Agent skill

Pixi Vn Testing

by DRincs-Productions in DRincs-Productions/pixi-vn

A skill your agent uses when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering…

LGPL-2.1Auto-check passedMedia & Creative

Install Pixi Vn Testing

skills CLI
$ npx skills add DRincs-Productions/pixi-vn --skill pixi-vn-testing -a claude-code

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

GitHub CLI
$ gh skill install DRincs-Productions/pixi-vn pixi-vn-testing --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/DRincs-Productions/pixi-vn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/testing .claude/skills/pixi-vn-testing && 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
pixi-vn-testing
GitHub stars
149
Token cost
~3.8k tokens
SKILL.md length
1,524 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
LGPL-2.1

At a glance

A skill your agent uses when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering…

  • Works in 5 steps: Why you can't just call… → Enabling it → Driving the game → …
  • An AI agent (or any external script) needs to play-test a running PixiVN game end-to-end in a real browser — starting the game
  • SKILL.md covers When to use this skill, 1. Why you can't just call…, 2. Enabling it and 3. Driving the game, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pixi Vn Testing is an agent skill from DRincs-Productions/pixi-vn. Use when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering input prompts, going back, and reading/writing storage — via Game.testing, the opt-in devtools bridge exposed on window. Load this before wiring up automated/agent-driven playtesting, not for authoring story content itself (see pixi-vn-narration).

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Text to speech and voice. It works with React and JavaScript. The repository describes itself as: Create visual novels with a modern 2D rendering engine and your favorite JavaScript framework.

When your agent uses it

  • An AI agent (or any external script) needs to play-test a running PixiVN game end-to-end in a real browser — starting the game
  • Advancing/branching the story
  • Answering input prompts
  • Reading/writing storage — via Game.testing

Example prompts

  • “/pixi-vn-testing”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Why you can't just call narration.continue({}) from the console
  2. Enabling it
  3. Driving the game
  4. Full state control
  5. Catching errors during an automated run

What it can do on your machine

Read from SKILL.md and the folder at commit 01c19cb. 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 javascript and typescript).

    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

Pixi Vn Testing loads about 3.8k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 1,524 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

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 DRincs-Productions/pixi-vn at commit 01c19cb, republished under its LGPL-2.1 licence (© DRincs-Productions). 1,524 words, ~3,776 tokens.

Download SKILL.mdSave it as .claude/skills/pixi-vn-testing/SKILL.md (or your agent's skills folder).
name
pixi-vn-testing
description
Use when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering input prompts, going back, and reading/writing storage — via `Game.testing`, the opt-in devtools bridge exposed on `window`. Load this before wiring up automated/agent-driven playtesting, not for authoring story content itself (see `pixi-vn-narration`).

Pixi'VN Testing module

When to use this skill

Use this skill when the task is to play the game from the outside — driving it like a player would, but from a script or an AI agent evaluating JavaScript in the page, instead of clicking UI. Typical asks this covers: "start the game and play through label X", "verify choice B leads to ending Y", "check that this bug repros after going back three steps", "seed storage with gold: 100 and confirm the shop unlocks", "run this game headless as a regression test".

This assumes the game's dev server (or a build served on a URL) and a browser are already running/reachable — starting either one is outside this skill; it only covers the game-control API itself. Do not use this skill for writing story content (pixi-vn-narration), save-file persistence (pixi-vn-saves), or the go-back UI/internals (pixi-vn-history) — those are the modules this skill drives, not what it teaches.

1. Why you can't just call narration.continue({}) from the console

narration.continue, .call, .jump, narration.choices.select, and stepHistory.back all take a props argument typed as StepLabelProps — the exact object a real game passes from its UI layer. Most real projects augment StepLabelProps (via TS module augmentation, see pixi-vn-getting-started) with app-specific fields: a router navigate, an i18n t, a toast, etc. (the official React template does exactly this — see pixi-vn-narration section 9). If a step calls props.navigate(...) or props.t(...), passing {} from a console/script call throws immediately.

Game.testing solves this once: the app pushes its real, live props to it (via setProps, see below) wherever it already builds them, and every action it exposes merges those in before delegating — so agent-driven calls behave exactly like a real player action, with no need to reconstruct or fake the app's props shape.

