Agent skill

Screen Wireframes

by pdcgomes in pdcgomes/redlamp

Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner.

MPL-2.0Auto-check passedFrontend & Design

Install Screen Wireframes

skills CLI
$ npx skills add pdcgomes/redlamp --skill screen-wireframes -a claude-code

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

GitHub CLI
$ gh skill install pdcgomes/redlamp screen-wireframes --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/pdcgomes/redlamp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/screen-wireframes .claude/skills/screen-wireframes && 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
screen-wireframes
GitHub stars
222
Token cost
~1.6k tokens
SKILL.md length
947 words
Files
2
Skills in repo
11
Repo updated
First seen
Licence
MPL-2.0

At a glance

Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner.

  • Works in 5 steps: Gather what it's drawn from: the design… → Copy template.tsx to the path above. → Replace the data at its top: WIREFRAMES… → …
  • Designing a screen
  • SKILL.md covers Where, Start, The tabs and Drawing a wireframe, plus 4 more sections
  • Calls git

What it does

Screen Wireframes is an agent skill from pdcgomes/redlamp. Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner. Every region is numbered and marked built, being built, planned or later, with notes keyed to the numbers and each question giving what's there now, the options and a lean. Use when designing a screen, a window or a set of panels before building them, when asked for wireframes or mockups, when showing what's built and what's…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Frontend & Design, covering UI design. The repository describes itself as: A native, open-source RAW photo editor for Mac, iPad and iPhone that feels immediately familiar to Lightroom users. The licence is MPL-2.0.

When your agent uses it

  • Designing a screen
  • A set of panels before building them
  • Asked for wireframes
  • Showing whats built and whats planned in a UI

Example prompts

  • “s built and what”
  • “Use the screen-wireframes skill to draw a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's…”
  • “/screen-wireframes”

Workflow steps

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

  1. Gather what it's drawn from: the design document, the tracker rows, the code as merged (git log), and the app it follows, if any…
  2. Copy template.tsx to the path above.
  3. Replace the data at its top: WIREFRAMES (title, a line saying what it's drawn from and the date, the reading note), the meanings in…
  4. Replace the example tab with one tab per area of the screen, listed in TABS between Overview and Questions.
  5. Link the canvas in your reply: Feature wireframes.

What it can do on your machine

Read from SKILL.md and the folder at commit bc52683. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Screen Wireframes loads about 1.6k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 947 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 pdcgomes/redlamp at commit bc52683, republished under its MPL-2.0 licence (© pdcgomes). 947 words, ~1,646 tokens.

Download SKILL.mdSave it as .claude/skills/screen-wireframes/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
screen-wireframes
description
Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner. Every region is numbered and marked built, being built, planned or later, with notes keyed to the numbers and each question giving what's there now, the options and a lean. Use when designing a screen, a window or a set of panels before building them, when asked for wireframes or mockups, when showing what's built and what's planned in a UI, or when collecting the owner's decisions on a UI.

Screen wireframes

A wireframes canvas shows how a complex screen looks and works before all of it exists: each region drawn where it sits, marked with where it stands, explained in a note, and the choices only the owner can make set out as questions. It is the design's picture, kept true to the code as the work lands. The library's (library-ui-wireframes.canvas.tsx in this project's canvases) is the example to follow.

Where

  • ~/.cursor/projects/<workspace>/canvases/<feature>-wireframes.canvas.tsx: <workspace> is the Cursor project folder for this repository (list ~/.cursor/projects/ if it isn't in the environment), <feature> a short kebab-case name (library-ui-wireframes, import-wireframes).
  • One canvas per feature or screen family. A workstream's board links to it, and its open questions also go on the board's Needs you (.cursor/skills/workstream-canvas/SKILL.md).
  • Read ~/.cursor/skills-cursor/canvas/SKILL.md once per session before the first write: its rules apply (theme tokens only, no empty states, no gradients, emojis or shadows).

Start

  1. Gather what it's drawn from: the design document, the tracker rows, the code as merged (git log), and the app it follows, if any (Lightroom Classic for the library). Note what each region's status rests on.
  2. Copy template.tsx to the path above.
  3. Replace the data at its top: WIREFRAMES (title, a line saying what it's drawn from and the date, the reading note), the meanings in STATUS, FLOW, PRINCIPLES and QUESTIONS. Keep the building blocks and the Overview and Questions tabs as they are.
  4. Replace the example tab with one tab per area of the screen, listed in TABS between Overview and Questions.
  5. Link the canvas in your reply: [Feature wireframes](/absolute/path/<feature>-wireframes.canvas.tsx).

