Agent skill

Vm Critico Visual

by corosolto in corosolto/client

Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma.

AGPL-3.0Auto-check passedGame Development

Install Vm Critico Visual

skills CLI
$ npx skills add corosolto/client --skill vm-critico-visual -a claude-code

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

GitHub CLI
$ gh skill install corosolto/client vm-critico-visual --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/corosolto/client.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/vm-critico-visual .claude/skills/vm-critico-visual && 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
vm-critico-visual
GitHub stars
257
Token cost
~929 tokens
SKILL.md length
484 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma.

  • Works in 2 steps: O caminho autorado precisa estar VIVO,… → Um servidor de pé, e só um navegador…
  • Game Development work in your project
  • SKILL.md covers Por que existe, Antes de rodar, Passo 1 — as figuras, no jogo… and Passo 2 — o crítico cego, plus 3 more sections
  • Calls node and npm

What it does

Vm Critico Visual is an agent skill from corosolto/client. Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma. Use ao reconstruir qualquer arma, antes de dizer que está pronta.

Its SKILL.md is about 930 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 Game Development. The repository describes itself as: FPS satírico de navegador: 5 facções brasileiras caricatas, 44 personagens, 5 mapas e 26 armas — rounds e Capture the Flag contra bots, direto na aba, sem instalar nada. Three.js… The licence is AGPL-3.0.

When your agent uses it

  • Game Development work in your project

Example prompts

  • “/vm-critico-visual”

Workflow steps

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

  1. O caminho autorado precisa estar VIVO, ou você vai criticar o viewmodel
  2. Um servidor de pé, e só um navegador headless por vez — duas sessões

What it can do on your machine

Read from SKILL.md and the folder at commit 6277618. 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:

    • node
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, 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

Vm Critico Visual loads about 929 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 484 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~929

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 corosolto/client at commit 6277618, republished under its AGPL-3.0 licence (© corosolto). 484 words, ~929 tokens.

Download SKILL.mdSave it as .claude/skills/vm-critico-visual/SKILL.md (or your agent's skills folder).
name
vm-critico-visual
description
Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma. Use ao reconstruir qualquer arma, antes de dizer que está pronta.

Rodada de crítica visual do viewmodel

Por que existe

O dono revisou o arsenal duas vezes no olho e achou, das duas, defeitos que nenhuma régua tinha pegado: arma invertida, recarga arrancando o cano, mão por cima do cano, metade do pente ficando presa. As réguas contavam vértice e ficavam verdes.

O motivo é sempre o mesmo e está na gauntlet-fps: quem constrói nunca dá a nota. Quem constrói conhece a intenção e lê o frame pela intenção.

Esta skill fecha esse buraco: gera a figura, entrega a um crítico que só vê pixel, e devolve o veredito no vocabulário do dono.

Antes de rodar

  1. O caminho autorado precisa estar VIVO, ou você vai criticar o viewmodel legado sem saber (foi o BUG-156, e custou um dia):

    bash
    npm run eval:vm-autorado-vivo

    Verde = as armas golden montam o GLB novo com mão visível. Vermelho = pare aqui, não adianta criticar.

  2. Um servidor de pé, e só um navegador headless por vez — duas sessões derrubam o boot e falsificam a medição.

    bash
    node tools/eval/serve.mjs 4361
    pkill -f "chrome-mac|chromium"

Passo 1 — as figuras, no jogo real

bash
node tools/viewmodels/prep/vm-arsenal-frames.mjs --porta=4361 --aspecto=32 \
  --modo=autorado --armas=<lista> --saida=/tmp/critica-r1

--aspecto=32 porque o dono joga em 3:2. Validar só em 16:9 já custou uma rodada inteira.

Gera <arma>-<estado>.png em idle, ads, fire e quadros da recarga. A recarga é uma sequência: um frame só não decide.

Complemente com a bancada, que mostra as 15 lado a lado e pinta de vermelho a peça que a recarga arranca — é a figura que decide "fica parte do pente":

bash
node tools/eval/vm-bancada-check.mjs --porta=4361 --clipe=Reload \
  --maos=1 --figura=/tmp/critica-r1/bancada-reload.png

Passo 2 — o crítico cego

Chame o agente critico-visual-vm passando só o diretório de figuras.

Não mande junto o que você consertou, por que consertou, nem o que espera que ele veja. Se ele souber a intenção, ele lê o frame pela intenção, e aí você tem um segundo construtor em vez de um crítico.

Prompt que funciona:

Julgue o viewmodel das armas nas figuras de /tmp/critica-r1.
A AK é a referência aprovada. Devolva o veredito por arma no formato da sua
definição. Leia TODAS as imagens antes de escrever.
Show full SKILL.md (187 more words)Show less

Passo 3 — o que fazer com o veredito

  • Regressão vem primeiro. Arma que piorou não dorme.
  • Agrupe por causa, não por arma. Dois vereditos seguidos mostraram que seis armas diferentes eram um defeito só no construtor.
  • Uma arma REPROVADA não fecha porque a régua de contagem está verde. Quando o dono diz que está errado e o portão está verde, o defeito é do portão (bug-hunt, lei 1).

