Agent skill

Screens

by genkovich in genkovich/sdd

A skill your agent uses to produce the canonical screen manifest for a UI feature — every screen in every state (default / loading / empty / error / success / validation), with reuse-first component…

MITAuto-check passedFrontend & Design

Install Screens

skills CLI
$ npx skills add genkovich/sdd --skill screens -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install genkovich/sdd screens --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/genkovich/sdd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/screens .claude/skills/screens && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
screens
GitHub stars
171
Token cost
~2.1k tokens
SKILL.md length
891 words
Files
2
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses to produce the canonical screen manifest for a UI feature — every screen in every state (default / loading / empty / error / success / validation), with reuse-first component…

  • Works in 6 steps: Gate + read. test -f… → Derive states per screen. For each… → Draw per the canon's tool. figma → draw… → …
  • With reuse-first component picks — written to docs/features/{slug}/screens.md between api and tasks
  • SKILL.md covers Owner, Inputs, Protocol and Definition of Done, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Screens is an agent skill from genkovich/sdd. Use to produce the canonical screen manifest for a UI feature — every screen in every state (default / loading / empty / error / success / validation), with reuse-first component picks — written to docs/features/{slug}/screens.md between api and tasks. Draws per the design-system tool: Figma MCP into the canon file, Pencil MCP into screens.pen, or inline markdown wireframes (code mode — also the degradation when an MCP is unavailable). Triggers on "screens for {slug}", "screen states for {slug}", "draw the…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `templates/screens.md`).

It sits in Frontend & Design, covering UI design and Design systems. It works with Model Context Protocol and Figma. The repository describes itself as: Spec-Driven Development for Claude Code: 12 atomic Socratic skills + a TDD implement engine (agent-team & dynamic-workflow modes). The licence is MIT.

When your agent uses it

  • With reuse-first component picks — written to docs/features/{slug}/screens.md between api and tasks
  • Screens for {slug}
  • Screen states for {slug}
  • Draw the screens

Example prompts

  • “screens for {slug}”
  • “screen states for {slug}”
  • “draw the screens”
  • “/screens”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Gate + read. test -f docs/features//sad.md → missing = refuse with the pointer
  2. Derive states per screen. For each SCR-NN from the inventory, list the full state set
  3. Draw per the canon's tool. figma → draw into the canon's figma_file via the Figma MCP,
  4. Write the manifest + commit. Fill ./templates/screens.md →
  5. Structural self-check — per ../_shared/self-check.md: re-read
  6. Handoff. Emit the stage-handoff block per ../_shared/handoff.md

What it can do on your machine

Read from SKILL.md and the folder at commit 4403913. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Screens loads about 2.1k tokens when it runs. Until then it costs about 212 tokens; SKILL.md has 891 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~212
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from genkovich/sdd at commit 4403913, republished under its MIT licence (© genkovich). 891 words, ~2,066 tokens.

Download SKILL.mdSave it as .claude/skills/screens/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
screens
description
Use to produce the canonical screen manifest for a UI feature — every screen in every state (default / loading / empty / error / success / validation), with reuse-first component picks — written to docs/features/{slug}/screens.md between api and tasks. Draws per the design-system tool: Figma MCP into the canon file, Pencil MCP into screens.pen, or inline markdown wireframes (code mode — also the degradation when an MCP is unavailable). Triggers on "screens for {slug}", "screen states for {slug}", "draw the screens", "mockups for {slug}", "/sdd:screens {slug}", "екрани для {slug}", "стани екранів {slug}", "намалюй екрани". States derive from §5 ACs + sad.md §6 branches + contract error responses; tasks/implement/review read ONLY the manifest. Hard-refuse if sad.md is missing; skipped when target_surfaces declares no UI surface.
model
inherit
effort
high

Skill: screens

Turns the approved architecture into the screen manifest — the one artifact tasks, implement and review read for what every screen shows in every state. It runs between api and tasks: by then the states are derivable, not invented — default plus every state the spec §5 ACs, the sad.md §6 alt/else branches, and the contract error responses imply (loading / empty / error / success / validation). Per state it names the components to reuse from the docs/design-system.md inventory — a NEW: component only with a why-no-primitive-fits justification. The visuals are drawn per the canon's tool; whatever the tool, the manifest is the contract — downstream never reads the raw Figma/.pen file.

Optional by surface: its N/A condition (no UI surface in sad.md target_surfaces) lives in ../_shared/size-matrix.md and is evaluated by api's handoff (carried forward when api itself is N/A). Invoked directly, it always runs.

Question phrasing → ../_shared/ask-style.md. Manifest prose follows artifact_language — state tokens (default/loading/…), SCR ids, component names and source-refs stay English → ../_shared/artifact-language.md.

Owner

Designer + frontend lead. The PM confirms the states match the ACs; review later checks the built screens against this manifest.

