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 ragnar-pwninskjold/tech-snacks --skill prd-to-uxgit clone --depth 1 https://github.com/ragnar-pwninskjold/tech-snacksWrote 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/ragnar-pwninskjold/tech-snacks/prd-to-ux)<a href="https://agentmods.dev/skills/ragnar-pwninskjold/tech-snacks/prd-to-ux"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/prd-to-ux/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/ragnar-pwninskjold/tech-snacks/prd-to-ux"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/prd-to-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01277 |
| Opus 5 | $0.00028 | $0.00639 |
| Sonnet 5 | $0.00011 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
prd-to-ux 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-to-ux
Take a PRD (or a raw product idea) and produce tool-agnostic, concept-driven screen prompts for web UX generators — Stitch, Figma AI, Pencil, Claude Design, and similar.
Output describes design intent: what a screen is for, what's visible, how it feels. It does NOT emit Tailwind, component trees, or hex codes (unless the user explicitly supplies them).
Pipeline
- Step 1 — PRD Shaping (optional) — when no PRD exists. See
references/step-1-prd-shaping.md. - Gate — PRD Validation — required pass between Step 1 and Step 1.5. See
references/prd-validation.md. - Step 1.5 — UX Philosophy (required) — 3 distinct philosophies, user picks. See
references/step-1-5-ux-philosophy.md. - Step 2 — Feature & State Briefs (required) — screens and states per feature. See
references/step-2-feature-states.md. - Step 3 — Design Direction (optional) — vibe brief, or shadcn-style default. See
references/step-3-design-direction.mdandreferences/default-design-direction.md. - Step 4 — Screen Prompts Export (required) — one prompt block per screen × state. See
references/step-4-screen-prompts.md.
The divergent→convergent pattern shared by Step 1 (features) and Step 1.5 (UX expressions) lives in references/divergent-convergent-pattern.md.
Artifacts
Written to the user's current working directory under:
docs/prd-to-ux/<YYYY-MM-DD>-<project-slug>/
├── 01-prd.md
├── 01b-ux-philosophy.md
├── 02-features-and-states.md
├── 03-design-direction.md (only if user opted in at Step 3)
└── 04-screen-prompts/
├── <feature-1>.md
└── ...
Project slug is lowercase kebab-case derived from the PRD title or elevator pitch. Skill proposes a slug and lets the user override.
Entry
User invokes /prd-to-ux or references the skill, optionally passing a PRD file path or pasted content.
Opening Move
- Introduce the pipeline stages briefly (Step 1 through Step 4, plus the validation gate).
- Ask: "Do you have a PRD, or should we build one from an idea?"
- Check the target directory
docs/prd-to-ux/<today>-<proposed-slug>/for existing artifacts.- Directory exists with artifacts: ask whether to resume at the next missing step or start fresh.
- Directory does not exist: propose the slug, confirm, then create it and proceed.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/default-design-direction.md 1.1 KB
- references/divergent-convergent-pattern.md 2.3 KB
- references/prd-validation.md 1.9 KB
- references/step-1-5-ux-philosophy.md 3.6 KB
- references/step-1-prd-shaping.md 3.8 KB
- references/step-2-feature-states.md 5.3 KB
- references/step-3-design-direction.md 1.8 KB
- references/step-4-screen-prompts.md 5.7 KB
- templates/design-direction.template.md 735 B
- templates/features-and-states.template.md 1.1 KB
- templates/prd.template.md 1008 B
- templates/screen-prompt.template.md 985 B
- templates/ux-philosophy.template.md 816 B
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.
- 12d ago First seen · 88 lines · 57 tokens per session scan A 0321cd396353
prd-to-ux is a skill published in the GitHub repository ragnar-pwninskjold/tech-snacks (132 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 1,277 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.