Lazyweb Propose Ui Changes logo

Lazyweb Propose Ui Changes

Organization
LazywebHQ
lazyweb-propose-ui-changes

Propose UI/flow changes (or explain context) on a STRUCTURED DIAGRAM that the user reviews and Accepts/Declines on a hosted lazyweb.com page, then apply the accepted ones. Use when the user wants a reviewable set of proposed changes to a product's UI, architecture, or flow — anything where you'd otherwise list suggestions in chat and want the user to approve/reject each before you act. Trigger on: "propose changes", "suggest UI changes for review", "let me review your suggestions", "annotate this flow/diagram", "create a proposal", "review and approve these changes", "explain this architecture/flow visually".

Overview

PublisherLazywebHQ
Repositorylazyweb-skill
Skill namelazyweb-propose-ui-changes
Stars
460
Forks
36
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by LazywebHQ on GitHub. Read the source before you install it.

Installation

Install the Lazyweb Propose Ui Changes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LazywebHQ/lazyweb-skill/tree/main/skills/lazyweb-propose-ui-changes
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LazywebHQ/lazyweb-skill.git /tmp/lazyweb-skill
mkdir -p .claude/skills
cp -r /tmp/lazyweb-skill/skills/lazyweb-propose-ui-changes .claude/skills/lazyweb-propose-ui-changes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lazyweb Propose Ui Changes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lazyweb Propose Ui Changes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lazyweb Propose Ui Changes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Lazyweb — Propose UI Changes

Propose changes against a structured diagram you build from the real code: you supply the current diagram, annotate its elements, and supply a proposed version; the user opens a lazyweb.com/proposal/<id>/ page, toggles Current ↔ Proposed to see before/after, and Accepts / Declines each suggestion; then you apply the accepted ones.

This skill drives these Lazyweb MCP tools:

  • lazyweb_health — verify MCP connectivity when the surface is uncertain.
  • lazyweb_propose_ui_changes — store a proposal (current + proposed + annotations), get a review URL.
  • lazyweb_get_proposal_decision — poll the user's accept/decline verdicts.

Prerequisite: the Lazyweb MCP must be connected and current. If lazyweb_propose_ui_changes isn't in the tool list, the skill pack/MCP is out of date — tell the user to update (curl -fsSL https://www.lazyweb.com/install.sh | sh) and restart their client.

MCP plan responses

Inspect every data-bearing tool result before applying its normal schema:

  • MCP_PRO_REQUIRED: relay the server message and returned intent-bound upgrade_url to the user, then stop. Do not retry another data tool or fall back to web/manual output.
  • FREE_REPORT_DAILY_LIMIT: relay the server message and returned intent-bound upgrade_url to the user, then stop. Do not retry another data tool or fall back to web/manual output.
  • Successful status: "locked_preview": relay display_to_user verbatim (or the returned MCP text if that is all the client exposes), including the preview and upgrade links. It is terminal: do not poll, retry another data tool, reconstruct output, or fall back.

When to use

  • The user wants to see and approve/reject a batch of changes before you make them.
  • You want to explain how a system/flow works by annotating a diagram they can click.
  • Changes span several places and a chat list would be hard to review.

When NOT to use

  • A single trivial edit you can just make — don't ceremony it into a proposal.
  • Pure design-from-screenshots work — use lazyweb_generate_report / the design skills.

The data you build

A proposal = diagram (the current state, nodes + edges each with a stable id, built from the REAL code) + proposed (a full copy of that diagram with your changes applied) + annotations (one per suggestion, targeting node/edge ids). The viewer shows Current from diagram and Proposed from proposed, and lists the annotations to Accept/Decline.

jsonc
{
  "diagram": { /* the CURRENT sectioned diagram: actors, sections, nodes, edges —
                  each element with a stable id, grounded in the real code. */ },
  "title": "Speed up repeat reports",
  "summary": "Three changes to cut latency.",
  "proposed": { /* the SAME sectioned diagram, edited: add/remove/modify nodes+edges.
                   Keep unchanged ids stable so Current↔Proposed line up. */ },
  "annotations": [
    { "target": "a_tkt",            // a node OR edge id IN THE DIAGRAM
      "kind": "change",             // change | add | remove | highlight | note
      "title": "Cache identical re-runs",
      "detail": "Return a cached result when the input hash is unchanged.",
      "before": "always rebuilds",  // optional
      "after": "instant on cache hit" },
    { "target": "a_poll", "kind": "add", "title": "Send progress, not just pending" }
  ]
}

kind sets the badge color/label: change (orange), add (green), remove (red), highlight (purple), note (blue). Defaults to note.

Steps

  1. Build the current diagram from the real code. Sections, actors, nodes and edges with stable ids, notes, and real data payloads — never invented structure. Proposals target these ids.

  2. Author the annotations. One per suggestion, each targeting a diagram node/edge id. Clear title + detail; add before/after for concrete changes; pick the right kind.

  3. Build proposed. Copy the diagram and apply the changes you're proposing — add/remove/modify nodes and edges — keeping unchanged ids stable so the Current↔Proposed toggle aligns. This is the "after" the user previews.

  4. Submit. lazyweb_propose_ui_changes({ diagram, title, summary, proposed, annotations }) → { proposal_id, proposal_url, ... }. On ok:false, surface error/detail; fix any unknownTargets (ids not in the diagram).

  5. Share the link. Give the user the proposal_url: they toggle Current ↔ Proposed and Accept/Decline each suggestion there. Don't paste the proposal back into chat — the page is the review surface.

  6. Get decisions. When they're done (or after a wait), poll lazyweb_get_proposal_decision(proposal_id) until status is completed (~20–30s between polls; don't hammer).

  7. Apply. Make the change for every accepted suggestion; skip declined. Confirm what you applied vs skipped.

Notes

  • The review page is unlisted (UUID-gated) — share the URL only with the reviewer.
  • Decisions are scoped to the submitting user.
  • Keep diagrams + proposals product-agnostic and target strictly by id; that's what makes this reproducible across products.

Frequently asked questions

What does the Lazyweb Propose Ui Changes AI skill do?

Propose UI/flow changes (or explain context) on a STRUCTURED DIAGRAM that the user reviews and Accepts/Declines on a hosted lazyweb.com page, then apply the accepted ones. Use when the user wants a reviewable set of proposed changes to a product's UI, architecture, or flow — anything where you'd otherwise list suggestions in chat and want the user to approve/reject each before you act. Trigger on: "propose changes", "suggest UI changes for review", "let me review your suggestions", "annotate this flow/diagram", "create a proposal", "review and approve these changes", "explain this architect...

Why use Lazyweb Propose Ui Changes on TypingMind?

Because you install it once and use it with any model. Lazyweb Propose Ui Changes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lazyweb Propose Ui Changes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LazywebHQ/lazyweb-skill/tree/main/skills/lazyweb-propose-ui-changes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Lazyweb Propose Ui Changes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lazyweb Propose Ui Changes?

As many as you like. As long as a model supports skills, you can use Lazyweb Propose Ui Changes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lazyweb Propose Ui Changes AI skill free?

Yes. It is published on GitHub by LazywebHQ under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