New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vastai Reference Architecture

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Design a governed Vast.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown.

MITAuto-check passedBackend & APIs

Install Vastai Reference Architecture

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill vastai-reference-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace vastai-reference-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/vastai-reference-architecture .claude/skills/vastai-reference-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vastai-reference-architecture
GitHub stars
2.8k
Token cost
~1.1k tokens
SKILL.md length
451 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Design a governed Vast.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown.

  • Works in 6 steps: Define the immutable intent → Separate planner and mutator → Choose the executor → …
  • Reviewing a production architecture spanning instances
  • SKILL.md covers Overview, Prerequisites, Instructions and Authentication, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vastai Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Design a governed Vast.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown. Use when reviewing a production architecture spanning instances or Serverless. Trigger with: "design a Vast.ai architecture", "govern GPU workload lifecycles", "review a Vast.ai platform".

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-docs.md`). Compatibility notes: Requires workload and data classification, Vast.ai account design, immutable artifacts, external storage, observability, and incident ownership.

It sits in Backend & APIs, covering Serverless. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Reviewing a production architecture spanning instances
  • With: design a Vast.ai architecture
  • Govern GPU workload lifecycles
  • Review a Vast.ai platform

Example prompts

  • “design a Vast.ai architecture”
  • “govern GPU workload lifecycles”
  • “review a Vast.ai platform”
  • “/vastai-reference-architecture”

Requirements

  • Compatibility (from SKILL.md): Requires workload and data classification, Vast.ai account design, immutable artifacts, external storage, observability, and incident ownership.
  • Pre-approved tools (allowed-tools): Read, Grep, Write, Edit

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Define the immutable intent
  2. Separate planner and mutator
  3. Choose the executor
  4. Externalize durable state
  5. Observe and reconcile
  6. Close every lifecycle

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.vast.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires workload and data classification, Vast.ai account design, immutable artifacts, external storage, observability, and incident ownership.

    From compatibility in the SKILL.md frontmatter.

Context cost

Vastai Reference Architecture loads about 1.1k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 451 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 451 words, ~1,138 tokens.

Download SKILL.mdSave it as .claude/skills/vastai-reference-architecture/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
vastai-reference-architecture
description
Design a governed Vast.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown. Use when reviewing a production architecture spanning instances or Serverless. Trigger with: "design a Vast.ai architecture", "govern GPU workload lifecycles", "review a Vast.ai platform".
allowed-tools
Read, Grep, Write, Edit
compatibility
Requires workload and data classification, Vast.ai account design, immutable artifacts, external storage, observability, and incident ownership.
version
2.0.0
argument-hint
[workload-types-slos-data-class-and-budget]
model
inherit
effort
high
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, vastai, architecture, governance, reliability

Governed Vast.ai GPU Workload Architecture

Overview

Center the architecture on an immutable run or release manifest and a lifecycle ledger. Search and planning are read-only; paid resource creation crosses an approval boundary; execution writes recoverable state externally; teardown closes both cost and evidence.

Prerequisites

  • Batch, training, interactive, or Serverless workload inventory with SLOs
  • Data, model, image, credential, region, reliability, and spend policies
  • Owners for approval, execution, recovery, billing, security, and platform incidents

Instructions

Step 1: Define the immutable intent

Create a signed or versioned manifest containing workload bytes, image/template/model identity, GPU policy, data/checkpoint routes, SLOs, budget, and expiry.

Step 2: Separate planner and mutator

Let a read-scoped planner evaluate offers or Serverless profiles. Require explicit approval before a narrowly scoped mutator creates, updates, transfers credit, or destroys.

Step 3: Choose the executor

Use an instance lifecycle for bounded jobs or dedicated services; use Serverless endpoint/workergroup control for managed inference scaling and rolling updates.

Step 4: Externalize durable state

Keep datasets, checkpoints, artifacts, event ledgers, and evidence outside disposable root disks with checksums and recovery objectives.

Step 5: Observe and reconcile

Combine provider states, signed notifications, bounded polling, workload SLOs, balance, charges, and resource inventory; reconcile events against periodic reads.

Step 6: Close every lifecycle

Accept output, copy evidence, destroy disposable resources, revoke temporary access, reconcile charges, and leave an auditable handoff for retained resources.

Authentication

Use native Teams roles and distinct scoped keys for planning, mutation, monitoring, and administration. Workload storage and registry credentials must never inherit control-plane authority.

Show full SKILL.md (202 more words)Show less

Tool Discipline

Use Read and Grep to inspect manifests, configuration, provider output, and existing tests before proposing a mutation. Use Write or Edit only for the approved plan, implementation, test, or redacted receipt; do not create, update, destroy, or fund Vast.ai resources without explicit operator approval.

