What is screen-specs?

A method for turning user flows and requirements into screen designs and build instructions. Each screen includes a visual mock and a matching specification for the developer.

Use it to design or document mobile or web screens, define the shared design system, map screens to flow steps and acceptance criteria, and provide implementation-ready details.

It connects the intended user journey to concrete screens and exposes requirements that cannot be represented clearly.

screen-specs — Skill for Claude Code by arozumenko/sdlc-skills

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/arozumenko/sdlc-skills

agentmods

npx agentmods add skills/arozumenko/sdlc-skills/screen-specs

Made for: Claude Code.

Or install sdlc-skills, the plugin that ships this one along with the rest of its 60 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/screen-specs/github.svg)](https://agentmods.dev/skills/arozumenko/sdlc-skills/screen-specs)

Your own site

<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/screen-specs"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/screen-specs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/screen-specs"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/screen-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,320 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00160	$0.02320
Opus 5.5	$0.00064	$0.00928
Sonnet 5.5	$0.00032	$0.00464
Haiku 4.5	$0.00016	$0.00232

Measured 1mo ago against content hash f3390991e4b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

screen-specs 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 1mo ago.

The scan reads SKILL.md. This mod also ships 18 executable files (scripts/build-screens.mjs, scripts/build-story.mjs, scripts/build-story.test.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

bundles/feature-development/skills/screen-specs/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screen specs

Turn a flow's nodes into screens that can actually be built. Each screen is documented twice from one source — a mock showing what it should look like, and the spec a developer implements from — so the picture and the contract cannot disagree.

The two rules

Every screen traces to a flow node and an acceptance criterion. No orphan screens. If a criterion cannot become a screen or a state, that is a finding about the criterion — record it in notes, don't invent a screen for it.
Real content only. A mock reading "Hotel Name / $XXX" teaches nobody anything. Use values that exist in the project's seed data.

Workflow

Settle the design system first, once, in design-system.json: colour roles (light and dark), the M3 type scale mapped to real platform text styles, shape, elevation, spacing, a component inventory covering every region type, and the standing platform calls — the conflicts decided app-wide so no screen re-litigates them. Choose the target (mobile or web), the style for web (material / neo-flat / minimal-neutral / fluent), and the device for mobile (iphone / iphone-max / android / iphone-se) here too.
Author one flow's specs as the pattern, then fan the rest out against it. Getting the system right on the hardest flow is what makes parallel work safe.
Build.
```
node scripts/build-screens.mjs \
  --system <design-system.json> --specs <dir> --out <dir> [--img ../assets/img/]
```
Every flow page carries a journey filmstrip above its screens — the flow's screens ordered by their node id (whole numbers ascending, then decimals under their parent; node-less screens sort last), each a small clickable card that jumps to its full section below. It renders in both layouts.

Add --layout story to build into a shared design-story site instead of a standalone set: pages land in <out>/screens/<slug>.html (one directory deeper — a relative --img base gets an extra ../ automatically) so they sit next to user-flow-maps' flows/ output. Under story, each screen's Flow node value links back to ../flows/<flowSlug>.html#node-<id>, and its Criteria chips link to ../coverage.html#ac-<id> — both resolve once the sibling builds (build-flowmaps.mjs --layout story and build-story.mjs) have run; until then they just 404, no build depends on the other running first.
Verify. See references/verifying.md. Check that no mock overflows its frame, no image is broken, and the page never scrolls sideways.
Tie flows and screens into one site. Once both builds have written into the same <out> with --layout story, run
```
node scripts/build-story.mjs --flows <flowspec dir|file> --screens <dir> --out <dir>
```
to generate <out>/index.html (the design-story hub) and <out>/coverage.html (the acceptance-criteria coverage matrix). See "Design-story site" below for the full recipe.

Read the full file on GitHub · 174 lines

Files

What ships with it

33 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.

Changes

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.

1mo ago First seen · 174 lines · 160 tokens per session scan A f3390991e4b6

Subscribe to this mod's changes

screen-specs is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 2,320 once invoked, about $0.0006 per session on Opus 5.5. 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.

Design and UX

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

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.

Yeachan-Heo/oh-my-codex · 52 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

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.

microsoft/hve-core · 47 tokens