2. Enabling it

Game.testing is opt-in and disabled by default, and nothing about it depends on any particular bundler (Vite, Webpack, or none at all). Two independent pieces make it work:

  • Turning the window bridge on/off — Game.testing.enable(options?) / .disable().
  • Keeping it supplied with live props — Game.testing.setProps(props).
Turning it on/off

If the project uses @drincs/pixi-vn/vite's vitePluginPixivn, this is already handled: its testing option defaults to true, auto-enabling Game.testing for as long as vite dev keeps running (by injecting a small module into index.html) — never during vite build, regardless of the option. No app code needed for this part:

ts
// vite.config.ts — this is already the default, shown here just to make it explicit
vitePluginPixivn({ testing: true }); // or { testing: { windowKey: "myGameTesting" } }, or false to opt out

Pass testing: false if you don't want this — e.g. a dev server shared with other people that you don't want remote-controllable.

Without the Vite plugin (a different bundler, or no bundler-level integration at all), call it yourself, gated behind your own dev-only check:

ts
import { Game } from "@drincs/pixi-vn";

if (import.meta.env.DEV) {
  // or process.env.NODE_ENV !== "production", a Webpack DefinePlugin flag, etc.
  Game.testing.enable();
}
  • options.windowKey (default "pixiVN") — the property name the API is attached under on window.
  • Returns the same API object it attaches to window[windowKey], in case you want to keep a direct reference instead of going through window.
  • Calling enable again (e.g. on hot reload) replaces the previous session instead of stacking.
  • Game.testing.disable() tears it down (detaches from window, stops capturing errors).
  • Game.testing.isEnabled() reports whether a session is currently active.

Only enable this when you actually want the game remote-controllable. It hands out full control over game state (see §4) to anything that can run JavaScript in that page — treat it like any other devtools/debug backdoor.

Keeping it supplied with live props: setProps

Call Game.testing.setProps(props) unconditionally, wherever your app already builds its StepLabelProps — it's a cheap assignment, safe to call whether or not testing happens to be enabled right now, and every Game.testing action reads through whatever was passed here most recently:

ts
import { Game, type StepLabelProps } from "@drincs/pixi-vn";

function useGameProps(): StepLabelProps {
  // ... build props the same way your app always has ...
  const props = { navigate, t, toast /* ... */ };
  Game.testing.setProps(props); // [!code focus]
  return props;
}
React template convention

The official React template's useGameProps() (src/lib/hooks/props-hooks.ts — see pixi-vn-narration section 9) already ends with exactly that Game.testing.setProps(props) call, and vite.config.ts's vitePluginPixivn(...) call needs no extra option — testing defaults to true. Since useGameProps() already runs on every render of every component that needs game props, this is the only line the template needs: no dedicated bridge component, no manual enable() call.

Routing through the app's own narration functions: setActions

Most real apps don't call narration.continue/stepHistory.back/etc. straight from a "next" button — they wrap them in their own functions that also handle UI-only concerns a test session should trigger too: a loading indicator, refusing to advance while a menu/dialog is open, refreshing cached interface data after the step resolves, and so on. By default Game.testing's actions skip all of that and call narration/stepHistory directly, so an agent driving the game through window.pixiVN can get out of sync with what the real UI would have done (e.g. it never sees the loading state, or advances past a guard the real "next" button respects).

Game.testing.setActions(actions) fixes this: register the app's own functions once, and continue()/goBack()/selectChoice()/start()/jump()/call() call them instead. Any action left out keeps calling narration/stepHistory directly, so this is opt-in per action:

ts
import { Game } from "@drincs/pixi-vn";

Game.testing.setActions({
  continue: () => goNext(),
  back: () => goBack(),
  selectChoice: (item) => selectChoice(item),
  start: (label, props) => async () => {
    await props.navigate("/game");
    return await startNewGame(label, props);
  },
  jump: (label, props) => jump(label, props),
  call: (label, props) => call(label, props),
});

Mount that hook once near the app root (same idea as useGameProps() always calling setProps) and window.pixiVN.continue() now runs the exact same code path as a player clicking "next".