Passo 4 — a segunda rodada

Reconstrua, gere /tmp/critica-r2 e chame o crítico com as duas pastas, pedindo explicitamente o que piorou. Contexto limpo: não reaproveite a sessão do crítico anterior, ou ele defende o veredito antigo.

Detector de giro: duas rodadas sem mover nenhuma arma de REPROVADA para RESSALVA/APROVADA significa que o loop está girando. Troque de frente ou pare e reporte o platô medido — rodada que não move número é custo.

O que esta skill não faz

Não julga o que não está na imagem: contagem de vértice, nome de osso, config. Para isso existem as réguas (eval:vm-*), e elas são cegas ao que o crítico vê. São instrumentos diferentes e nenhum dos dois substitui o dono jogando.

© corosolto, AGPL-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

Just SKILL.md in .claude/skills/vm-critico-visual of corosolto/client.

Open the folder on GitHubat commit 6277618

Compare with similar skills

Vm Critico Visual 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.

Vm Critico Visual compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vm Critico Visual this skillcorosolto/client257—~929Automated safety check: PassAGPL-3.0
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
Web CloneJane-xiaoer/claude-skill-web-clone1k1 repos~2.7kAutomated safety check: PassMIT
Threejs Game Directormajidmanzarpour/threejs-game-skills2.5k—~2.2kAutomated safety check: PassMIT
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed
  • Web Clone

    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…

    1k GitHub starsUsed in 1 repo~2.7k tokens
    Game DevelopmentAuto-check passed
  • Threejs Game Director

    majidmanzarpour/threejs-game-skills

    Entrypoint for building, upgrading, and finishing Three.js browser games.

    2.5k GitHub stars~2.2k tokensUpdated 11 days ago
    Game DevelopmentAuto-check passed
  • Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 7 days ago
    Game DevelopmentAuto-check passed
  • Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed
  • Uloop Execute Dynamic Code

    CyberAgentGameEntertainment/NovaShader

    Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.

    1.6k GitHub starsUsed in 1 repo~1.9k tokens
    Game DevelopmentAuto-check passed

More from corosolto/client

All 21 skills in this repo
  • Threejs Gameplay Systems

    corosolto/client

    Build and iterate playable Three.js game systems. An agent skill from corosolto/client.

    257 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Threejs Gltf Loading

    corosolto/client

    Load glTF/GLB models in three.js with GLTFLoader and play their skinned animations with AnimationMixer, including DRACO/Meshopt-compressed meshes and KTX2 textures.

    257 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Threejs 3D Generator

    corosolto/client

    Generate, texture, rig, animate, stylize, convert, and download 3D assets for Three.js games using the Tripo API.

    257 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Light and shade a three.js scene: choose materials (MeshStandardMaterial PBR vs unlit MeshBasicMaterial), add ambient/hemisphere/directional/point/spot lights, turn on shadow maps, and use an…

    257 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Threejs Scene Setup

    corosolto/client

    Stand up a three.js scene: import maps and the three/addons path, the Scene/PerspectiveCamera/WebGLRenderer trio, the setAnimationLoop render loop, responsive resize, and OrbitControls.

    257 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Threejs Game Director

    corosolto/client

    Primary entrypoint for complete Three.js browser game creation and premium iteration.

    257 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Questions about Vm Critico Visual

What does Vm Critico Visual do?

Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma. Vm Critico Visual is an agent skill from corosolto/client. Rodada de crítica visual do viewmodel do arsenal — gera as figuras no jogo real, chama o crítico cego e devolve o veredito por arma.

When should I use Vm Critico Visual?

Vm Critico Visual fits situations like: game Development work in your project.

How do I install Vm Critico Visual in Claude Code?

Run `npx skills add corosolto/client --skill vm-critico-visual -a claude-code`. Or copy the skill folder (.claude/skills/vm-critico-visual in corosolto/client) into .claude/skills/vm-critico-visual in your project. Claude Code loads it when a task matches its description.

How do I install Vm Critico Visual in Codex?

Run `npx skills add corosolto/client --skill vm-critico-visual -a codex`. Or copy the skill folder (.claude/skills/vm-critico-visual in corosolto/client) into .agents/skills/vm-critico-visual in your project. Codex loads it when a task matches its description.

Can I use Vm Critico Visual 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 corosolto/client --skill vm-critico-visual -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vm-critico-visual, .gemini/skills/vm-critico-visual, .github/skills/vm-critico-visual and .opencode/skills/vm-critico-visual in your project.

What does Vm Critico Visual need to run?

Going by SKILL.md and its folder, Vm Critico Visual needs the command-line tools its instructions call (node and npm).

Does Vm Critico Visual access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Vm Critico Visual 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 Vm Critico Visual use?

Vm Critico Visual is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vm Critico Visual use?

About 929 tokens (SKILL.md is roughly 3.7k 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 Vm Critico Visual?

Skills that share tags, products or a category with Vm Critico Visual: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vm Critico Visual?

corosolto (a GitHub organization) maintains it in corosolto/client, which has 257 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 9, 2026.

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