Upgrade Notes
getknit/knit
Read the vendor's breaking changes, deprecations, migration notes and CVEs for every version between the one pinned now and the one being moved to, through the whatsnew MCP server's upgradenotes tool.
Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens.
Install Device Screenshots
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install parawanderer/OpenTagViewer device-screenshots --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/device-screenshots .claude/skills/device-screenshots && rm -rf skills-srcUse ~/.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/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .claude/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshotsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install parawanderer/OpenTagViewer device-screenshots --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/device-screenshots .agents/skills/device-screenshots && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .agents/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install parawanderer/OpenTagViewer device-screenshots --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/device-screenshots .cursor/skills/device-screenshots && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .cursor/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/parawanderer/OpenTagViewer.git --path .claude/skills/device-screenshots--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install parawanderer/OpenTagViewer device-screenshots --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/device-screenshots .gemini/skills/device-screenshots && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .gemini/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install parawanderer/OpenTagViewer device-screenshotsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/device-screenshots .github/skills/device-screenshots && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .github/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install parawanderer/OpenTagViewer device-screenshots --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parawanderer/OpenTagViewer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/device-screenshots .opencode/skills/device-screenshots && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "device-screenshots" agent skill from https://github.com/parawanderer/OpenTagViewer/tree/main/.claude/skills/device-screenshots into .opencode/skills/device-screenshots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "device-screenshots", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
device-screenshots- GitHub stars
- 420
- Token cost
- ~1.4k tokens
- SKILL.md length
- 656 words
- Files
- 3
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens.
- A change is visual - colours
- SKILL.md covers Never Read a raw screenshot, Screenshots that go somewhere…, Getting the screenshots and Two traps, both hit here already, plus 2 more sections
- Runs Python scripts from its folder; calls python
- A screenshot needs comparing before and after
What it does
Device Screenshots is an agent skill from parawanderer/OpenTagViewer. Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens. Use whenever a change is visual - colours, themes, drawables, layout - or when a screenshot needs comparing before and after, light and dark.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `blur.py` and `sheet.py`).
It sits in Security. It works with Gradle. The repository describes itself as: Track your AirTags, iDevices and other FindMy devices on Android. The licence is MIT.
When your agent uses it
- A change is visual - colours
- A screenshot needs comparing before and after
Example prompts
- “/device-screenshots”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 335b258. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
python
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
Device Screenshots loads about 1.4k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 656 words of instructions outside code blocks.
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 parawanderer/OpenTagViewer at commit 335b258, republished under its MIT licence (© parawanderer). 656 words, ~1,351 tokens.
Download SKILL.mdSave it as
.claude/skills/device-screenshots/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- device-screenshots
- description
- Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens. Use whenever a change is visual - colours, themes, drawables, layout - or when a screenshot needs comparing before and after, light and dark.
Looking at the app's UI
Two halves: getting a screenshot off the device, and reading it cheaply. The second is the part that is easy to get wrong.
Never Read a raw screenshot
A device screenshot is ~1080px wide and mostly whitespace. Reading one costs a lot of vision tokens for a picture whose informative part is a few hundred pixels, and reading a before/after pair separately doubles it for a comparison that wants to be side by side anyway.
Run them through the sheet tool first:
python .claude/skills/device-screenshots/sheet.py \
app/build/outputs/managed_device_android_test_additional_output/debug/testEmulator \
<scratchpad>/shotsThen Read the sheets it prints. One subject, all its variants, one image, a few hundred pixels wide.
Files are grouped on the part before the last hyphen; the part after is the variant label:
my_device_list_item-fixed.png -> subject my_device_list_item, variant "fixed"
my_device_list_item-wallpaper.png variant "wallpaper"| Flag | Default | For |
|---|---|---|
--width | 420 | target width per panel |
--max-height | 420 | cap, so a tall image cannot produce a 2000px sheet |
--dark | dark,wallpaper_dark,night | variants composited over black rather than white |
Needs Pillow (python -m pip install pillow).
Screenshots that go somewhere public
A capture destined for the wiki or an issue is a screenshot of a real build on a real device, and some of what is on it belongs to whoever took it. The AMap key dialog is the worked example: it prints the package name and signing fingerprint, because that is exactly what AMap's console asks you to paste — correct behaviour, and not something to publish.
py -3 .claude/skills/device-screenshots/blur.py shot.png --band 0.42 0.55--band takes fractions of the height, so it survives a change of device resolution; repeat it
for more than one strip. Blur rather than crop — a cropped dialog looks like it has fewer fields
than it does, and the next person wonders what was removed. It pixelates before blurring, so the
characters are gone rather than merely soft.
Worth a look before publishing any capture: a signed-in email address, a real street name from
the geocoder, a XXXX-XXXX-XXXX bundle passcode, coordinates. The capture classes fabricate all
of those on purpose; a hand-taken screenshot does not.
Getting the screenshots
SystemColorsLayoutTest is the working example. Inflate a layout — or load a drawable —
against a themed context, draw it to a Bitmap, and write it to the directory AGP passes as the
additionalTestOutputDir instrumentation argument. AGP copies that back to the host after the
run:
app/build/outputs/managed_device_android_test_additional_output/debug/testEmulator/Run it on the managed device, which provisions and tears down its own emulator:
JAVA_HOME='C:\Program Files\Android\Android Studio\jbr' ./gradlew :app:testEmulatorDebugAndroidTestNo activity is needed for most of this. Inflating the layout against a
ContextThemeWrapper(context, R.style.Theme_OpenTagViewer) on the main thread is enough, and it
avoids every problem that comes with launching one.
