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

Autobots Auto Improvement

ASecurity

Use quando precisar criar agentes que se auto-melhoram continuamente (autobots) — avaliador independente, auto-retrain, ciclo de melhoria autônomo, integração CRM/Slack/GitHub/broker. Triggers em "autobots", "auto-melhoria IA", "auto-retrain", "avaliador independente", "Abacos", "ciclo melhoria autônomo", "IA que aprende sozinha", "auto-improvement loop".

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

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill autobots-auto-improvement --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Autobots Auto Improvement?

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

Security grade badge for Autobots Auto Improvement
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-autobots-auto-improvement/badge)](https://www.skillsdirectory.com/skills/majinmagros-autobots-auto-improvement)

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

Download Zip
Files
SKILL.md
---
name: autobots-auto-improvement
description: Use quando precisar criar agentes que se auto-melhoram continuamente (autobots) — avaliador independente, auto-retrain, ciclo de melhoria autônomo, integração CRM/Slack/GitHub/broker. Triggers em "autobots", "auto-melhoria IA", "auto-retrain", "avaliador independente", "Abacos", "ciclo melhoria autônomo", "IA que aprende sozinha", "auto-improvement loop".
metadata:
  origin: ECC
---

# Skill: Autobots — Agentes que se Auto-Melhoram (Auto-Improvement Loop)

> Baseado no vídeo `yRkvxxRpkiw` (AI Revolution em Português) — Abacos: 4 autobots rodando em produção (vendas Notion→Slack, código GitHub, YouTube, broker). Agente executa trabalho, avaliador independente avalia, auto-retrain baseado em conversão. "IA esquece, agente aprende."

## Quando usar

- Precisa de agente que melhora sozinho sem intervenção humana
- Quer separar **execução** de **avaliação** (evita autoconfiança/viés)
- Precisa de auto-retrain baseado em métricas reais (conversão, performance, erro)
- Quer integrar CRM (Notion), Slack, GitHub, broker, YouTube como fontes de feedback
- "IA esquece, agente aprende" — ciclo contínuo de melhoria autônoma

## 2. Arquitetura do Autobot (Divisão Obrigatória)

```
┌─────────────────────────────────────────────────────────────┐
│                    AUTOBOSS (Orquestrador)                  │
│  - Agenda (cron 4AM)                                        │
│  - Roteia: Executor → Avaliador → Retrain → Deploy          │
│  - Guarda estado global (ledger de versões)                 │
└─────────────────────────────────────────────────────────────┘
         ↓                    ↓                    ↓
┌───────────────┐    ┌───────────────┐    ┌───────────────┐
│   EXECUTOR    │    │  AVALIADOR    │    │   RETRAINER   │
│  (Worker)     │    │  (Judge)      │    │  (Trainer)    │
│  - Executa    │    │  - Métrica    │    │  - Novo model │
│    tarefa     │    │    objetiva   │    │    versionado │
│  - Output     │    │  - 0-100      │    │  - A/B test   │
│    bruto      │    │  - Sem viés   │    │  - Deploy se  │
└───────────────┘    └───────────────┘    │    melhor     │
                                            └───────────────┘
```

**Regra de Ouro:** Executor e Avaliador são **modelos/separados/instâncias diferentes**. Avaliar próprio trabalho gera autoconfiança → viés → estagnação.

## 2.1 4 Autobots de Referência (Abacos)

| Autobot | Domínio | Fonte Feedback | Métrica | Frequência |
|---|---|---|---|---|
| **Sales** | Pipeline Notion CRM | Slack (demos) | Lead score 0-100, conversão | 4AM diário (3 runs) |
| **Code** | Repo GitHub | Testes, CI, code review | Pass rate, latency, bugs | Push/PR |
| **Content** | Canal YouTube | Analytics, comentários | CTR, retention, engagement | Diário |
| **Trading** | Corretora (broker API) | P&L, Sharpe, drawdown | ROI, risk-adjusted | Tick/horário |

## 3. Ciclo de Melhoria (Loop Obrigatório)

```python
# Pseudocódigo do ciclo
while True:
    # 1. EXECUTOR executa tarefa
    output = executor.run(task, context)
    
    # 2. AVALIADOR independente avalia
    score = evaluator.score(output, ground_truth_or_metric)
    
    # 3. REGISTRA no ledger (versão, score, diff)
    ledger.log(version=executor.version, score=score, output=output)
    

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 →