triage-visual-changes
Triage a UI Verify build from your coding agent via the UI Verify MCP — bucket a build's changed stories into real regressions vs cosmetic reflow vs rendering noise, summarize the real regressions for a PR comment, and accept baselines in bulk. Use after a UI Verify build reports changes and you want the agent to review, summarize, or accept from the terminal instead of clicking through the dashboard. Triggers - "triage this build", "summarize the visual regressions", "accept all the new baselines".
uiverify · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add uiverify/uiverify --skill triage-visual-changes技能说明
name: triage-visual-changes description: Triage a UI Verify build from your coding agent via the UI Verify MCP — bucket a build's changed stories into real regressions vs cosmetic reflow vs rendering noise, summarize the real regressions for a PR comment, and accept baselines in bulk. Use after a UI Verify build reports changes and you want the agent to review, summarize, or accept from the terminal instead of clicking through the dashboard. Triggers - "triage this build", "summarize the visual regressions", "accept all the new baselines".
Triage a UI Verify build from your agent
When a build comes back changed, the dashboard shows a triptych per story (baseline / candidate / diff). This skill does that review from your agent over the UI Verify MCP — read what changed, look at the pixels when a number is ambiguous, then summarize or accept.
Connect the MCP (once)
The server is a remote Streamable-HTTP MCP at https://uiverify.ai/api/mcp, authed with your project's
uv_proj_… API key as a Bearer token. Add it as a real MCP server in your agent — don't hand-roll
curl against the endpoint. Over raw curl the image tools come back as MCP image blocks a shell
can't render, so the pixels are useless to a script; a native client shows them to the model directly.
Claude Code:
claude mcp add --transport http uiverify https://uiverify.ai/api/mcp \
--header "Authorization: Bearer $UIVERIFY_API_KEY"
Cursor — add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"uiverify": {
"url": "https://uiverify.ai/api/mcp",
"headers": { "Authorization": "Bearer YOUR_uv_proj_KEY" }
}
}
}
Any other MCP client (Codex, Copilot, Gemini): point it at the same Streamable-HTTP URL with the
Authorization: Bearer header. If a client can only reach it over HTTP by hand, prefer the get_diff
tool (it returns downloadable image URLs) over render_diff_image (inline pixels) — see the tool
table below.
Tools it exposes:
| Tool | Does | Key args |
|---|---|---|
list_builds | Recent builds + gate status, to find the one to inspect | branch?, status?, limit? |
get_build | Lean triage of one build — the gate + counts {total, changed, failed, unchanged}, the AI tally, and the first page (25) of changed/failed stories (each with a diffResultId, diff %, and when AI review is on the judge's aiVerdict, aiConfidence, and for a regression aiFlagReason = its one-line "what looks unintended"), the page carrying a nextCursor. It does not dump the unchanged list — counts.unchanged is the signpost; page the rest with list_build_stories | one of commitSha / prNumber / buildId |
list_build_stories | Page through one build's stories by status — the only way to browse the full changed / failed / unchanged set beyond get_build's first page. counts.unchanged from get_build is the exact count it pages | selector, status: changed | unchanged | failed, cursor?, limit? (default 25, max 100) |
get_diff | Per-story diff metrics + presigned image URLs (baseline / candidate / diff) you can download to a file or link straight into a PR; when AI review is on, the judge's full call: aiVerdict, aiConfidence, aiSummary (what changed), aiReasoning (why), aiFlagReason. Pass storyId to pull one story even if it didn't change — you get its current baseline URL, so you can show "identical to baseline" on a passed build | same selector, optional storyId |
render_diff_image | The actual pixels of one image, inline for the vision model to look at (not a URL): baseline / candidate / diff, or before_after for a before-and-after crop zoomed to the changed region — one crop per region, stacked, when the story moved in several far-apart places (a header and a footer) | diffResultId (or storyId for a story that didn't change), which |
review_diff | Record a decision on one story | diffResultId, decision: accept | deny | ignore |
accept_build | Accept every changed story in a build at once | same selector |
Recipe 1 — "Triage this build"
Bucket the changes so the human sees signal, not 60 rows. Call get_build for the PR — it carries the
AI judge's call per story (aiVerdict, and for a regression the aiFlagReason) for the first page of
changes; if counts.changed is larger than that page, keep paging list_build_stories { status: "changed" } on the nextCursor until it runs out, so no regression slips past the page boundary. Read the judge before
you form your own view, and for anything that actually changed content, adjudicate it against the
before image, not in isolation:
- Render BOTH images, not just the diff.
render_diff_imagewhich: "baseline"andwhich: "candidate"and compare them. The green diff mask tells you where pixels moved, never whether the result is good — a code block that went dark-on-dark, text that lost contrast, a control that's now clipped all look like "some pixels changed" in the mask and only reveal themselves as regressions in the before/after. Judging the candidate alone is how "it has colours now → improvement" passes an illegible block. Pullget_difffor the judge'saiReasoning/aiFlagReasonon the ones it flagged.
Report in four buckets, with real story names and % deltas:
- Regression — a real change that's wrong — content changed and the after is broken or worse: illegible/low-contrast text, clipping, overlap, missing content, a control that stopped reading as itself. A regression the current PR caused is still a regression — "my diff explains it" says nothing about whether it's correct. Never accept these; they're the reason to triage.
- Intended change — content changed and the after is correct and matches the PR's stated intent (a deliberate restyle, new copy, a genuinely new story). These