MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
melta DS の契約から画面 1 枚(ページ / スクリーン)を生成し、checkhtml で自己検証して coverage と評価不可まで報告する。トリガー: 「画面を作って」「〜ページを生成」「画面生成」「ダッシュボードを作って」「設定画面を作って」「build screen」「generate a page」。AGENTS.md のタスクベース読み込みガイドで契約を引き当て、最大 3…
$ npx skills add tsubotax/melta-ui --skill build-screen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tsubotax/melta-ui build-screen --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/build-screen .claude/skills/build-screen && rm -rf skills-srcUse ~/.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/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .claude/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tsubotax/melta-ui/tree/main/skills/build-screenType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tsubotax/melta-ui --skill build-screen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tsubotax/melta-ui build-screen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/build-screen .agents/skills/build-screen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .agents/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tsubotax/melta-ui --skill build-screen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tsubotax/melta-ui build-screen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/build-screen .cursor/skills/build-screen && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .cursor/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tsubotax/melta-ui.git --path skills/build-screen--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tsubotax/melta-ui --skill build-screen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tsubotax/melta-ui build-screen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/build-screen .gemini/skills/build-screen && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .gemini/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tsubotax/melta-ui build-screenInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tsubotax/melta-ui --skill build-screen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/build-screen .github/skills/build-screen && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .github/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tsubotax/melta-ui --skill build-screen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tsubotax/melta-ui build-screen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsubotax/melta-ui.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/build-screen .opencode/skills/build-screen && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "build-screen" agent skill from https://github.com/tsubotax/melta-ui/tree/main/skills/build-screen into .opencode/skills/build-screen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-screen", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
build-screenmelta DS の契約から画面 1 枚(ページ / スクリーン)を生成し、checkhtml で自己検証して coverage と評価不可まで報告する。トリガー: 「画面を作って」「〜ページを生成」「画面生成」「ダッシュボードを作って」「設定画面を作って」「build screen」「generate a page」。AGENTS.md のタスクベース読み込みガイドで契約を引き当て、最大 3…
Build Screen is an agent skill from tsubotax/melta-ui. melta DS の契約から画面 1 枚(ページ / スクリーン)を生成し、checkhtml で自己検証して coverage と評価不可まで報告する。トリガー: 「画面を作って」「〜ページを生成」「画面生成」「ダッシュボードを作って」「設定画面を作って」「build screen」「generate a page」。AGENTS.md のタスクベース読み込みガイドで契約を引き当て、最大 3 問だけ意図を確認してから生成する。ボタン 1 個・カード 1 枚のようなコンポーネント単体の生成には使わない(DESIGN.md のクイックモードで足りる)。既存 HTML のレビューにも使わない(design-review skill が担当)。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Frontend & Design, covering Design tokens, Design review and critique and Agent instruction files. It works with Tailwind CSS and Model Context Protocol. The repository describes itself as: 人間にも、AIにも、読めるデザインシステム — AI-Ready Design System for Claude Code & Cursor. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a44f290. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
npmghFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm and gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Build Screen loads about 1.3k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 414 words of instructions outside code blocks.
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.
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.
The full file from tsubotax/melta-ui at commit a44f290, republished under its MIT licence (© tsubotax). 414 words, ~1,322 tokens.
