Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Capricho

ASecurity

Evolucao do unlazy com gates de qualidade visual + relatorio obrigatorio. Use when precisa de entrega caprichada: site/app com acabamento visual, Kanban drag-and-drop, boids/cardume. Triggers on "capricho", "caprichado", "acabamento visual", "entrega premium", "unlazy melhorado".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgogitfrontend

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill capricho --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Capricho?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Capricho
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-capricho/badge)](https://www.skillsdirectory.com/skills/majinmagros-capricho)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: capricho
description: Evolucao do unlazy com gates de qualidade visual + relatorio obrigatorio. Use when precisa de entrega caprichada: site/app com acabamento visual, Kanban drag-and-drop, boids/cardume. Triggers on "capricho", "caprichado", "acabamento visual", "entrega premium", "unlazy melhorado".
---

# Capricho — Unlazy com Acabamento Visual e Relatório

> Evolução criada por `Maestros da IA` sobre `Leonxlnx/unlazy` (vídeo `8fAuXr8fQBo` l.61-589, transcript local `8fAuXr8fQBo.pt.dedup.txt` em `YT_DIR`). `unlazy` = base open-source MIT; `capricho` = exclusiva comunidade, aqui reimplementada como extensão ECC open.

`Capricho = Unlazy + 2 gates extras` — o pipeline é o mesmo, mas vence onde `unlazy` falha: **qualidade visual** e **histórico reportável**.

## Quando usar

- Mesmos gatilhos de `unlazy` + precisa de nota visual (landing, dashboard, Three.js, cardume)
- Unlazy entregou funcional mas com "cara de AI slop" (vídeo l.221-242, l.565-581)
- Precisa de relatório que o agente e o humano consigam auditar depois (l.583-589)

## Quando NÃO usar

- Tarefa não-visual pura (ex: migração DB) → use `unlazy` puro (mais leve)
- Ideação/validação → use `triagem-ideias`

## O que muda vs Unlazy

| Dimensão | Unlazy | Capricho (esta) |
|----------|--------|-----------------|
| Gates funcionais | ✅ CHECK/EXPECT/EVIDENCE | ✅ idem |
| **Gate visual** | ❌ não avalia estética | ✅ gate manual com checklist visual + screenshot/preview obrigatório |
| **Gate de relatório** | opcional | ✅ obrigatório: `.capricho/RELATORIO.md` com gates, prints, custo, tempo |
| Pipeline | 4 passes (implement, re-read, hunt, polish) | **5 passes**: os 4 + `visual polish` (design system, micro-interações, densidade, tipografia) |
| Custo | ~$69 (video l.599-601) | ~$71 mas **mais rápido** (paralelismo melhor, video l.617-624) |

## Workflow

1. **Herde tudo de `unlazy`**: escreva gates funcionais (GATES.md, CHECK/EXPECT).
2. **Adicione 2 gates obrigatórios**:
   - `V1: Qualidade visual aprovada` — `EVIDENCE: screenshot <path> + checklist (tipografia, espaçamento, contraste, micro-interação)` — manual, mas bloqueia done.
   - `R1: Relatório gerado` — `CHECK: test -f .capricho/RELATORIO.md && grep -q "Gates:" .capricho/RELATORIO.md` / `EXPECT: Gates:`
3. **5 passes por leaf**: execute os 4 de unlazy + `visual polish` — aplique `frontend-patterns`, `taste`, `motion-patterns` conforme domínio.
4. **Gere relatório** (template em `references/relatorio-template.md`):
   ```md
   # Relatório Capricho — <task>
   Gates: N/N, Abandonados: 0
   Custo: $X, Tempo: Y min (wall-clock Z)
   Gates visuais: V1 [x] evidência <screenshot>
   Ledger: <cole GATES.md completo>
   ```
5. **Valide**: `gate-check.mjs` deve marcar V1 e R1 como met; sem eles, done bloqueia mesmo com gates funcionais OK.

## Checklist visual (gate V1)

- [ ] Densidade e hierarquia tipográfica ok (não wall of text)
- [ ] Espaçamento, bordas, sombras coerentes (evita AI slop)
- [ ] Interação chave funciona (ex: kanban drag-and-drop l.187-195, l.205-210)
- [ ] Screenshot anexado em `EVIDENCE`

## Solo vs Orquestrado

Mesma regra de `unlazy`: `tree ≤3` solo, `≥4` orquestrado com `dispatch.json` e parent `--reverify`. Capricho herda Stop hook.

## Referências

- `references/relatorio-template.md` — template do relatório
- `references/visual-gate.md` — checklist visual detalhado
- Base: `skills/unlazy/SKILL.md` + https://github.com/Leonxlnx/unlazy

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →