New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Use Vishot

by moeru-ai in moeru-ai/airi

Capture deterministic screenshots with Vishot and return a structured manifest of the generated images.

MITAuto-check passedMobile

Install Use Vishot

skills CLI
$ npx skills add moeru-ai/airi --skill use-vishot -a claude-code

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

GitHub CLI
$ gh skill install moeru-ai/airi use-vishot --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/moeru-ai/airi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/use-vishot .claude/skills/use-vishot && 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
use-vishot
GitHub stars
50k
Token cost
~867 tokens
SKILL.md length
413 words
Files
2
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

Capture deterministic screenshots with Vishot and return a structured manifest of the generated images.

  • Works in 10 steps: Identify every requested surface and… → Reuse product-owned Vishot scenarios,… → If the existing scenarios do not expose… → …
  • Visual comparison inputs
  • SKILL.md covers Workflow and Capture Contract
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Use Vishot is an agent skill from moeru-ai/airi. Capture deterministic screenshots with Vishot and return a structured manifest of the generated images. Use for UI inspection, documentation, visual comparison inputs, or any screenshot task across Electron, web, and Capacitor applications; this skill is not specific to pull requests.

Its SKILL.md is about 870 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 Mobile, covering Cross-platform mobile apps and Pull requests. The repository describes itself as: 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of… The licence is MIT.

When your agent uses it

  • Visual comparison inputs
  • Any screenshot task across Electron
  • Capacitor applications
  • This skill is not specific to pull requests

Example prompts

  • “/use-vishot”

Workflow steps

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

  1. Identify every requested surface and state: route or window, viewport, theme, locale, fixture data, and any interaction needed to reach it.
  2. Reuse product-owned Vishot scenarios, stories, routes, and stable selectors before creating temporary automation.
  3. If the existing scenarios do not expose a valid reusable helper for the requested state, write the smallest disposable scenario or helper…
  4. Select the runtime variant
  5. When developing or debugging the disposable automation, use a locally available $agent-browser to inspect web or Capacitor DOM and…
  6. Produce the final screenshot artifacts with Vishot whenever possible, even when agent-browser helped discover selectors or verify the…
  7. Give the variant an explicit output directory. Directory ownership belongs to the caller; Vishot only writes named capture artifacts into…
  8. Keep locale, theme, data, viewport, and readiness conditions deterministic when captures will be compared.
  9. Inspect every generated image. Reject blank, loading, error, permission, onboarding, or unstable frames unless that is the requested state.
  10. Return a manifest rather than relying on directory order

What it can do on your machine

Read from SKILL.md and the folder at commit 4a24300. 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.

    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

Use Vishot loads about 867 tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 413 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~867

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 moeru-ai/airi at commit 4a24300, republished under its MIT licence (© moeru-ai). 413 words, ~867 tokens.

Download SKILL.mdSave it as .claude/skills/use-vishot/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
use-vishot
description
Capture deterministic screenshots with Vishot and return a structured manifest of the generated images. Use for UI inspection, documentation, visual comparison inputs, or any screenshot task across Electron, web, and Capacitor applications; this skill is not specific to pull requests.

Use Vishot

Use Vishot as the common screenshot interface and delegate runtime-specific behavior to the matching variant skill.

Workflow

  1. Identify every requested surface and state: route or window, viewport, theme, locale, fixture data, and any interaction needed to reach it.
  2. Reuse product-owned Vishot scenarios, stories, routes, and stable selectors before creating temporary automation.
  3. If the existing scenarios do not expose a valid reusable helper for the requested state, write the smallest disposable scenario or helper needed to reach it. Keep this automation outside tracked scenario directories unless the user separately asks to productize it. Run the complete startup, state preparation, capture, and artifact-inspection flow; do not stop after documenting that a helper is missing.
  4. Select the runtime variant:
    • Invoke $use-vishot-with-electron for Electron windows.
    • Invoke $use-vishot-with-web for browser routes.
    • Invoke $use-vishot-with-capacitor for Capacitor WebView or native-shell evidence.
    • Also invoke $use-vishot-with-input-file when reaching the requested state requires a local file chooser or file input.
  5. When developing or debugging the disposable automation, use a locally available $agent-browser to inspect web or Capacitor DOM and interaction paths. For Electron window discovery and interaction, also invoke $agent-browser-electron. Use these skills as development and validation aids; do not make their availability a prerequisite for Vishot capture.
  6. Produce the final screenshot artifacts with Vishot whenever possible, even when agent-browser helped discover selectors or verify the interaction sequence. Treat a missing product helper as temporary automation work, not as proof that Vishot cannot capture the state; report a Vishot limitation only after reproducing a concrete runtime failure.
  7. Give the variant an explicit output directory. Directory ownership belongs to the caller; Vishot only writes named capture artifacts into that directory.
  8. Keep locale, theme, data, viewport, and readiness conditions deterministic when captures will be compared.
  9. Inspect every generated image. Reject blank, loading, error, permission, onboarding, or unstable frames unless that is the requested state.
  10. Return a manifest rather than relying on directory order:
Show full SKILL.md (90 more words)Show less
text
id: settings-connection
title: Settings / Connection
runtime: web
viewport: 1440x900
image: /absolute/output/settings-connection.png

Include the failure reason instead of an image path when capture cannot complete. Do not invent PR, revision, upload, or repository-storage policy; the invoking workflow owns those decisions.

Capture Contract

  • Use stable IDs and human-readable titles for all requested states.
  • Omit --name when the URL or Electron window produces a unique meaningful name. Use it when states would collide or need an explicit identifier.
  • Treat --settle-ms as a final rendering delay, not a substitute for a state-specific readiness condition.
  • Return absolute paths and the parameters needed to reproduce each capture.