.claude/skills/build-screen/SKILL.md (or your agent's skills folder).melta の契約から画面 1 枚を生成し、生成物を自分で lint して、「何を自動検査したか / 何を検査していないか」まで含めて報告する。依頼から提出までの往復を 1 回に潰すための手順書。
参照の実体は MCP ツールと AGENTS.md / DESIGN.md / design/contracts/ に置く。この手順書に仕様を複製しない(複製した瞬間に drift する)。
AGENTS.md の「## タスクベース読み込みガイド」の表を読み、依頼を該当行に当てる。表をここに写さない(AGENTS.md が正)。複数の行に跨る依頼(例: 「サイドバー付きの設定画面」= サイドバー付きページ + 設定画面)は該当行の和集合を取るget_component(契約の exact value)と search(どの契約が該当するかの探索)を優先するdesign/contracts/components/*.contract.json を直接読むDESIGN.md。競合したら契約が勝つ(design/authority.md)引き当てが 1 つも無い依頼(DS に契約が存在しないコンポーネントを含む)は、生成前にその旨を伝える。契約の無い部品を勝手に発明しない。
下の質問バンクを上から見て、依頼文から答えが取れる問いは飛ばす。残ったものだけを 1 回でまとめて聞く。4 問以上聞かない。3 問を超える不確定さが残るなら、残りは仮置きして Step 5 の報告に「こう仮定した」と書く。
出力先が未指定なら提案する。examples/ は CI の Full Scan 対象なので、DS 公式サンプルにする意図が無い限り避ける。
拡張子は .html に揃える(Step 4 の CLI 経路が検査できるのは .html / .tsx / .jsx / .vue だけ。.htm などを渡すと検査自体が実行されない)。
ダークモードは聞かない。AGENTS.md の「テーマ・ダークモード」表の設定に従う。
Claude Code では AskUserQuestion で聞く。他のクライアントでは箇条書きで聞いて回答を待つ(推測で進めない)。
DESIGN.md の原則 + Step 1 で引き当てた契約の exact value で HTML を 1 枚書く。Tailwind class は契約の値を使う(近い値を目分量で選ばない)error でも detector が manual のルールは Step 4 で絶対に捕まらない(例: 実効タップ標的 44px の下限 [A11Y_MIN_TAP_TARGET_44])。生成時に守るのが唯一の機会なので、使うコンポーネントのカテゴリのルールを design/contracts/rules.json で先に見るcheck_html に生成物を渡す。passed / violations / coverage.automated / coverage.notAutomated が返るnpm run design:lint-generated -- <生成ファイルのパス>。error があれば exit 1。返るのは違反一覧と件数と PASSED / FAILED だけで、passed フィールドも coverage も返らないerror を全部直して再検査する。warn は残してよいが Step 5 に列挙する使った契約と読んだファイル — Step 1 で控えたもの。Step 2 で仮置きした前提があればここに書く
lint 結果 — 最終検査の結果を、使った経路が実際に返した形のまま書く。要約も補完もしない
passed の値と violationspassed という語は使わない)warn が残っていれば、どちらの経路でも全件列挙するcoverage
coverage.automated / coverage.notAutomated をそのまま転記する(要約しない)check_html が使える環境で再検査すると取れる)」と書く。件数を推測して埋めない評価不可 — この画面に関係するのに自動検査で判定できないルールを design/contracts/rules.json から ID で引いて列挙する。列は design-review の ## 評価不可 節と同じ 3 列。ただし reason の語彙は design-review(human-only / not-observable-static / ルール無し)とは違い、rules.json の automationStatus の値を使う
| aspect | reason | proposal |
|---|---|---|
サイドバーの現在ページ表示 [SPACE_NO_MISSING_ARIA_CURRENT] | impossible-static | 実際のルーティングと突き合わせる |
Drawer のフォーカストラップ [SPACE_NO_DRAWER_NO_FOCUS_TRAP] | human-only | 実機で Tab / Shift+Tab の循環を確認する |
human-only — 人が実機を操作しないと判定できないimpossible-static — 静的 HTML からは判定できない(属性は書けるが、その中身が正しいかは外部の情報が要る)llm-judge-candidate — 自動検査は無いが design-review skill が審査できるcovered-by-test — 既存テストがルールを担保しているが、この生成物の実動作は別に確認が要る未分類 — automationStatus の宣言が無いルール(rules.json に 44 件ある。例: [SPACE_NO_P0_CARDS])。分類が未了なだけで、検査されているかは別に確認するルール無し — 対応するルールが design/contracts/rules.json に無い。この行に ID は書かないautomationStatus の値 / 無ければ 未分類 / ルール自体が無ければ ルール無し)でどのルールにも reason を割り当てられる。空欄にしないautomationStatus が auto のルールは Step 4 が検査するので、この節には載せない最後に 1 行。3 分岐。どれにも共通して「ブランド未承認」を書く
context: fork にしない — 生成物と検証結果はメインコンテキストに残す必要がある。fork すると呼び出し元に要約しか戻らず、Step 5 の転記が伝聞になるgh api 等でのリモート取得)。インストール済みのファイルと MCP だけを読むdocs/ と hook の block 文言に置くcheck_html の passed を完成承認と言わない。lint-clean draft であってブランド適合の保証ではないDESIGN.md のクイックモードで足りる© tsubotax, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/build-screen of tsubotax/melta-ui.
