | $0.00986 |
| Sonnet 5 | $0.00011 | $0.00394 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
ai-conversation-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Conversation Architect
Design conversations between humans and AI that are natural, purposeful, and resilient. The DIALOGUE framework ensures every conversational AI experience handles the full spectrum from first message to complex multi-turn reasoning.
Core Principle
A conversation with AI is not a command line with friendlier words. It is a collaborative sense-making process where both parties contribute, clarify, and course-correct. Design for the collaboration, not just the query.
The DIALOGUE Framework
| Letter | Phase | Design Question |
|---|---|---|
| D | Discover Intent | How does the system understand what the user actually wants (not just what they typed)? |
| I | Identify Ambiguity | Where might the user's request be unclear, and how does the AI ask for clarification without interrogating? |
| A | Adapt Tone | How does the AI match the user's emotional state, formality, and expertise level? |
| L | Layer Information | How is the response structured so users get the right depth - summary first, details on demand? |
| O | Offer Navigation | How does the AI help users explore related topics, refine their question, or pivot direction? |
| G | Guard Boundaries | How does the AI communicate what it can and cannot do without breaking conversational flow? |
| U | Understand Memory | How does the conversation maintain context across turns, sessions, and time? |
| E | Exit Gracefully | How does the conversation end - or hand off to a human - without abandoning the user? |
Conversation Turn Anatomy
Every AI response has four invisible layers. Design all four explicitly:
| Layer | What It Does | Example |
|---|---|---|
| Acknowledgment | Shows the AI understood the input | "You're asking about deployment options for your EU customers." |
| Substance | Delivers the actual answer or action | The core content, recommendation, or task completion |
| Orientation | Tells the user where they are and what's possible next | "Would you like me to compare the pricing for each option?" |
| Metacommunication | Signals about the conversation itself (confidence, limitations) | "I'm fairly confident about this, but you should verify the regulatory details." |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 156 lines · 56 tokens per session scan A 4d196523a7e2
ai-conversation-architect is a skill published in the GitHub repository varunk130/ai-ux-skill-library (3 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,971 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
component-family-consistency
Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library…
modular-scale-typography
Typography feels cohesive and intentional when font sizes follow a modular scale — a ratio-based sequence where every size is mathematically related to the others. Use when defining type scales, setting up design tokens, reviewing font size choices, or when typography feels inconsistent or arbitrary.
extract-design
Extract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — from any live website using Dembrandt. Runs a headless browser against the URL and returns real computed values from the DOM. Use when you need a site's actual design tokens, want to reverse-engineer a visual…
algorithmic-color-palette
Derive a full UI colour palette algorithmically from one or two brand colours. Darker and lighter variants for interactive states, desaturated greys from the brand hue for borders and backgrounds, and semantic colours that feel coherent with the brand rather than generic. Use when building a colour system from scratch…
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…