Output

  • Trust-boundary and component decision record
  • Immutable manifest, lifecycle ledger, recovery, and observability contracts
  • Threat, failure, cost, rollback, and teardown evidence plan

Return workload classes, chosen executors, authority boundaries, immutable artifacts, recovery targets, SLOs, budgets, event reconciliation, and lifecycle owners.

Examples

A planner selects verified offers but cannot rent; an approved mutator creates from a signed run manifest; the training executor checkpoints externally; a signed event plus reconciliation loop detects failure; a finalizer destroys the instance and closes the charge ledger.

Error Handling

FailureResponse
One service can plan, fund, mutate, and erase evidenceSplit authority and add independent approval and audit.
Durable state exists only on an instanceMove it to an external verified store before production.
Event stream is treated as completeAdd periodic resource reconciliation and idempotent processing.
Resource has no expiry or cleanup ownerReject the architecture until the lifecycle can close.

Resources

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/vastai-reference-architecture of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/official-docs.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Vastai Reference Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vastai Reference Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vastai Reference Architecture this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: PassMIT
Arcgis To Portaljsdatopian/portaljs2.4k1 repos~2kAutomated safety check: PassMIT
AWS Serverless Edazxkane/aws-skills3674 repos~3.2kAutomated safety check: PassMIT
NubaseOtterMind/Nubase622—~2.2kAutomated safety check: NotesApache-2.0
Tianji Worker Operationsmsgbyte/tianji3.1k—~1.1kAutomated safety check: PassApache-2.0
Qstash JSupstash/qstash-js269—~746Automated safety check: PassMIT

Similar skills

  • Arcgis To Portaljs

    datopian/portaljs

    Migrate a whole ArcGIS Hub site into a PortalJS Arc portal end-to-end.

    2.4k GitHub starsUsed in 1 repo~2k tokens
    Backend & APIsAuto-check passed

  • AWS Serverless Eda

    zxkane/aws-skills

    AWS serverless and event-driven architecture expert based on Well-Architected Framework.

    367 GitHub starsUsed in 4 repos~3.2k tokens
    Backend & APIsAuto-check passed

  • Nubase

    OtterMind/Nubase

    A skill your agent uses when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets…

    622 GitHub stars~2.2k tokensUpdated 13 days ago
    Backend & APIsAuto-check: notes

  • Tianji Worker Operations

    msgbyte/tianji

    Operates Tianji Workers: create, test, deploy, invoke, schedule, pause and roll back them, plus manage their environment variables and shared modules.

    3.1k GitHub stars~1.1k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

  • Qstash JS

    upstash/qstash-js

    Official

    Work with the QStash JavaScript/TypeScript SDK for serverless messaging, scheduling.

    269 GitHub stars~746 tokensUpdated 5 days ago
    Backend & APIsAuto-check passed

  • AWS Solution Architect

    alirezarezvani/claude-skills

    Design AWS architectures for startups using serverless patterns and IaC templates.

    28k GitHub starsUsed in 1 repo~2.5k tokens
    Backend & APIsAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Vastai Reference Architecture

What does Vastai Reference Architecture do?

Design a governed Vast.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown. Vastai Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace.ai GPU control plane that separates planning, paid mutation, execution, recovery, evidence, and teardown.

When should I use Vastai Reference Architecture?

Vastai Reference Architecture fits situations like: reviewing a production architecture spanning instances; with: design a Vast.ai architecture; govern GPU workload lifecycles; review a Vast.ai platform.

How do I install Vastai Reference Architecture in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill vastai-reference-architecture -a claude-code`. Or copy the skill folder (skills/.curated/vastai-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/vastai-reference-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Vastai Reference Architecture in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill vastai-reference-architecture -a codex`. Or copy the skill folder (skills/.curated/vastai-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/vastai-reference-architecture in your project. Codex loads it when a task matches its description.

Can I use Vastai Reference Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill vastai-reference-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vastai-reference-architecture, .gemini/skills/vastai-reference-architecture, .github/skills/vastai-reference-architecture and .opencode/skills/vastai-reference-architecture in your project.

What does Vastai Reference Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Vastai Reference Architecture is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Write, Edit. Compatibility (from SKILL.md): Requires workload and data classification, Vast.ai account design, immutable artifacts, external storage, observability, and incident ownership..

Does Vastai Reference Architecture access the network?

SKILL.md names 1 domain. As links in the text: docs.vast.ai. This is read from the text; nothing was executed.

Is Vastai Reference Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vastai Reference Architecture use?

Vastai Reference Architecture is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vastai Reference Architecture use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 329 tokens, read only when the agent opens those files.

What are the alternatives to Vastai Reference Architecture?

Skills that share tags, products or a category with Vastai Reference Architecture: Arcgis To Portaljs (datopian/portaljs, 2.4k stars), AWS Serverless Eda (zxkane/aws-skills, 367 stars), Nubase (OtterMind/Nubase, 622 stars) and Tianji Worker Operations (msgbyte/tianji, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vastai Reference Architecture?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.