How do I install the Infra Advisor skill?

Run npx skillmds@latest add zedarvates/infra-advisor in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Infra Advisor safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Infra Advisor?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Infra Advisor free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Infra Advisor?

zedarvates (@zedarvates) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Infra Advisor by zedarvates — Agent Skill

Name: Infra Advisor
Author: zedarvates

Infra Advisor

Audit the local cluster's hardware/software/MCP setup and recommend changes that cut token cost — GPU upgrades, Hailo NPU for vision, moving the inference node to Linux, running Qdrant locally, wiring MCP — with an ASCII cluster diagram. Also provides an auto one-pass audit (directives + infra + code duplication + skills) on the project. Use when the user asks how to reduce token/usage cost via hardware/infra, wants cluster setup tips, an ASCII diagram of their setup, or a quick all-in-one audit.

zedarvates 45a2b17 7 files · 26.9 KB Updated Sep 17, 2026

File contents

infra_advisor — cut token cost beyond the code

Most audits only look at code. This looks at the machine and the local cluster and recommends concrete hardware/software/infra changes that move work off paid cloud models — then bundles a fast one-pass audit of the project.

Commands

# Cluster tips + ASCII diagram
python -m skills.infra_advisor.cli tips
python -m skills.infra_advisor.cli tips --subnet --json

# One-pass audit on the project where Botte Secrète is installed
python -m skills.infra_advisor.cli auto .
python -m skills.infra_advisor.cli auto /path/to/project --json

Infra tips (rules, prioritized P0→P3)

Install a local LLM (LM Studio/Ollama) if none — the foundation for any saving.
Add/upgrade a GPU (≥12-16 GB VRAM) → run a 7-14B coder locally.
Add a Hailo-8 / 8L / 10 NPU → vision (detection/OCR/PDF) at ~0 tokens via media_loader.
Move the always-on inference node to Linux/WSL2 → no forced Windows reboots/updates killing the endpoint; more free VRAM/RAM.
Run Qdrant locally → unlock the semantic response cache (-60% repeats).
Dedicate the strongest host as a shared inference node for all projects.
Wire the MCP server (bootstrap) so the agent actually uses the local tools.

Each tip carries why and an impact (expected token/cost effect). An ASCII cluster diagram is rendered by default (--json for machine-readable).

Auto audit

auto combines the cheap, reliable passes into one report: directives health (directives_audit) · infra tips + diagram · duplicate function bodies across files (stdlib AST, free) · skill catalog size · plus pointers to deeper passes (full mousquetaires/fallow pipeline, skill_project_optimizer, understand-anything, botte terminal compression).

Exposed via [[llm_mcp]] as infra_tips and auto_audit. Related: [[bootstrap]], [[llm_backends]], [[directives_audit]], [[skill_finder]].

---name: infra-advisordescription: Audit the local cluster's hardware/software/MCP setup and recommend changes that cut token cost — GPU upgrades, Hailo NPU for vision, moving the inference node to Linux, running Qdrant locally, wiring MCP — with an ASCII cluster diagram. Also provides an auto one-pass audit (directives + infra + code duplication + skills) on the project. Use when the user asks how to reduce token/usage cost via hardware/infra, wants cluster setup tips, an ASCII diagram of their setup, or a quick all-in-one audit.---# infra_advisor — cut token cost beyond the codeMost audits only look at code. This looks at the **machine and the local cluster**and recommends concrete hardware/software/infra changes that move work off paidcloud models — then bundles a fast one-pass audit of the project.## Commands```bash# Cluster tips + ASCII diagrampython -m skills.infra_advisor.cli tipspython -m skills.infra_advisor.cli tips --subnet --json# One-pass audit on the project where Botte Secrète is installedpython -m skills.infra_advisor.cli auto .python -m skills.infra_advisor.cli auto /path/to/project --json```## Infra tips (rules, prioritized P0→P3)- **Install a local LLM** (LM Studio/Ollama) if none — the foundation for any saving.- **Add/upgrade a GPU** (≥12-16 GB VRAM) → run a 7-14B coder locally.- **Add a Hailo-8 / 8L / 10 NPU** → vision (detection/OCR/PDF) at ~0 tokens via `media_loader`.- **Move the always-on inference node to Linux/WSL2** → no forced Windows reboots/updates killing the endpoint; more free VRAM/RAM.- **Run Qdrant locally** → unlock the semantic response cache (-60% repeats).- **Dedicate the strongest host** as a shared inference node for all projects.- **Wire the MCP server** (`bootstrap`) so the agent actually uses the local tools.Each tip carries `why` and an `impact` (expected token/cost effect). An ASCIIcluster diagram is rendered by default (`--json` for machine-readable).## Auto audit`auto` combines the cheap, reliable passes into one report:**directives** health (`directives_audit`) · **infra** tips + diagram · **duplicatefunction bodies** across files (stdlib AST, free) · **skill catalog** size · pluspointers to deeper passes (full `mousquetaires`/fallow pipeline, `skill_project_optimizer`,`understand-anything`, `botte` terminal compression).Exposed via [[llm_mcp]] as `infra_tips` and `auto_audit`. Related: [[bootstrap]],[[llm_backends]], [[directives_audit]], [[skill_finder]].

Frequently asked questions