Agent skill

Review Local UI Screenshots

by xiaocang in xiaocang/easydict_win32

Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory.

GPL-3.0Auto-check passedTesting & QA

Install Review Local UI Screenshots

skills CLI
$ npx skills add xiaocang/easydict_win32 --skill review-local-ui-screenshots -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xiaocang/easydict_win32 review-local-ui-screenshots --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xiaocang/easydict_win32.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/review-local-ui-screenshots .claude/skills/review-local-ui-screenshots && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-local-ui-screenshots
GitHub stars
104
Token cost
~1.1k tokens
SKILL.md length
446 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
GPL-3.0

At a glance

Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory.

  • Works in 4 steps: visual-diffs/ and *_diff.png: likely… → baseline-candidates/: new or changed… → Diagnostic failure snapshots: names… → …
  • Asked to inspect local UI test screenshots
  • SKILL.md covers Goal, Locate Artifacts, Review Priority and Filename Semantics, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review Local UI Screenshots is an agent skill from xiaocang/easydict_win32. Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory. Use when asked to inspect local UI test screenshots, validate whether screenshot contents match filenames, review visual-diffs, baseline-candidates, failure snapshots, or summarize visual regressions from local artifacts.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Testing & QA, covering Visual regression testing. The repository describes itself as: Easy to look up words or translate text. Windows port of tisfeng/Easydict. The licence is GPL-3.0.

When your agent uses it

  • Asked to inspect local UI test screenshots
  • Validate whether screenshot contents match filenames
  • Review visual-diffs
  • Baseline-candidates

Example prompts

  • “/review-local-ui-screenshots”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. visual-diffs/ and *_diff.png: likely visual regression failures. Compare against nearby actual/baseline/candidate screenshots when…
  2. baseline-candidates/: new or changed baseline candidates that need human approval.
  3. Diagnostic failure snapshots: names containing not_found, failed, failure, missing, error, or navigation_failed.
  4. Regular workflow screenshots.

What it can do on your machine

Read from SKILL.md and the folder at commit 2b4231d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are powershell).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Local UI Screenshots loads about 1.1k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xiaocang/easydict_win32 at commit 2b4231d, republished under its GPL-3.0 licence (© xiaocang). 446 words, ~1,065 tokens.

Download SKILL.mdSave it as .claude/skills/review-local-ui-screenshots/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review-local-ui-screenshots
description
Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory. Use when asked to inspect local UI test screenshots, validate whether screenshot contents match filenames, review visual-diffs, baseline-candidates, failure snapshots, or summarize visual regressions from local artifacts.

Review Local UI Screenshots

Goal

Review screenshots as visual evidence. Check whether the visible UI state matches the meaning implied by the file name and directory, then report actionable mismatches first.

Locate Artifacts

Use the user-provided directory if present. Otherwise check, in order:

powershell
artifacts/ui-screenshots
artifacts
screenshots

List images recursively and keep paths relative to the artifact root in the report. Prefer inspecting individual screenshots over only reading gallery/contact-sheet images.

powershell
Get-ChildItem -Recurse -File artifacts/ui-screenshots -Include *.png,*.jpg,*.jpeg |
  Sort-Object FullName

Review Priority

Inspect in this order:

  1. visual-diffs/ and *_diff.png: likely visual regression failures. Compare against nearby actual/baseline/candidate screenshots when available.
  2. baseline-candidates/: new or changed baseline candidates that need human approval.
  3. Diagnostic failure snapshots: names containing not_found, failed, failure, missing, error, or navigation_failed.
  4. Regular workflow screenshots.

Do not treat diagnostic names as passing states. A screenshot named overlay_not_found means the test captured a failure context; verify whether the screenshot explains that failure.

Filename Semantics

Infer expected state from path and filename:

  • before, initial: starting state, no translated result unless the scenario says otherwise.
  • after, result, translate, translated: result content should be visible and the app should still be usable.
  • light, dark, follow-system: palette should match the named theme; look for mixed light/dark controls.
  • settings_*: the named settings page, tab, expander, or scroll section should be visible.
  • ocr, overlay, capture: capture overlay or OCR state should be visible when named; after-cancel/dismiss screenshots should show recovery.
  • mini, fixed, main: the named window type should be the primary subject.
  • workflow_XX, step, streaming_XX: screenshots should form a plausible sequence with monotonic or expected UI progression.
  • fullscreen: expect desktop/app context; tolerate environmental noise but flag wrong app focus or missing target UI.
Show full SKILL.md (180 more words)Show less

Visual Checks

For each reviewed image, inspect pixels with the available image viewer. Flag:

  • blank, black, tiny, corrupted, or wrong-window screenshots
  • content that contradicts the filename or directory
  • clipped, offscreen, hidden, or overlapped target UI
  • wrong theme, mixed palette, unreadable contrast, or stale state
  • expected controls/results missing from a named state
  • unintended dialogs, taskbar popups, desktop clutter, or other apps covering the target
  • secrets or personal data visible in a screenshot intended for CI review

When there are many screenshots, triage with ui-screenshot-gallery.jpg or generate one with:

powershell
dotnet/scripts/ci/Publish-UiScreenshotSummary.ps1 `
  -ScreenshotRoot artifacts/ui-screenshots `
  -ArtifactName local-ui-screenshots `
  -Title "Local UI screenshot review" `
  -SummaryPath artifacts/ui-screenshots/local-review-summary.md

Then open individual priority images before making findings.