Open the folder on GitHubat commit a44f290
Build Screen 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Build Screen this skilltsubotax/melta-ui | 201 | — | ~1.3k | Automated safety check: Pass | MIT | |
| MCP Developmentcoollabsio/coolify | 63k | 1 repos | ~949 | Automated safety check: Pass | MIT | |
| Figma Codegenawdr74100/figwright | 995 | — | ~4.2k | Automated safety check: Pass | MIT | |
| Persian Rtl UITronIsHere/vibefarsiui | 210 | — | ~1.7k | Automated safety check: Warn | None | |
| Design Reviewpproenca/dot-skills | 215 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Kaizen UINVIDIA/Personal-AI-Router | 1.6k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 |
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
awdr74100/figwright
Generate framework-aware code from a Figma design. An agent skill from awdr74100/figwright.
TronIsHere/vibefarsiui
Build right-to-left Persian (Farsi) UI in React and Tailwind the way an Iranian product team would: logical CSS only, Persian fonts without letter-spacing, Persian digits and «تومان», Jalali dates…
pproenca/dot-skills
Structured UI design review — existing code (React/JSX, CSS, Tailwind) and, when behaviour matters, the running app in a real browser — reported as a prioritised Before / After / Why table.
NVIDIA/Personal-AI-Router
Kaizen UI (KUI) component library and design-pattern advisor for NVIDIA applications.
warpdotdev/warp
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.
tsubotax/melta-ui
Register AI-generated-looking UI patterns as prohibited rules in the design system.
tsubotax/melta-ui
HTMLファイルをmelta UIデザインシステムに照らしてレビューし、違反を検出・分類・修正提案する。トリガー: 「デザインレビュー」「DSチェック」「禁止パターンチェック」「design review」「check compliance」「DS準拠確認」。対象ファイルのパスを引数で受け取る。
Works with
Categories
melta DS の契約から画面 1 枚(ページ / スクリーン)を生成し、checkhtml で自己検証して coverage と評価不可まで報告する。トリガー: 「画面を作って」「〜ページを生成」「画面生成」「ダッシュボードを作って」「設定画面を作って」「build screen」「generate a page」。AGENTS.md のタスクベース読み込みガイドで契約を引き当て、最大 3…. Build Screen is an agent skill from tsubotax/melta-ui.
Build Screen fits situations like: tasks that involve Design tokens; tasks that involve Design review and critique; tasks that involve Agent instruction files.
Run `npx skills add tsubotax/melta-ui --skill build-screen -a claude-code`. Or copy the skill folder (skills/build-screen in tsubotax/melta-ui) into .claude/skills/build-screen in your project. Claude Code loads it when a task matches its description.
Run `npx skills add tsubotax/melta-ui --skill build-screen -a codex`. Or copy the skill folder (skills/build-screen in tsubotax/melta-ui) into .agents/skills/build-screen in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tsubotax/melta-ui --skill build-screen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/build-screen, .gemini/skills/build-screen, .github/skills/build-screen and .opencode/skills/build-screen in your project.
Going by SKILL.md and its folder, Build Screen needs the command-line tools its instructions call (npm and gh).
SKILL.md contains no URLs. Its commands use npm and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Build Screen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Build Screen: MCP Development (coollabsio/coolify, 63k stars), Figma Codegen (awdr74100/figwright, 995 stars), Persian Rtl UI (TronIsHere/vibefarsiui, 210 stars) and Design Review (pproenca/dot-skills, 215 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
tsubotax (a GitHub user) maintains it in tsubotax/melta-ui, which has 201 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 27, 2026.
Source: tsubotax/melta-ui on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.