© moeru-ai, 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 1 other file in .agents/skills/use-vishot of moeru-ai/airi.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 4a24300

Compare with similar skills

Use Vishot 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.

Use Vishot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Use Vishot this skillmoeru-ai/airi50k—~867Automated safety check: PassMIT
Flutter Calendar Carousel Workflowshyochan/flutter_calendar_carousel860—~757Automated safety check: PassMIT
Review Selfhyochan/flutter_calendar_carousel860—~999Automated safety check: PassMIT
Nitro Sound Workflowshyochan/react-native-nitro-sound961—~1.2kAutomated safety check: PassMIT
Frb Prepare PRfzyzcjy/flutter_rust_bridge5.4k—~998Automated safety check: PassMIT
Frb PR Reviewfzyzcjy/flutter_rust_bridge5.4k—~485Automated safety check: PassMIT

Similar skills

  • Flutter Calendar Carousel Workflows

    hyochan/flutter_calendar_carousel

    A skill your agent uses for fluttercalendarcarousel repository work that should follow its shared workflows for issue resolution, dependency and Flutter upgrades, full verification, commits, pushes…

    860 GitHub stars~757 tokensUpdated 19 days ago
    MobileAuto-check passed

  • Review Self

    hyochan/flutter_calendar_carousel

    Independently review and improve the current fluttercalendarcarousel implementation, working-tree changes, commit range, or pull request; fix actionable in-scope gaps; rerun relevant verification…

    860 GitHub stars~999 tokensUpdated 19 days ago
    MobileAuto-check passed

  • Nitro Sound Workflows

    hyochan/react-native-nitro-sound

    A skill your agent uses for react-native-nitro-sound repository work that should follow the project workflows for PR review, code audit, knowledge compilation, full verification, iOS or Android…

    961 GitHub stars~1.2k tokensUpdated 11 days ago
    MobileAuto-check passed

  • Frb Prepare PR

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses when about to create a PR or push changes in flutterrustbridge to ensure code generation is up to date

    5.4k GitHub stars~998 tokensUpdated yesterday
    MobileAuto-check passed

  • Frb PR Review

    fzyzcjy/flutter_rust_bridge

    Review a flutterrustbridge PR before treating it as ready, including subagent checks for correctness and test weakening.

    5.4k GitHub stars~485 tokensUpdated yesterday
    MobileAuto-check passed

  • Review PR

    hyochan/flutter_calendar_carousel

    Inspect and finish fluttercalendarcarousel pull requests by fixing valid review findings, replying and resolving threads, diagnosing CI, using review-self when automation is unavailable, and polling…

    860 GitHub stars~1.4k tokensUpdated 19 days ago
    DevelopmentAuto-check passed

More from moeru-ai/airi

All 24 skills in this repo

  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    Auto-check passed

  • Enforce Rules For I18n

    moeru-ai/airi

    Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Upload GitHub Attachment

    moeru-ai/airi

    Upload a local image or file to GitHub's user-attachments storage and return a URL suitable for issue, pull request, discussion, or comment Markdown.

    50k GitHub stars~554 tokensUpdated yesterday
    Auto-check passed

  • Create PR

    moeru-ai/airi

    Prepare and create an AIRI pull request with verifiable change context, architecture evidence, and required visual evidence.

    50k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Use Agent Browser For Airi

    moeru-ai/airi

    Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts.

    50k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Agent Browser Electron

    moeru-ai/airi

    A skill your agent uses when Codex needs to inspect, debug, or automate an Electron app through agent-browser and Chrome DevTools Protocol, especially when the app has multiple BrowserWindow…

    50k GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Use Vishot

What does Use Vishot do?

Capture deterministic screenshots with Vishot and return a structured manifest of the generated images. Use Vishot is an agent skill from moeru-ai/airi. Capture deterministic screenshots with Vishot and return a structured manifest of the generated images.

When should I use Use Vishot?

Use Vishot fits situations like: visual comparison inputs; any screenshot task across Electron; capacitor applications; this skill is not specific to pull requests.

How do I install Use Vishot in Claude Code?

Run `npx skills add moeru-ai/airi --skill use-vishot -a claude-code`. Or copy the skill folder (.agents/skills/use-vishot in moeru-ai/airi) into .claude/skills/use-vishot in your project. Claude Code loads it when a task matches its description.

How do I install Use Vishot in Codex?

Run `npx skills add moeru-ai/airi --skill use-vishot -a codex`. Or copy the skill folder (.agents/skills/use-vishot in moeru-ai/airi) into .agents/skills/use-vishot in your project. Codex loads it when a task matches its description.

Can I use Use Vishot 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 moeru-ai/airi --skill use-vishot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/use-vishot, .gemini/skills/use-vishot, .github/skills/use-vishot and .opencode/skills/use-vishot in your project.

What does Use Vishot need to run?

SKILL.md names no scripts, command-line tools or credentials: Use Vishot is instructions for the agent only.

Does Use Vishot 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 Use Vishot 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 Use Vishot use?

Use Vishot 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 Use Vishot use?

About 867 tokens (SKILL.md is roughly 3.5k 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 Use Vishot?

Skills that share tags, products or a category with Use Vishot: Flutter Calendar Carousel Workflows (hyochan/flutter_calendar_carousel, 860 stars), Review Self (hyochan/flutter_calendar_carousel, 860 stars), Nitro Sound Workflows (hyochan/react-native-nitro-sound, 961 stars) and Frb Prepare PR (fzyzcjy/flutter_rust_bridge, 5.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Use Vishot?

moeru-ai (a GitHub organization) maintains it in moeru-ai/airi, which has 50,234 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 10, 2026.

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