Show full SKILL.md (239 more words)Show less
Two traps, both hit here already
Transparency. Several layouts have no background of their own. Converting them straight to RGB renders every transparent pixel black, and the result looks like a catastrophic bug that is not there. The tool composites over a background; do the same anywhere else.
Images are not assertions. A screenshot proves what one configuration looked like once.
Whatever the change is, assert it as well — a resolved colour, a contrast ratio, a measured
height. SystemColorsLayoutTest requires the timeline tiles to clear WCAG 3:1 against their
background, which is what actually fails the build; the images are what explain why.
And be careful what the assertion is about. That same test renders drawables through a themed
context, so it kept passing while the history timeline was invisible in the app — the app was
loading them with a null theme. The test proved the drawable could render, not that the app asked
for it correctly. ThemedDrawableLoadingTest covers the call site instead.
Dark mode
Rendering the day theme only is the usual mistake — the app has a full values-night palette. A
themed context can be forced to night without changing the device:
Configuration night = new Configuration(context.getResources().getConfiguration());
night.uiMode = (night.uiMode & ~Configuration.UI_MODE_NIGHT_MASK)
| Configuration.UI_MODE_NIGHT_YES;
Context darkContext = context.createConfigurationContext(night);
// then wrap in ContextThemeWrapper(darkContext, R.style.Theme_OpenTagViewer)Name those outputs -dark so the sheet tool composites them over black.
Related
AGENTS.mdrule 2 — do not claim something works if you have not run it. A rendered sheet is evidence; "it should look right" is not.CONTRIBUTING.mdfor how the managed device is configured.
© parawanderer, MIT. 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 2 other files in .claude/skills/device-screenshots of parawanderer/OpenTagViewer.
- SKILL.md
- blur.py
- sheet.py
Open the folder on GitHubat commit 335b258
Compare with similar skills
Device 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Device Screenshots this skillparawanderer/OpenTagViewer | 420 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Upgrade Notesgetknit/knit | 132 | — | ~1.2k | Automated safety check: Pass | GPL-3.0 | |
| Security Vulnerabilities Patcheraxelixlabs/axelix | 148 | — | ~4.2k | Automated safety check: Pass | LGPL-3.0 | |
| Review Dependenciestobihagemann/turbo | 409 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Spring AImagnus919/agent-skills | 116 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Dependency Audit Assistantaiskillstore/marketplace | 430 | — | ~2.2k | Automated safety check: Notes | None |
Similar skills
Security Vulnerabilities Patcher
axelixlabs/axelix
Create batched Dependabot-style pull requests for GitHub security findings in axelixlabs/axelix, grouped by dependency surface such as master/front-end, master/build.gradle.kts, or starter Gradle…
Review Dependencies
tobihagemann/turbo
Detect package managers and CI action pins, then discover outdated or vulnerable dependencies.
Spring AI
magnus919/agent-skills
Diagnose and operate Spring AI projects with version-aware Maven or Gradle checks for ChatClient, advisors, retrieval, conversation memory, tool/MCP boundaries, streaming, configuration, and…
Dependency Audit Assistant
aiskillstore/marketplace
Reviews package dependencies for security vulnerabilities, outdated versions, and license compliance.
Gradle Build Performance
Moustachauve/WLED-Android
Debug and optimize Android/Gradle build performance. An agent skill from Moustachauve/WLED-Android.
More from parawanderer/OpenTagViewer
Add Strings
parawanderer/OpenTagViewer
Add or back-fill user-facing Android strings across all locales in OpenTagViewer.
Investigating Bug Reports
parawanderer/OpenTagViewer
Read a GitHub bug report completely - every comment and every image - before diagnosing or asking the reporter for more.
Watch Gradle Tests
parawanderer/OpenTagViewer
Watch a Gradle instrumented-test run to a verdict without hand-writing greps.
Watch PR
parawanderer/OpenTagViewer
Watch a pushed PR's checks with the Monitor tool, and act on the verdict.
Related
Works with
Categories
Questions about Device Screenshots
What does Device Screenshots do?
Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens. Device Screenshots is an agent skill from parawanderer/OpenTagViewer. Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens.
When should I use Device Screenshots?
Device Screenshots fits situations like: A change is visual - colours; A screenshot needs comparing before and after.
How do I install Device Screenshots in Claude Code?
Run `npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a claude-code`. Or copy the skill folder (.claude/skills/device-screenshots in parawanderer/OpenTagViewer) into .claude/skills/device-screenshots in your project. Claude Code loads it when a task matches its description.
How do I install Device Screenshots in Codex?
Run `npx skills add parawanderer/OpenTagViewer --skill device-screenshots -a codex`. Or copy the skill folder (.claude/skills/device-screenshots in parawanderer/OpenTagViewer) into .agents/skills/device-screenshots in your project. Codex loads it when a task matches its description.
Can I use Device 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 parawanderer/OpenTagViewer --skill device-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/device-screenshots, .gemini/skills/device-screenshots, .github/skills/device-screenshots and .opencode/skills/device-screenshots in your project.
What does Device Screenshots need to run?
Going by SKILL.md and its folder, Device Screenshots needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Device 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 Device 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 Device Screenshots use?
Device Screenshots is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Device Screenshots use?
About 1.4k tokens (SKILL.md is roughly 5.4k 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 Device Screenshots?
Skills that share tags, products or a category with Device Screenshots: Upgrade Notes (getknit/knit, 132 stars), Security Vulnerabilities Patcher (axelixlabs/axelix, 148 stars), Review Dependencies (tobihagemann/turbo, 409 stars) and Spring AI (magnus919/agent-skills, 116 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Device Screenshots?
parawanderer (a GitHub user) maintains it in parawanderer/OpenTagViewer, which has 420 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 19, 2026.
Source: parawanderer/OpenTagViewer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.