A few things follow from continue/back taking no arguments themselves:

  • The extraProps/options a caller passes to window.pixiVN.continue(...) / window.pixiVN.goBack(...) are ignored once an override is registered — the override manages its own props (typically via setProps) and usually has no notion of { steps, runNow }. Drive those through window.pixiVN.props/narration/stepHistory directly if you need that level of control.
  • selectChoice's override receives the already-resolved choice item (the same shape as getState().choices[i]), not the raw choiceIndex — the lookup (and the "no open choice with that index" error) still happens before the override runs.
  • setActions is safe to call whether or not testing is enabled yet, safe to call again to update the registered functions, and persists across disable()/enable() — same as setProps.
Show full SKILL.md (602 more words)Show less

3. Driving the game

Every action below reads through window.pixiVN (or your custom windowKey), evaluated in the page — e.g. via a browser automation tool's "evaluate script" capability, or by pasting into the devtools console by hand. If the Chrome DevTools MCP server is available, prefer it over any other browser automation for this: evaluate_script runs the snippets below directly in the page, navigate_page/ click/take_snapshot drive UI the game itself doesn't expose through window.pixiVN (e.g. a login screen), take_screenshot lets you actually look at the canvas instead of only trusting getState(), and list_console_messages surfaces errors/warnings a script-only check would miss — checking console output after every meaningful step, not just at the end, has caught real bugs (e.g. a framework deprecation warning) that a headless script relying only on errors/return values missed. Fall back to a Playwright/chromium-cli script, or another MCP browser tool, only when Chrome DevTools MCP isn't available. All of the actions below are async except setInput, closeCurrentLabel/ closeAllLabels, and getState.

js
// Start the game from a label (id or Label object). Clears all game data first, like a real "New Game".
await window.pixiVN.start("start");

// Advance one step (same guard a "next" button uses — see canContinue in getState() below).
await window.pixiVN.continue();

// Call a sub-label (returns to the caller when it runs out of steps) / jump to another label (no return).
await window.pixiVN.call("some_label");
await window.pixiVN.jump("some_label");

// Pick an open choice by its choiceIndex (see getState().choices below for what's available).
await window.pixiVN.selectChoice(0);

// Answer a pending input prompt, then continue like the player pressing confirm would.
window.pixiVN.setInput("Liam");
await window.pixiVN.continue();

// Go back one (or more) steps.
await window.pixiVN.goBack();
await window.pixiVN.goBack({}, { steps: 3 });

// Close the current label / close every open label (can end the game — see pixi-vn-narration).
window.pixiVN.closeCurrentLabel();
window.pixiVN.closeAllLabels();

Every action accepts an optional second extraProps argument (first argument for selectChoice's props is its second argument, continue/goBack's is first) that's shallow-merged on top of the live props for that one call — useful to override just one field (e.g. a fake navigate to observe where the game tried to go) without touching the app's real wiring:

js
await window.pixiVN.continue({
  navigate: (to) => console.log("would navigate to", to),
});
Reading state before deciding the next action

Don't act blindly — read getState() first to see what's actually on screen and what actions are valid right now:

js
window.pixiVN.getState();
// {
//   dialogue: { text: "What do you choose?", character: {...} } | undefined,
//   dialogueGlue: false,
//   choices: [{ text: "A", choiceIndex: 0, ... }, { text: "Close", choiceIndex: 1, ... }] | undefined,
//   input: { isRequired: false, type: undefined, value: undefined },
//   canContinue: true,
//   canGoBack: true,
//   labelsOpened: [...],       // narration.labels.opened
//   currentLabelId: "choice_label",
//   stepCounter: 12,
// }
  • If choices is set, call selectChoice(choiceIndex) — don't call continue(), it won't advance past an open choice menu.
  • If input.isRequired is true, call setInput(value) before the next continue().
  • If canContinue is false for any other reason, a step is mid-flight (e.g. an async transition) — wait and re-check rather than firing another action immediately.
Driving the app's UI directly, not just narration

window.pixiVN.props is the same live object setProps was last called with — whatever your app's StepLabelProps augmentation defines. Most projects put a navigate function there (see pixi-vn-getting-started and the wiki's "Navigate/switch between UI screens" page) so labels can switch screens; that same function is reachable here for full control over what's on screen, not just the story — e.g. opening a settings screen, jumping to a main menu, or checking where a bugged label tried to send the player, all without going through a choice/label:

js
window.pixiVN.props.navigate("/settings");

Anything else the app's StepLabelProps happens to expose (a toast, a t translator, ...) is reachable the same way. If your project doesn't augment StepLabelProps with a navigation function at all, this simply isn't available — driving screen navigation is then whatever mechanism the app itself uses outside of Pixi'VN (e.g. calling the router directly from the evaluated script).