Report Format

Lead with findings. For each finding include:

  • severity: High, Medium, or Low
  • screenshot path
  • expected state inferred from the file name
  • observed state
  • why this is a mismatch
  • suggested next check or fix

After findings, add:

  • coverage: which artifact root and screenshot groups were reviewed
  • pass summary: notable groups that matched their names
  • skipped/not reviewed: any large groups intentionally sampled, with reason

If no issues are found, say that clearly and mention any residual risk such as sampled screenshots or missing baseline comparisons.

© xiaocang, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .codex/skills/review-local-ui-screenshots of xiaocang/easydict_win32.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 2b4231d

Compare with similar skills

Review Local UI Screenshots next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review Local UI Screenshots compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Local UI Screenshots this skillxiaocang/easydict_win32104—~1.1kAutomated safety check: PassGPL-3.0
Handsontable Visual Test Demoshandsontable/handsontable22k—~1.3kAutomated safety check: PassCustom licence
Kc Screenshotimran31415/kube-coder388—~870Automated safety check: NotesMIT
Visual QAliangdabiao/Godogen126—~1.4kAutomated safety check: PassMIT
Meticulous FixFlintSH/Flare135—~2.3kAutomated safety check: PassMIT
Visual QA For Web And Terminal UIscode-yeongyu/oh-my-openagent70k—~9.5kAutomated safety check: PassCustom licence

Similar skills

  • Handsontable Visual Test Demos

    handsontable/handsontable

    Explains how to add or change the demo pages that Handsontable's visual regression suite photographs, including per-feature routes in the js demo and the shared grid.

    22k GitHub stars~1.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Kc Screenshot

    imran31415/kube-coder

    Capture desktop + mobile, dark + light screenshots of the kube-coder dashboard SPA for visual QA of a UI change.

    388 GitHub stars~870 tokensUpdated 2 days ago
    Testing & QAAuto-check: notes
  • Visual QA

    liangdabiao/Godogen

    Visual quality assurance — analyze game screenshots for defects, compare against reference, check motion in frame sequences.

    126 GitHub stars~1.4k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Meticulous Fix

    FlintSH/Flare

    Fix the visual diffs that have been reviewed and rejected on a Meticulous test run, following their review comments if given.

    135 GitHub stars~2.3k tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Visual QA For Web And Terminal UIs

    code-yeongyu/oh-my-openagent

    Checks a built UI against a human-interface checklist and any reference image, pairing day and night screenshots at two screen widths.

    70k GitHub stars~9.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Argent Screenshot Diff

    bbplayer-app/BBPlayer

    Compare saved or live app screenshots with the argent screenshot-diff tool.

    1.2k GitHub stars~1.1k tokensUpdated 3 days ago
    Testing & QAAuto-check passed

More from xiaocang/easydict_win32

  • Review PR UI Screenshots

    xiaocang/easydict_win32

    Download and review Easydict pull request CI screenshot artifacts from GitHub Actions using gh, then verify whether each screenshot matches its filename and artifact directory.

    104 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Review Local UI Screenshots

What does Review Local UI Screenshots do?

Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory. Review Local UI Screenshots is an agent skill from xiaocang/easydict_win32. Review Easydict UI automation screenshot artifacts already present in local artifacts/ui-screenshots, screenshots, or a user-provided artifact directory.

When should I use Review Local UI Screenshots?

Review Local UI Screenshots fits situations like: asked to inspect local UI test screenshots; validate whether screenshot contents match filenames; review visual-diffs; baseline-candidates.

How do I install Review Local UI Screenshots in Claude Code?

Run `npx skills add xiaocang/easydict_win32 --skill review-local-ui-screenshots -a claude-code`. Or copy the skill folder (.codex/skills/review-local-ui-screenshots in xiaocang/easydict_win32) into .claude/skills/review-local-ui-screenshots in your project. Claude Code loads it when a task matches its description.

How do I install Review Local UI Screenshots in Codex?

Run `npx skills add xiaocang/easydict_win32 --skill review-local-ui-screenshots -a codex`. Or copy the skill folder (.codex/skills/review-local-ui-screenshots in xiaocang/easydict_win32) into .agents/skills/review-local-ui-screenshots in your project. Codex loads it when a task matches its description.

Can I use Review Local UI Screenshots in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xiaocang/easydict_win32 --skill review-local-ui-screenshots -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-local-ui-screenshots, .gemini/skills/review-local-ui-screenshots, .github/skills/review-local-ui-screenshots and .opencode/skills/review-local-ui-screenshots in your project.

What does Review Local UI Screenshots need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Local UI Screenshots is instructions for the agent only.

Does Review Local UI Screenshots access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Local UI Screenshots safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review Local UI Screenshots use?

Review Local UI Screenshots is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Local UI Screenshots use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Local UI Screenshots?

Skills that share tags, products or a category with Review Local UI Screenshots: Handsontable Visual Test Demos (handsontable/handsontable, 22k stars), Kc Screenshot (imran31415/kube-coder, 388 stars), Visual QA (liangdabiao/Godogen, 126 stars) and Meticulous Fix (FlintSH/Flare, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Local UI Screenshots?

xiaocang (a GitHub user) maintains it in xiaocang/easydict_win32, which has 104 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: xiaocang/easydict_win32 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.