Agent skill

Use Vishot With Web

by moeru-ai in moeru-ai/airi

Capture deterministic web routes with Vishot. An agent skill from moeru-ai/airi.

MITAuto-check passedProductivity & Automation

Install Use Vishot With Web

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

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

GitHub CLI
$ gh skill install moeru-ai/airi use-vishot-with-web --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-with-web .claude/skills/use-vishot-with-web && 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-with-web
GitHub stars
50k
Token cost
~1.4k tokens
SKILL.md length
691 words
Files
2
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

Capture deterministic web routes with Vishot. An agent skill from moeru-ai/airi.

  • Works in 9 steps: Identify the route, state, viewport,… → Ensure Vishot's Playwright Chromium… → Start the application with its… → …
  • The selected Vishot target is a locally runnable browser application and Codex must capture routes
  • SKILL.md covers Workflow, Viewport Sizing, Scenario Readiness and Locators and Constraints
  • Calls pnpm

What it does

Use Vishot With Web is an agent skill from moeru-ai/airi. Capture deterministic web routes with Vishot. Use when the selected Vishot target is a locally runnable browser application and Codex must capture routes, responsive viewports, or interaction-driven UI states without requiring agent-browser.

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 `agents/openai.yaml`).

It sits in Productivity & Automation, covering Browser automation. It works with Playwright. 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

  • The selected Vishot target is a locally runnable browser application and Codex must capture routes
  • Responsive viewports
  • Interaction-driven UI states without requiring agent-browser

Example prompts

  • “/use-vishot-with-web”

Workflow steps

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

  1. Identify the route, state, viewport, theme, locale, and output directory supplied by the caller.
  2. Ensure Vishot's Playwright Chromium runtime exists. If Vishot reports a missing executable, run pnpm exec playwright install chromium once…
  3. Start the application with its repository-owned development or preview command.
  4. Wait until the development server reports that it is listening, then apply the scenario readiness conditions below. Use an explicit…
  5. Run the documented scene command when the app exposes Vishot capture roots and a ready signal.
  6. Otherwise capture the route directly
  7. Repeat for each requested route and viewport. Use --name only when URL-derived names collide or fail to describe the state.
  8. Inspect each image for loading screens, stale data, iframe refusal, missing fonts, permission prompts, and animation instability.
  9. Return its stable ID, title, viewport, and absolute path to $use-vishot or the caller.

What it can do on your machine

Read from SKILL.md and the folder at commit ec682e2. 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

    Shell commands in SKILL.md call:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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 With Web loads about 1.4k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 691 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 ec682e2, republished under its MIT licence (© moeru-ai). 691 words, ~1,435 tokens.

Download SKILL.mdSave it as .claude/skills/use-vishot-with-web/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
use-vishot-with-web
description
Capture deterministic web routes with Vishot. Use when the selected Vishot target is a locally runnable browser application and Codex must capture routes, responsive viewports, or interaction-driven UI states without requiring agent-browser.

Use Vishot with Web

Prefer product-owned Vishot capture roots when available. Otherwise capture a local URL directly.

Workflow

  1. Identify the route, state, viewport, theme, locale, and output directory supplied by the caller.

  2. Ensure Vishot's Playwright Chromium runtime exists. If Vishot reports a missing executable, run pnpm exec playwright install chromium once and retry.

  3. Start the application with its repository-owned development or preview command.

  4. Wait until the development server reports that it is listening, then apply the scenario readiness conditions below. Use an explicit --settle-ms 2500 for final rendering. Vishot intentionally has no default delay because it serves projects with different readiness contracts.

  5. Run the documented scene command when the app exposes Vishot capture roots and a ready signal.

  6. Otherwise capture the route directly:

    bash
    pnpm exec vishot render \
      --target browser \
      http://127.0.0.1:5173/settings \
      --width 1440 \
      --height 900 \
      --settle-ms 2500 \
      --output-dir /absolute/output/settings
  7. Repeat for each requested route and viewport. Use --name only when URL-derived names collide or fail to describe the state.

  8. Inspect each image for loading screens, stale data, iframe refusal, missing fonts, permission prompts, and animation instability.

  9. Return its stable ID, title, viewport, and absolute path to $use-vishot or the caller.

Viewport Sizing

Prefer Vishot's browser dimensions when the size is known before launch:

bash
pnpm exec vishot render \
  --target browser \
  http://127.0.0.1:5173/settings \
  --width 1440 \
  --height 900 \
  --output-dir /absolute/output/settings

Use Playwright's viewport API when a browser scenario must change responsive states during the same run:

ts
await page.setViewportSize({ width: 390, height: 844 })
await page.waitForFunction(size => (
  globalThis.innerWidth === size.width
  && globalThis.innerHeight === size.height
), { width: 390, height: 844 })
  • Web pages do not have an Electron BrowserWindow; page.setViewportSize() is therefore the correct way to change the browser viewport in scenario code.
  • Do not use DOM APIs such as window.resizeTo() to control Vishot output. Browser security and window-manager behavior can ignore them, and they do not define the Playwright capture viewport reliably.
  • Treat width and height as CSS pixels. The output image can contain more device pixels when the browser context uses a device scale factor above 1.

Scenario Readiness and Locators

  • Implement readiness for the specific route and UI state. A heading, button, or expected text from one page is not a reusable readiness condition for another page.

  • With UnoCSS on a development server, visible content can precede generated utility styles or their HMR update. Server readiness and a fixed delay do not prove style readiness.

  • After opening the target state, wait for representative computed styles from its loaded utilities and for document.fonts.ready. Then allow layout to settle before capture.

  • Choose style conditions that hold in both revisions, such as an unchanged dialog radius or field gap. Do not wait for the visual fix itself: that can prevent the before capture from completing.