4. Full state control

Beyond the guided actions above, the API also exposes the underlying singletons directly, for anything not covered by a dedicated method — most commonly storage, to set up a scenario without replaying the whole story to reach it, or to assert on state a dialogue doesn't surface:

js
// Arrange: seed state before starting/continuing.
window.pixiVN.storage.set("gold", 100);
window.pixiVN.storage.flags.set("met_liam", true);

// Assert: read state after driving the story forward.
window.pixiVN.storage.get("gold"); // 100

// Reset between test scenarios.
window.pixiVN.storage.clear(); // back to storage.default
window.pixiVN.Game.clear(); // wipes storage + narration + history + canvas + sound

// Snapshot / restore full game state instead of replaying steps to get back to a scenario.
const snapshot = window.pixiVN.Game.exportGameState();
// ... drive the game further, try something risky ...
await window.pixiVN.Game.restoreGameState(snapshot);

window.pixiVN.narration and window.pixiVN.stepHistory are the same narration/stepHistory singletons documented in pixi-vn-narration and pixi-vn-history — anything those skills document (narration.dialogue, narration.labels.current, stepHistory.narrativeHistory, ...) is reachable the same way here, read-only or not.

5. Catching errors during an automated run

An automated/agent-driven session can't "notice" a red error toast the way a human tester would. Game.testing.enable registers its own Game.addOnError handler for as long as it's active, so errors raised anywhere in the game (including inside steps) are captured instead of only surfacing in the UI:

js
window.pixiVN.errors;
// [{ error: Error("..."), timestamp: 1730000000000 }, ...]

window.pixiVN.clearErrors(); // e.g. between test cases, so failures don't bleed across scenarios

This is in addition to, not a replacement for, whatever Game.addOnError handlers the app itself registers (e.g. drawCanvasErrorHandler()) — both run.

pixi-vn-getting-started, pixi-vn-narration, pixi-vn-storage, pixi-vn-history, pixi-vn-saves

© DRincs-Productions, LGPL-2.1. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/testing of DRincs-Productions/pixi-vn.

Open the folder on GitHubat commit 01c19cb

Compare with similar skills

Pixi Vn Testing 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.

Pixi Vn Testing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pixi Vn Testing this skillDRincs-Productions/pixi-vn149—~3.8kAutomated safety check: PassLGPL-2.1
Dotlottie WebLottieFiles/dotlottie-web892—~3.5kAutomated safety check: PassMIT
Anything2explainerVincentwei1021/anything2explainer2.4k—~2.7kAutomated safety check: PassCustom licence
Speech To Texttadaspetra/loop2962 repos~2kAutomated safety check: PassMIT
Edit Timeline StudioMartinDelophy/ai-video-editor905—~7kAutomated safety check: PassMIT
Explainroovincentsch/explainroo515—~439Automated safety check: PassMIT

Similar skills

  • Dotlottie Web

    LottieFiles/dotlottie-web

    Implement Lottie animations using dotLottie runtimes (@lottiefiles/dotlottie-web and @lottiefiles/dotlottie-react).

    892 GitHub stars~3.5k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Anything2explainer

    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated…

    2.4k GitHub stars~2.7k tokensUpdated 23 days ago
    Media & CreativeAuto-check passed
  • Speech To Text

    tadaspetra/loop

    Transcribe audio to text using ElevenLabs Scribe v2. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~2k tokens
    Media & CreativeAuto-check passed
  • Edit Timeline Studio

    MartinDelophy/ai-video-editor

    Analyze images, video, speech, motion, products, and websites; route local vision, audio, depth, tracking, matting, identity, and restoration models; auto-edit, replicate, enhance, caption, voice…

    905 GitHub stars~7k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Explainroo

    vincentsch/explainroo

    Make an explainer video (MP4) with a voice-over using explainroo.

    515 GitHub stars~439 tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • OneWorks 3D Avatar Designer

    oneworks-ai/avatar

    Creates, refines and exports editable OneWorks 3D geometric avatars for mascots, bots or agents, keeping one shared scene state across preview, share link and export.

    251 GitHub stars~1.7k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from DRincs-Productions/pixi-vn

All 13 skills in this repo
  • Pixi Vn Assets

    DRincs-Productions/pixi-vn

    A skill your agent uses when adding, organizing, registering, or loading non-code files (images, audio, video) in a Pixi'VN project — local assets processed by PixiJS AssetPack vs.

