url-to-code

Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.

Repositório: XiaomiMiMo/MiMo-Code
Última atividade na origem: 18 de julho de 2026 às 03:01
Idioma detectado do SKILL.md: inglês
Estrelas: 12.781
Forks: 1.309

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/XiaomiMiMo/MiMo-Code --skill url-to-code

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Explorador de arquivos

2 arquivos

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

mimocode-docs

Use whenever the user asks about MiMoCode itself: features, TUI or CLI commands, keybindings, terminal compatibility, rendering glitches, TUI lag, SSH or remote rendering, agent modes (build / plan / compose) and how to switch between them, configuration, file locations, providers, models, authentication, or custom OpenAI-compatible or Anthropic-compatible API endpoints. Especially trigger when a prompt supplies or asks to configure a base URL/baseURL, API key/apiKey, model name or ID, provider, Anthropic Messages API, or global/project mimocode.json/jsonc, or when the user asks how to enter or leave plan mode. Also trigger when a skill, task, subprocess, or external client needs to borrow this instance's models — the OpenAI-compatible /v1 chat, audio/speech, and audio/transcriptions endpoints every MiMoCode server serves, `mimo llm-server` task tokens, or how to expose a listening port for them. Use this skill to inspect existing config safely, make minimal changes, and verify them without guessing schema fi

2026-08-18

llm-endpoint-demo

Demo and end-to-end fixture for MiMoCode's temporary local LLM server. Use when verifying that a skill can borrow a configured chat or text-to-speech model through a local base_url and a throwaway token instead of a real provider API key, or when testing the expire-and-reissue loop. Not a general-purpose skill.

2026-08-18

compose-next

Use for multi-step feature work, bug fixes, or refactors where requirements need to settle, a feature document should carry design + tasks + delivery evidence, and the change deserves independent review before merge. Use it only when the user explicitly requests this workflow, whether with `/compose-next`, by name, or in any other clear natural language; do not infer the request from task complexity alone. Not for one-shot edits, single-file tweaks, or answering questions — those need no orchestration overhead.

2026-08-12

Ver todas deste repositório

URL to Code

Use this workflow only when the user asks to clone or faithfully recreate a live site they own or have permission to reproduce. For redesign, improvement, or a loosely inspired result, route through ../index/SKILL.md to context and ideation instead.

Read ../index/SKILL.md, ../../references/critical-overrides.md, and relevant saved context before building.

Workflow

Remind the user that they must have permission and follow the target site's terms.

Open the source with the browser selected by the index. Stop if it resolves to a wrong page, login wall, error, unrelated redirect, or other surface that cannot ground the requested clone.

Capture the full desktop page and a representative mobile viewport. Inspect small scroll increments so sticky, lazy-loaded, and animated content is not missed.

Inspect the DOM and visible behavior for text, links, controls, component states, images, icons, fonts, colors, spacing, dimensions, breakpoints, and interaction behavior.

Test important interactions one at a time and return to the starting state between tests. Preserve evidence for changed states.

Save permitted source assets locally. Do not hotlink them in the final result. When an asset cannot be obtained, use an available generation tool or an appropriate open replacement and disclose the substitution.

Inspect the target repository and use its existing framework and conventions. React is not required. If no app exists, create the smallest suitable frontend supported by the harness; plain HTML/CSS/JavaScript is acceptable.

Build only from captured evidence. Implement the visible desktop/mobile layouts and primary interactions without inventing unrelated design choices or backend behavior.

Run and inspect the local implementation with a real browser. Compare the same viewport and states against the source.

Run ../design-qa/SKILL.md, save design-qa.md, fix blocking and high-impact mismatches, and hand off only after final result: passed or a clearly documented verification blocker.

Hard rules

Capture source evidence before scaffolding or editing.

Do not infer hidden states when source evidence is available.

Do not use screenshots alone when DOM/style/interaction evidence can be inspected.

Do not leave placeholder assets or improvised icon glyphs in the final implementation.

Build success and server health are not visual verification.

Publish only when the user asks and the host exposes an authorized deployment tool.