  • Keep these conditions in the product scenario or disposable capture helper. Use a bounded timeout and report which condition failed. Do not modify production CSS to satisfy capture readiness.

  • If a capture has missing styles, reject it and repeat the affected before/after pair with the same corrected readiness conditions.

  • Wait in this order: let Vishot establish URL and reload stability, confirm the final route, wait for a state-specific visible locator, confirm transient overlays or loading indicators are gone, then let Vishot keep its final settle window for remaining bundling, refresh, animation, or rendering.

  • Use text only when it is visible, unique, stable for the selected locale, and intrinsic to the intended state. Do not wait on generic headings, placeholders, network-derived values, or text copied from another scenario.

  • Prefer semantic locators such as getByRole('button', { name }) and getByLabel(). For an icon-only control, locate the owning button by its icon and click the button, not the icon node:

    ts
    const settingsButton = page.locator('button').filter({
      has: page.locator('[i-solar\\:settings-minimalistic-outline]'),
    }).first()

    Escape : in attribute-based icon selectors. Inspect the rendered DOM and repository icon usage before choosing a selector; avoid coordinates, nth-child, and incidental layout classes.

  • Treat drawers, menus, accordions, onboarding, and responsive navigation as stateful UI. Check the desired content, aria-expanded, or data-state before clicking a toggle. Make ensureOpen()-style helpers idempotent: return when already open, otherwise click once and wait for the open-state postcondition.

  • If no stable accessible or product-owned selector exists, add one to the product scenario or UI instead of weakening the wait to a fixed timeout.

Show full SKILL.md (42 more words)Show less

Constraints

  • Keep the target app local. Do not use this workflow to capture an untrusted remote page.
  • Keep route state deterministic with fixtures or seeded local storage when necessary.
  • Use identical dimensions and device scale behavior for captures that will be compared.

© 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-with-web of moeru-ai/airi.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit ec682e2

Compare with similar skills

Use Vishot With Web 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 With Web compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Use Vishot With Web this skillmoeru-ai/airi50k—~1.4kAutomated safety check: PassMIT
Camoufox CLIBin-Huang/camoufox-cli3501 repos~4.5kAutomated safety check: PassMIT
Berth Browsersean-brydon/berthd293—~1.4kAutomated safety check: PassMIT
Browser AutomationbenjaminasterA/antigravity-awesome-skills3751 repos~524Automated safety check: PassMIT
C Browserdaxaur/openpaw173—~383Automated safety check: PassMIT
Lightpanda Browsershepherdjerred/monorepo112—~1.2kAutomated safety check: PassGPL-3.0

Similar skills

  • Camoufox CLI

    Bin-Huang/camoufox-cli

    Anti-detect browser automation CLI & Skills for AI agents. An agent skill from Bin-Huang/camoufox-cli.

    350 GitHub starsUsed in 1 repo~4.5k tokens
    Productivity & AutomationAuto-check passed
  • Berth Browser

    sean-brydon/berthd

    Use your worktree's own page in a headless browser on the box — open it, read a compact snapshot with @refs, click, fill, press keys, wait, take a screenshot to a file, read console errors, and set…

    293 GitHub stars~1.4k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Browser Automation

    benjaminasterA/antigravity-awesome-skills

    Browser automation powers web testing, scraping, and AI agent interactions.

    375 GitHub starsUsed in 1 repo~524 tokens
    Productivity & AutomationAuto-check passed
  • C Browser

    daxaur/openpaw

    Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli.

    173 GitHub stars~383 tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Lightpanda Browser

    shepherdjerred/monorepo

    Lightpanda headless browser CLI for fast web content extraction, searching, and fetching When browsing the web, fetching URLs, searching the web, extracting web page content, or needing rendered…

    112 GitHub stars~1.2k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Covers 原生 Playwright Browser Tool、Chromium 进程池、Session Context、页面与 ARIA snapshot/ref 权威、同源安全、诊断/截图和 Web Browser 面板投影。

    181 GitHub stars~2k tokensUpdated yesterday
    Productivity & AutomationAuto-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
  • Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • 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 today
    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 today
    Auto-check passed
  • 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 today
    Auto-check passed
  • 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 today
    Auto-check passed

Works with

Questions about Use Vishot With Web

What does Use Vishot With Web do?

Capture deterministic web routes with Vishot. An agent skill from moeru-ai/airi. Use Vishot With Web is an agent skill from moeru-ai/airi. Capture deterministic web routes with Vishot.

When should I use Use Vishot With Web?

Use Vishot With Web fits situations like: the selected Vishot target is a locally runnable browser application and Codex must capture routes; responsive viewports; interaction-driven UI states without requiring agent-browser.

How do I install Use Vishot With Web in Claude Code?

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

How do I install Use Vishot With Web in Codex?

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

Can I use Use Vishot With Web 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-with-web -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-with-web, .gemini/skills/use-vishot-with-web, .github/skills/use-vishot-with-web and .opencode/skills/use-vishot-with-web in your project.

What does Use Vishot With Web need to run?

Going by SKILL.md and its folder, Use Vishot With Web needs the command-line tools its instructions call (pnpm).

Does Use Vishot With Web 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 With Web 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 With Web use?

Use Vishot With Web 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 With Web use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 With Web?

Skills that share tags, products or a category with Use Vishot With Web: Camoufox CLI (Bin-Huang/camoufox-cli, 350 stars), Berth Browser (sean-brydon/berthd, 293 stars), Browser Automation (benjaminasterA/antigravity-awesome-skills, 375 stars) and C Browser (daxaur/openpaw, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Use Vishot With Web?

moeru-ai (a GitHub organization) maintains it in moeru-ai/airi, which has 50,267 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 11, 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.