# Ag Avaliar Software

> Avaliacao tecnica de software externo antes de incorporacao. Analisa stack, qualidade, seguranca, dados e compatibilidade. Produz score Go/No-Go.

- **Type:** Skill
- **Install:** `agentstack add skill-andregusman-raiz-a-gusman-claude-ag-avaliar-software`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [andregusman-raiz](https://agentstack.voostack.com/s/andregusman-raiz)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [andregusman-raiz](https://github.com/andregusman-raiz)
- **Source:** https://github.com/andregusman-raiz/a-gusman-claude/tree/main/skills/ag-avaliar-software

## Install

```sh
agentstack add skill-andregusman-raiz-a-gusman-claude-ag-avaliar-software
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ag-avaliar-software — Due Diligence Tecnica

Spawn the `ag-avaliar-software` agent to evaluate external software for incorporation. Analyzes stack, quality, security, data, and compatibility. Produces Go/No-Go score.

## Invocation

Use the **Agent tool** with:
- `subagent_type`: `ag-avaliar-software`
- `mode`: `auto`
- `run_in_background`: `true`
- `prompt`: Compose from template below + $ARGUMENTS

## Prompt Template

```
Projeto: [CWD or user-provided path]
Software: [nome do software externo]
URL/Path: [URL do repo ou path local]

## Output
- Due diligence report com Go/No-Go score
- Analise de: stack, qualidade de codigo, seguranca, dados, compatibilidade com rAIz Platform
- Riscos identificados com mitigacao sugerida

Realize due diligence tecnica completa: identificacao, stack analysis, qualidade de codigo,
seguranca, dados/schema, compatibilidade com rAIz Platform (Next.js 14, TS, Supabase, Vercel).
Produza relatorio com score Go/No-Go fundamentado.
Referencia: Playbook 11 (Incorporacao de Software).
```

## Important
- ALWAYS spawn as Agent subagent — do NOT execute inline
- Runs in background — produces detailed evaluation report
- After spawning, confirm to the user

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [andregusman-raiz](https://github.com/andregusman-raiz)
- **Source:** [andregusman-raiz/a-gusman-claude](https://github.com/andregusman-raiz/a-gusman-claude)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-andregusman-raiz-a-gusman-claude-ag-avaliar-software
- Seller: https://agentstack.voostack.com/s/andregusman-raiz
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.