The tabs

  • Overview: the user's path through the screen as three to six numbered steps, each with its status; what makes the design work, three to six points with a title and a sentence; how to read the wireframes, the statuses and what each means; and a callout to the questions while any are open.
  • One tab per area: a window, a panel set, a sheet, a flow (the library's are The window, Finding photos, Culling, Keywords and metadata, and Import, files and health). Each opens with a heading and a sentence, then the wireframe, then its notes, then what doesn't draw well: a table of keys, the tokens a field takes, the states a control goes through.
  • Questions: each choice the wireframes leave open, and below them the ones answered.

Drawing a wireframe

  • The real layout, in proportion. A Window with its toolbar, regions laid out on a CSS grid with the screen's real columns and widths ("170px minmax(0, 1fr) 230px"). Draw what the user sees, not the code's structure.
  • Every region a Box: a number (n), a short label and a status. The notes under the wireframe use the same numbers: what the region does and why, the tracker ID or decision it comes from (LIB-27, DEC-48), and its status. A wireframe with more than about ten regions splits into two.
  • Real content. Real labels, menu names, keys (Kbd), templates and values, and plausible counts, saying once in the reading note that counts are made up. No placeholder text, no "TBD" box: a region not yet designed isn't drawn, it's a question.
  • Dashed boxes for what shows on demand: a sheet, a popover, a panel opened from a menu.
  • The building blocks: Box, Window, ListSection (a sidebar's rows with counts), Tile (a cell of content), Field (a labelled value), Segmented, Chip, Kbd, Slider, Mini, Caption, Notes, StatusTag. Add a block the screen needs (a domain's cell, such as the library's photo with stars and flags) beside them, in the same style.
  • A playground where a behaviour is easier to feel than to read: the library's query bar narrows a made-up million photos as terms are clicked. Keep it self-contained (useState, data inline) and say it's illustrative.
Show full SKILL.md (317 more words)Show less

Statuses

Each region, step and note carries one of four, and each must be true when written:

  • Built: merged where it ships and tested; checked in git log and the tracker.
  • Being built: an agent is building it now.
  • Planned: in the tracker for this release; its engine may exist without its panel, and the note says so.
  • Later: after the release, or waiting on a measurement or the owner, the note saying which.

Never mark built what isn't merged, and say plainly what hasn't been tried in the app.

Questions

  • Only choices whose answer changes what's built next: a layout, a default, what a key does. Not taste, and not what the design already settles.
  • Each one: the question as the title; now, what's built or designed today; two or three options, shown as A, B and C; and lean, your recommendation and why, in a sentence.
  • When the owner answers: set the question's answer to what they chose, in a sentence, so it moves under Answered. Record the decision where it belongs (the design document, the tracker row's text, a DEC- row when it's a product decision, the board's decisions) and brief the agents building those parts. Redraw the regions it changes.

Keep it current

  • When work lands, in the same turn as the merge: the regions' and notes' statuses, any region that came out differently from its drawing, and the date in the intro.
  • A region added to the design gets its box and note; one dropped is taken out, its note saying where it went if it moved.
  • After each edit the tool result shows a Canvas TypeScript check line: fix errors until it reports none.

Style

Plain, complete sentences in the project's voice, calm and precise, with no superlatives. Status colours come from theme.category, and the accent goes on the region markers only. Neutral boxes, structural borders, the canvas skill's rules throughout.

© pdcgomes, MPL-2.0. 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 .cursor/skills/screen-wireframes of pdcgomes/redlamp.

  • SKILL.md
  • template.tsx

Open the folder on GitHubat commit bc52683

Compare with similar skills

Screen Wireframes 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.

Screen Wireframes compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Screen Wireframes this skillpdcgomes/redlamp222—~1.6kAutomated safety check: PassMPL-2.0
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
LobeHub Interactive Prototypelobehub/lobehub83k—~1.6kAutomated safety check: PassCustom licence
Make Interfaces Feel Bettersamuelclay/NewsBlur7.6k10 repos~1.5kAutomated safety check: PassMIT
UI UX Pro MaxZxBing0066/pixel-converter18113 repos~2.6kAutomated safety check: NotesBSD-2-Clause
Design Dnazanwei/design-dna1.9k1 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Make Interfaces Feel Better

    samuelclay/NewsBlur

    Design engineering principles for making interfaces feel polished.