    149 GitHub stars~2.9k tokensUpdated 10 days ago
    Auto-check passed
  • Pixi Vn Characters

    DRincs-Productions/pixi-vn

    A skill your agent uses when defining visual novel characters for a @drincs/pixi-vn game — creating a character with a name, color, icon and other props, registering it so it can be looked up by id…

    149 GitHub stars~3.1k tokensUpdated 10 days ago
    Auto-check passed
  • Pixi Vn History

    DRincs-Productions/pixi-vn

    A skill your agent uses when implementing "go back" / "rewind" / step-navigation features in a Pixi'VN game, or when you need to read the player-facing dialogue/choice history (e.g.

    149 GitHub stars~2.6k tokensUpdated 10 days ago
    Auto-check passed
  • Pixi Vn Minigames

    DRincs-Productions/pixi-vn

    A skill your agent uses when adding a minigame (snake, quiz, puzzle, timing/reaction game, ...) to a Pixi'VN visual novel — the useMinigame lifecycle hook pattern, using PixiJS directly on its own…

    149 GitHub stars~2.9k tokensUpdated 10 days ago
    Auto-check passed
  • Pixi Vn Narration

    DRincs-Productions/pixi-vn

    A skill your agent uses when writing or editing Pixi'VN story content — defining labels (scenes) with newLabel, writing dialogue steps, adding player choices with…

    149 GitHub stars~4.9k tokensUpdated 10 days ago
    Auto-check passed
  • Pixi Vn Saves

    DRincs-Productions/pixi-vn

    A skill your agent uses when implementing save/load in a Pixi'VN game — Game.exportGameState()/restoreGameState()/jsonToGameState(), what the exported GameState contains, and how to persist it (save…

    149 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed

Works with

Questions about Pixi Vn Testing

What does Pixi Vn Testing do?

A skill your agent uses when an AI agent (or any external script) needs to play-test a running Pixi'VN game end-to-end in a real browser — starting the game, advancing/branching the story, answering…. Pixi Vn Testing is an agent skill from DRincs-Productions/pixi-vn.testing, the opt-in devtools bridge exposed on window.

When should I use Pixi Vn Testing?

Pixi Vn Testing fits situations like: an AI agent (or any external script) needs to play-test a running PixiVN game end-to-end in a real browser — starting the game; advancing/branching the story; answering input prompts; reading/writing storage — via Game.testing.

How do I install Pixi Vn Testing in Claude Code?

Run `npx skills add DRincs-Productions/pixi-vn --skill pixi-vn-testing -a claude-code`. Or copy the skill folder (skills/testing in DRincs-Productions/pixi-vn) into .claude/skills/pixi-vn-testing in your project. Claude Code loads it when a task matches its description.

How do I install Pixi Vn Testing in Codex?

Run `npx skills add DRincs-Productions/pixi-vn --skill pixi-vn-testing -a codex`. Or copy the skill folder (skills/testing in DRincs-Productions/pixi-vn) into .agents/skills/pixi-vn-testing in your project. Codex loads it when a task matches its description.

Can I use Pixi Vn Testing 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 DRincs-Productions/pixi-vn --skill pixi-vn-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pixi-vn-testing, .gemini/skills/pixi-vn-testing, .github/skills/pixi-vn-testing and .opencode/skills/pixi-vn-testing in your project.

What does Pixi Vn Testing need to run?

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

Does Pixi Vn Testing 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 Pixi Vn Testing 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 Pixi Vn Testing use?

Pixi Vn Testing is published under the LGPL-2.1 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pixi Vn Testing use?

About 3.8k tokens (SKILL.md is roughly 15k 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 Pixi Vn Testing?

Skills that share tags, products or a category with Pixi Vn Testing: Dotlottie Web (LottieFiles/dotlottie-web, 892 stars), Anything2explainer (Vincentwei1021/anything2explainer, 2.4k stars), Speech To Text (tadaspetra/loop, 296 stars) and Edit Timeline Studio (MartinDelophy/ai-video-editor, 905 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pixi Vn Testing?

DRincs-Productions (a GitHub organization) maintains it in DRincs-Productions/pixi-vn, which has 149 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 1, 2026.

Source: DRincs-Productions/pixi-vn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.