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

Local Ai Hardware

ASecurity

Deploy local AI hardware (Nvidia DGX Spark $3k, AI PC) vs cloud. Use when deciding buy vs rent GPU, need 100% offline or TCO analysis. Triggers on \"DGX Spark\", \"AI PC\", \"local hardware\", \"Nvidia DGX\", \"hardware local\"

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

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Local Ai Hardware?

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

Security grade badge for Local Ai Hardware
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-local-ai-hardware/badge)](https://www.skillsdirectory.com/skills/majinmagros-local-ai-hardware)

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

Download Zip
Files
SKILL.md
---
name: local-ai-hardware
description: "Deploy local AI hardware (Nvidia DGX Spark $3k, AI PC) vs cloud. Use when deciding buy vs rent GPU, need 100% offline or TCO analysis. Triggers on \"DGX Spark\", \"AI PC\", \"local hardware\", \"Nvidia DGX\", \"hardware local\""
---

# Local AI Hardware — DGX Spark

> Fonte: `1p0HXLv_5wM` (DGX Spark $3k), transcript `1p0HXLv_5wM.pt.dedup.txt:130-180`

Transição cloud → edge: DGX Spark na mesa, 100% grátis/offline, hoje nicho (heavy users), tendência baratear para notebooks.

## Quando usar

- Heavy user/empresa, custo cloud > $500/mês
- Precisa offline, privacidade, latência zero
- Comparar DGX Spark vs `ito-compute` (aluguel) vs Apple Silicon

## Decisão Buy vs Rent

| Critério | Comprar (DGX Spark) | Alugar (ito-compute) |
|---|---|---|
| Custo inicial | $3k | $0 |
| Custo/mês | $0 (energia) | $50-300 |
| Offline | Sim | Não |
| Upgrade | Manual | Instant |

TCO = `hardware + energia*meses` vs `tokens/mês * $/token` (`cost-aware-llm-pipeline`).

## Workflow

1. Estime tokens/mês + custo cloud (`roteamento-modelos-baratos`)
2. Calcule TCO 12 meses
3. Se buy: `DGX Spark` → `vLLM` local → benchmark `local-llm-efficiency`
4. Se rent: use `ito-compute`

## Referências

## Exemplo

```text
Cloud $600/mês em tokens → TCO 12m: $7,2k cloud vs $3k DGX + energia
Buy: DGX Spark → vLLM local → benchmark (tokens/s, qualidade vs cloud)
Rent: segue no ito-compute (upgrade instant, zero capex)
Decide pelo número, não pelo hype do "100% offline"
```

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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 →