Inputs

  • <slug> — feature slug.
  • Gate (hard-refuse if missing): docs/features/<slug>/sad.md — target_surfaces + the §6 branches feed the state derivation. Absent → STOP: «run design <slug> first».
  • (Expected) docs/features/<slug>/ux-flows.md — the SCR inventory this manifest details. Absent → soft: offer /sdd:ux-flows <slug> first, or derive the inventory from spec §4 + the SAD with a noted gap in the manifest — never a silent invention.
  • (Expected) docs/design-system.md — the tool + the component inventory. Absent → code mode
    • recommend /sdd:design-system in the handoff.
  • (Read) docs/features/<slug>/contracts/ (error responses → error states), spec.md §5 (ACs → states), .size/.route (depth + handoff resolution; defaults stated loudly when missing).

Protocol

  1. Gate + read. test -f docs/features/<slug>/sad.md → missing = refuse with the pointer above. Read target_surfaces (no UI surface declared → say so and STOP — this stage is for UI features; the upstream handoff normally skips it). Read ux-flows.md (or run the soft fallback above), docs/design-system.md (tool + inventory), sad.md §6, contracts/, spec §5. Read interview_depth (else medium; --depth= wins) — it governs the per-screen confirm volume.
  2. Derive states per screen. For each SCR-NN from the inventory, list the full state set: default + every state the ACs / §6 branches / contract errors imply; a state class that genuinely doesn't apply gets one explicit N/A: <reason> row. Pick the components per state — from the design-system inventory by name; a NEW: <name> only when no existing primitive fits, with the one-line why. Confirm per screen Socratically (medium/hard: one AskUserQuestion per screen — Accept / Fix / Save-as-OQ / Drop; easy: derive + ledger, ask only where the AC↔state mapping is genuinely ambiguous).
  3. Draw per the canon's tool. figma → draw into the canon's figma_file via the Figma MCP, record the node-id per state; pencil → batch_design into docs/features/<slug>/screens.pen, record node ids; code → inline markdown wireframes in the manifest. Degrade, don't block: the tool's MCP unavailable in this session → fall back to code mode and name the degradation in the manifest §Source + the handoff (→ ../_shared/tool-adapters.md).
  4. Write the manifest + commit. Fill ./templates/screens.md → docs/features/<slug>/screens.md (frontmatter tool copied from the canon; §Source; one ### SCR-NN section per screen; §New components). Stamp updated_at; propose commit screens: <slug> manifest.
  5. Structural self-check — per ../_shared/self-check.md: re-read the manifest from disk and verify 4 items: (1) every SCR-NN from ux-flows.md has a section (inventory fully covered — or the noted-gap fallback is stated); (2) every screen shows ≥ default + (error or empty) — or carries the explicit N/A: <reason> row; (3) every component name exists in the design-system inventory or sits in §New components with a justification; (4) for figma/pencil, every state row carries a source-ref (node-id) — for code, the wireframes are present. Fix + re-check ≤2 cycles; surface anything unresolved.
  6. Handoff. Emit the stage-handoff block per ../_shared/handoff.md — What I did (tool used or the degradation, «self-check: 4/4 pass») + Review (docs/features/<slug>/screens.md, + screens.pen / the Figma file when tool-drawn) + Run next: /clear, then /sdd:tasks <slug> (each ui task will cite these SCR ids + states).
Show full SKILL.md (251 more words)Show less

Definition of Done

  • docs/features/<slug>/screens.md exists: §Source per the canon's tool, one section per SCR with the derived state table, components reuse-first (NEW: only justified), §New components filled or explicitly «None».
  • States are derived — every error/empty state traces to an AC, a §6 branch, or a contract error response; nothing invented, nothing silently missing.
  • For figma/pencil: every state has its node source-ref; for code: the wireframes are inline.
  • The manifest is the only thing downstream needs — tasks/implement/review never open the raw design file.

Anti-patterns

  • Happy-path-only screens. A screen with just default hides exactly the states users hit — the error/empty derivation is the point of this stage.
  • Inventing states with no source. Every non-default state traces to an AC / branch / contract error; a state with no origin is scope creep in a costume.
  • Hand-rolling a component the inventory already has — the reuse rule this pipeline exists to enforce; NEW: requires the why-no-primitive-fits line.
  • Blocking on a missing MCP. code mode is always available — degrade with a named degradation, never refuse the stage over tooling.
  • Making downstream read the design file. Node-ids are source-refs for humans; the manifest carries everything tasks/implement/review consume.
  • Architecture decisions here. The surface set, SSR-vs-SPA, state management — all design's; screens details what was declared, it never re-decides.

References & template

© genkovich, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/screens of genkovich/sdd.