    7.6k GitHub starsUsed in 10 repos~1.5k tokens
    Frontend & DesignAuto-check passed
  • UI UX Pro Max

    ZxBing0066/pixel-converter

    UI/UX design intelligence with searchable database. An agent skill from ZxBing0066/pixel-converter.

    181 GitHub starsUsed in 13 repos~2.6k tokens
    Frontend & DesignAuto-check: notes
  • Design Dna

    zanwei/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…

    1.9k GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed
  • Figma Design to Code

    warpdotdev/warp

    Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.

    65k GitHub starsUsed in 4 repos~2.9k tokens
    Frontend & DesignAuto-check passed

More from pdcgomes/redlamp

All 11 skills in this repo
  • Redlamp Bench

    pdcgomes/redlamp

    Redlamp Bench, the way an agent asks the owner to do a step in another app and gets the results back without anyone moving files.

    231 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Redlamp Manual

    pdcgomes/redlamp

    The Redlamp User Manual (docs/manual), a dense, book-style PDF for photographers, typeset from Markdown and a print style sheet by Chrome, with its ranges, defaults and shortcuts generated from the…

    231 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Redlamp Promo Studio

    pdcgomes/redlamp

    The promo studio, which makes Redlamp's short promotional videos for social feeds the way a small creative agency does - a brief, hooks and copy, a script on a music grid, visuals from the promo…

    231 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Redlamp Site

    pdcgomes/redlamp

    Map of redlamp.app, the Next.js website in web/: its stack and commands, its pages, the home page's sections with their anchors, components and content sources, the brand's Tailwind tokens and…

    231 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Redlamp Blog

    pdcgomes/redlamp

    The blog room, where every redlamp.app blog post is tracked from idea to announcement in a canvas the owner marks as they post.

    231 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Redlamp Press

    pdcgomes/redlamp

    The press room, where every outlet Redlamp is pitched to (newsletters, Mac and photography sites, developer and open-source communities, lists and directories) is tracked from finding it to its…

    231 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about Screen Wireframes

What does Screen Wireframes do?

Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner. Screen Wireframes is an agent skill from pdcgomes/redlamp. Draws a complex screen or feature's UI as an annotated wireframe canvas, with tabs for an overview of the user's flow, one per area of the screen, and the questions left for the owner.

When should I use Screen Wireframes?

Screen Wireframes fits situations like: designing a screen; A set of panels before building them; asked for wireframes; showing whats built and whats planned in a UI.

How do I install Screen Wireframes in Claude Code?

Run `npx skills add pdcgomes/redlamp --skill screen-wireframes -a claude-code`. Or copy the skill folder (.cursor/skills/screen-wireframes in pdcgomes/redlamp) into .claude/skills/screen-wireframes in your project. Claude Code loads it when a task matches its description.

How do I install Screen Wireframes in Codex?

Run `npx skills add pdcgomes/redlamp --skill screen-wireframes -a codex`. Or copy the skill folder (.cursor/skills/screen-wireframes in pdcgomes/redlamp) into .agents/skills/screen-wireframes in your project. Codex loads it when a task matches its description.

Can I use Screen Wireframes 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 pdcgomes/redlamp --skill screen-wireframes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/screen-wireframes, .gemini/skills/screen-wireframes, .github/skills/screen-wireframes and .opencode/skills/screen-wireframes in your project.

What does Screen Wireframes need to run?

Going by SKILL.md and its folder, Screen Wireframes needs the command-line tools its instructions call (git).

Does Screen Wireframes access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Screen Wireframes 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 Screen Wireframes use?

Screen Wireframes is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Screen Wireframes use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 Screen Wireframes?

Skills that share tags, products or a category with Screen Wireframes: UI Styling (Ohh-889/skyroc, 795 stars), LobeHub Interactive Prototype (lobehub/lobehub, 83k stars), Make Interfaces Feel Better (samuelclay/NewsBlur, 7.6k stars) and UI UX Pro Max (ZxBing0066/pixel-converter, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Screen Wireframes?

pdcgomes (a GitHub user) maintains it in pdcgomes/redlamp, which has 222 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

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