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…
Skill by LazywebHQ
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lazywebhq-lazyweb-propose-ui-changes
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lazyweb-propose-ui-changes
What's inside
- Skill name
lazyweb-propose-ui-changes- Description
- 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".
- License
- MIT
- Instructions
- 109 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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 `id`s). 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 `id`s, `note`s, and real `data` payloads — never invented
structure. Proposals **target these ids**.
2. **Author the annotations.** One per suggestion, each `target`ing 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.From LazywebHQ/lazyweb-skill, MIT.
More from LazywebHQ/lazyweb-skill
- 0.795score
lazyweb
LazywebHQ
Use Lazyweb to find real product evidence, improve conversion, and turn research into clear product decisions.
SkillAFreshness: A★ 461Claude Code +9 - 0.755score
lazyweb-apply-design-best-practices
LazywebHQ
Apply the best available expert design guidance to the user's actual UI task.
SkillBFreshness: B★ 461Claude Code +9 - 0.755score
lazyweb-explain-flow
LazywebHQ
EXPLAIN how something works with a hosted, tappable flow diagram — a walkthrough, a failure trace, an answer to "how does X work?", a hypothetical.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-flows
LazywebHQ
Study complete product flows for onboarding, checkout, paywalls, signup, and other multi-step journeys.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-experiments
LazywebHQ
Find real product experiments for pricing, trials, paywalls, monetization, and conversion decisions.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-screens
LazywebHQ
Find real product screens and UI patterns to guide a design or conversion decision.
SkillBFreshness: B★ 461Claude Code +9 - 0.747score
lazyweb-growth-experiments
LazywebHQ
Deprecated name for /lazyweb-growth-experiments.
SkillBFreshness: B★ 461Claude Code +9 - 0.747score
lazyweb-design
LazywebHQ
Deprecated name for /lazyweb-design.
SkillBFreshness: B★ 461Claude Code +9 - 0.747score
lazyweb-quick-search
LazywebHQ
Deprecated name for /lazyweb-quick-search.
SkillBFreshness: B★ 461Claude Code +9 - 0.745score
lazyweb-design-create
LazywebHQ
INTERNAL create / greenfield backend.
SkillBFreshness: B★ 461Claude Code +9 - 0.743score
lazyweb-growth-score
LazywebHQ
Score a website's growth readiness, create a new score, or compare progress over time.
SkillBFreshness: B★ 461Claude Code +9 - 0.743score
lazyweb-growth-report
LazywebHQ
Get an evidence-backed Growth Report with prioritized ways to improve a product screen or webpage.
SkillBFreshness: B★ 461Claude Code +9
Signals
- Stars
- 461
- Forks
- 36
- Open issues
- 7
- Last commit (this folder)
- Aug 7, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/LazywebHQ/lazyweb-skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LazywebHQ
- 0.795score
lazyweb
LazywebHQ
Use Lazyweb to find real product evidence, improve conversion, and turn research into clear product decisions.
SkillAFreshness: A★ 461Claude Code +9 - 0.755score
lazyweb-explain-flow
LazywebHQ
EXPLAIN how something works with a hosted, tappable flow diagram — a walkthrough, a failure trace, an answer to "how does X work?", a hypothetical.
SkillBFreshness: B★ 461Claude Code +9 - 0.755score
lazyweb-apply-design-best-practices
LazywebHQ
Apply the best available expert design guidance to the user's actual UI task.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-flows
LazywebHQ
Study complete product flows for onboarding, checkout, paywalls, signup, and other multi-step journeys.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-experiments
LazywebHQ
Find real product experiments for pricing, trials, paywalls, monetization, and conversion decisions.
SkillBFreshness: B★ 461Claude Code +9 - 0.748score
lazyweb-search-screens
LazywebHQ
Find real product screens and UI patterns to guide a design or conversion decision.
SkillBFreshness: B★ 461Claude Code +9
Cite this page
lazyweb-propose-ui-changes skill. Agent Mart. https://agentmart.dev/skills/lazywebhq-lazyweb-propose-ui-changes (last updated 2026-10-24)