  • SKILL.md
  • templates/screens.md

Open the folder on GitHubat commit 4403913

Compare with similar skills

Screens next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Screens compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Screens this skillgenkovich/sdd171—~2.1kAutomated safety check: PassMIT
Refero Designreferodesign/refero_skill299—~5.3kAutomated safety check: PassMIT
Build Figmacursor/plugins11k—~961Automated safety check: PassNone
Igniteui Angular Generate From Image DesignIgniteUI/igniteui-angular599—~4.7kAutomated safety check: PassMIT
Edit Figma Designwarpdotdev/warp65k1 repos~2.4kAutomated safety check: PassAGPL-3.0
Igniteui Angular Figma To AppIgniteUI/igniteui-angular599—~6.4kAutomated safety check: PassMIT

Similar skills

  • Refero Design

    referodesign/refero_skill

    Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive…

    299 GitHub stars~5.3k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Build Figma

    cursor/plugins

    Official

    Guides an agent through turning a Figma node into production UI with the repo's own components, then checks the result visually before finishing.

    11k GitHub stars~961 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Implements Angular application views from design images using Ignite UI Angular components.

    599 GitHub stars~4.7k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Edit Figma Design

    warpdotdev/warp

    Creates or revises Figma designs from a written description using the Figma MCP authoring tools, in a new blank file or an existing one.

    65k GitHub starsUsed in 1 repo~2.4k tokens
    Frontend & DesignAuto-check passed
  • Igniteui Angular Figma To App

    IgniteUI/igniteui-angular

    Builds Angular views from Figma designs with Ignite UI for Angular, supporting Indigo.Design kits, third-party kits, and plain frames.

    599 GitHub stars~6.4k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed

More from genkovich/sdd

All 21 skills in this repo
  • Fix

    genkovich/sdd

    A skill your agent uses to fix a reported bug spec-first: reproduce it, trace the symptom to the owning feature's acceptance criteria, pin it with a failing (RED) test, apply the minimal GREEN fix…

    171 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Implement

    genkovich/sdd

    A skill your agent uses to implement a feature from its tasks.json with test-driven development — writes a failing test first, makes it pass, refactors, gates, and commits per task.

    171 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Interview

    genkovich/sdd

    Use BEFORE roadmap or specify to get the idea OUT OF YOUR HEAD and onto disk — a Socratic interview that surfaces hidden assumptions, names tradeoffs, exposes imprecisions and proposes fresh angles…

    171 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Classify Size

    genkovich/sdd

    A skill your agent uses to classify a feature into XS/S/M/L/XL and write docs/features/{slug}/.size plus the pipeline route docs/features/{slug}/.route (quick|standard|full) so later skills know how…

    171 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Decide Adr

    genkovich/sdd

    A skill your agent uses to record a post-hoc or asynchronous architecture decision as a MADR ADR when it was NOT captured during the synchronous design pass — a choice made in code, in a chat, on a…

    171 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Tasks

    genkovich/sdd

    A skill your agent uses to break a designed feature into atomic, ≤1-day tasks with a dependency graph, a per-task Definition of Done, and a machine-readable tasks.json that the implement engine…

    171 GitHub stars~4.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Screens

What does Screens do?

A skill your agent uses to produce the canonical screen manifest for a UI feature — every screen in every state (default / loading / empty / error / success / validation), with reuse-first component…. Screens is an agent skill from genkovich/sdd.md between api and tasks.

When should I use Screens?

Screens fits situations like: with reuse-first component picks — written to docs/features/{slug}/screens.md between api and tasks; screens for {slug}; screen states for {slug}; draw the screens.

How do I install Screens in Claude Code?

Run `npx skills add genkovich/sdd --skill screens -a claude-code`. Or copy the skill folder (skills/screens in genkovich/sdd) into .claude/skills/screens in your project. Claude Code loads it when a task matches its description.

How do I install Screens in Codex?

Run `npx skills add genkovich/sdd --skill screens -a codex`. Or copy the skill folder (skills/screens in genkovich/sdd) into .agents/skills/screens in your project. Codex loads it when a task matches its description.

Can I use Screens in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add genkovich/sdd --skill screens -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/screens, .gemini/skills/screens, .github/skills/screens and .opencode/skills/screens in your project.

What does Screens need to run?

SKILL.md names no scripts, command-line tools or credentials: Screens is instructions for the agent only.

Does Screens access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Screens safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Screens use?

Screens is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Screens use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Screens?

Skills that share tags, products or a category with Screens: Refero Design (referodesign/refero_skill, 299 stars), Build Figma (cursor/plugins, 11k stars), Igniteui Angular Generate From Image Design (IgniteUI/igniteui-angular, 599 stars) and Edit Figma Design (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Screens?

genkovich (a GitHub user) maintains it in genkovich/sdd, which has 171 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 5, 2026.

Source: genkovich/sdd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.