check-visual-changes

Check the visual impact of an edit mid-task with `uiverify check` — render just the components you're touching on the UI Verify fleet and diff them against the real CI baseline, without opening a PR, posting a check, or moving a baseline. Works for every capture method (Storybook, Playwright, Vitest archives, and raw screenshots). Use when a coding agent has changed UI and wants a fast, authoritative "would this pass" answer before pushing — "check my visual changes", "did I break anything visually", "preview this diff", "run uiverify check". Hands off to triage-visual-changes for the pixel review.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The SKILL.md body is lean, executable, and well-structured: it gives concrete per-method commands, an explicit feedback loop with validation checkpoints, and appropriately offloads detail to a sibling skill. It matches the top anchor on all four content dimensions.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and explains only non-obvious domain specifics (fleet-vs-macOS rendering, scoped-vs-transitive affected sets, why `changed` exits 0); every section earns its tokens with no generic-concept padding.	5 / 5
Actionability	Provides copy-paste-ready `sh` commands per capture method with exact flags (`--target`, `--static-dir`, `--screenshots`), concrete story-id and glob examples, and the required `UIVERIFY_API_KEY` env var, covering the common cases.	5 / 5
Workflow Clarity	Sequences a clear edit→check→triage→accept→edit loop with per-method prepare-then-check ordering, plus validation checkpoints: a pre-upload secret/PII inspection and an exit-code contract that treats `changed` (exit 0) as expected review, not a gate.	5 / 5
Progressive Disclosure	A single-purpose, self-contained skill with no bundle files; it is organized into well-signaled sections and delegates pixel-review depth to a separate skill rather than inlining it, keeping navigation trivial and references one level deep.	5 / 5
	Total	20 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concise, and complete: it states concrete capabilities, enumerates all capture methods, gives natural trigger phrases, and cleanly distinguishes itself from adjacent skills. It matches the top anchor on every dimension with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — render scoped components, diff against the resolved CI baseline, and explicitly avoids PR/check/baseline movement — and enumerates all four capture methods (Storybook, Playwright, Vitest archives, raw screenshots), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers what it does (scoped render + diff vs CI baseline with no PR/check/baseline side effects) and when to use it via concrete "Use when a coding agent has changed UI..." trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say — "check my visual changes", "did I break anything visually", "preview this diff", "run uiverify check" — alongside the tool name and capture-method terms, covering synonyms and variants.	5 / 5
Distinctiveness Conflict Risk	Carves a clear mid-edit-preview niche distinct from CI `uiverify upload`, and explicitly hands the pixel review off to `triage-visual-changes`, minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: FranciscoMoretti/chat-js
Path: .agents/skills/check-visual-changes/SKILL.md
Commit: 4584f09

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.