Agent skill

Backend AI Guide

by lablup in lablup/backend.ai-webui

Expert guide for Backend.AI distributed computing platform. An agent skill from lablup/backend.ai-webui.

LGPL-3.0Auto-check passedBackend & APIs

Install Backend AI Guide

skills CLI
$ npx skills add lablup/backend.ai-webui --skill backend-ai-guide -a claude-code

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

GitHub CLI
$ gh skill install lablup/backend.ai-webui backend-ai-guide --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/lablup/backend.ai-webui.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/backend-ai-guide .claude/skills/backend-ai-guide && 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
backend-ai-guide
GitHub stars
133
Used in
1 other repo
Token cost
~1.8k tokens
SKILL.md length
638 words
Files
6
Skills in repo
13
Repo updated
First seen
Licence
LGPL-3.0

At a glance

Expert guide for Backend.AI distributed computing platform. An agent skill from lablup/backend.ai-webui.

  • Works in 5 steps: Identify the Question Scope → Fetch the Main README → Recursively Fetch Component Documentation → …
  • S ask about: - Backend.AI architecture
  • SKILL.md covers Purpose, When to Use, Primary Documentation Sources and Instructions, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Backend AI Guide is an agent skill from lablup/backend.ai-webui. Expert guide for Backend.AI distributed computing platform. Automatically activates when users ask about: - Backend.AI architecture, components (Manager, Agent, Storage Proxy, Webserver, App Proxy) - Features (session scheduling, Sokovan orchestrator, multi-tenancy, resource allocation) - APIs (REST, GraphQL), authentication, RBAC authorization - Container runtime (kernels, jail sandbox, hook library, virtual folders) - Accelerator support (CUDA, ROCm, TPU, NPU, Graphcore IPU) - Client SDKs (Python, Java…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `common-questions.md`, `component-overview.md` and `examples/architecture-example.md`).

It sits in Backend & APIs, covering GraphQL, Authorization and RBAC and Multi-tenancy. It works with Python, GraphQL, PostgreSQL and Redis. The repository describes itself as: Backend.AI Web UI for web / desktop app (Windows/Linux/macOS). Backend.AI Web UI provides a convenient environment for users, while allowing various commands to be executed… The licence is LGPL-3.0.

When your agent uses it

  • S ask about: - Backend.AI architecture
  • Components (Manager
  • App Proxy) - Features (session scheduling
  • Sokovan orchestrator

Example prompts

  • “Backend.AI”
  • “backend.ai”
  • “Sokovan”
  • “/backend-ai-guide”

Requirements

  • Python 3
  • Docker
  • Pre-approved tools (allowed-tools): WebFetch, Read

Workflow steps

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

  1. Identify the Question Scope
  2. Fetch the Main README
  3. Recursively Fetch Component Documentation
  4. Follow Additional Links
  5. Synthesize and Present Information

What it can do on your machine

Read from SKILL.md and the folder at commit 10554dc. 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:

    • WebFetch
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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):

    • github.com

    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.

Context cost

Backend AI Guide loads about 1.8k tokens when it runs. Until then it costs about 258 tokens; SKILL.md has 638 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~258
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 lablup/backend.ai-webui at commit 10554dc, republished under its LGPL-3.0 licence (© lablup). 638 words, ~1,772 tokens.

Download SKILL.mdSave it as .claude/skills/backend-ai-guide/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
backend-ai-guide
description
Expert guide for Backend.AI distributed computing platform. Automatically activates when users ask about: - Backend.AI architecture, components (Manager, Agent, Storage Proxy, Webserver, App Proxy) - Features (session scheduling, Sokovan orchestrator, multi-tenancy, resource allocation) - APIs (REST, GraphQL), authentication, RBAC authorization - Container runtime (kernels, jail sandbox, hook library, virtual folders) - Accelerator support (CUDA, ROCm, TPU, NPU, Graphcore IPU) - Client SDKs (Python, Java, JavaScript, PHP) - Setup, requirements (Python 3.13+, Docker, PostgreSQL, Redis, etcd) - How WebUI connects to/interacts with Backend.AI backend - Plugin interfaces, development setup, infrastructure Use when user mentions "Backend.AI", "backend.ai", "Sokovan", component names, or asks about the backend platform this WebUI connects to. For this deployment's live data, a GraphQL field's meaning, or a status value the UI shows, use the `bai-agent` skill instead — it queries the manager and the schema.
allowed-tools
WebFetch, Read

Backend.AI Guide Skill

Purpose

This skill provides expert-level information about the Backend.AI platform by:

  • Fetching official documentation from the Backend.AI GitHub repository
  • Recursively exploring Major Components documentation links
  • Following relevant links to gather comprehensive technical details
  • Providing accurate, source-backed answers about Backend.AI architecture and features

When to Use

Activate this skill when the user asks about:

  • Backend.AI platform overview or architecture
  • Backend.AI components (Manager, Agent, Storage Proxy, Webserver, App Proxy)
  • Backend.AI setup, requirements, or infrastructure
  • Backend.AI APIs (REST, GraphQL)
  • Backend.AI features (session scheduling, resource allocation, multi-tenancy)
  • Backend.AI kernels, containers, or runtime elements
  • How the WebUI connects to or interacts with Backend.AI backend
  • Differences between Backend.AI components

Primary Documentation Sources

  1. Main README: https://github.com/lablup/backend.ai/blob/main/README.md

    • Overview and architecture
    • Major Components section with component links
    • Requirements and setup information
  2. Major Component READMEs: Follow links from the Major Components section

    • Manager component details
    • Agent component details
    • Storage Proxy details
    • Webserver details
    • App Proxy details
    • And other components
  3. Recursive Link Following: When a component README references additional documentation, follow those links to gather comprehensive information

Instructions

Step 1: Identify the Question Scope
  • Determine what aspect of Backend.AI the user is asking about
  • Identify which components or features are relevant
Step 2: Fetch the Main README
Step 3: Recursively Fetch Component Documentation
  • For questions about specific components, fetch their individual READMEs
  • Component README links are found in the "Major Components" section
  • Example component paths (adjust based on actual links):
    • Manager: src/ai/backend/manager/README.md
    • Agent: src/ai/backend/agent/README.md
    • Storage Proxy: src/ai/backend/storage/README.md
    • Webserver: src/ai/backend/web/README.md
    • App Proxy: src/ai/backend/appproxy/README.md
  • If component READMEs reference additional documentation, follow those links
  • Common additional documentation types:
    • Architecture diagrams
    • API documentation
    • Configuration guides
    • Development guides
  • Important: Only follow links that are relevant to answering the user's question
Step 5: Synthesize and Present Information
  • Combine information from all fetched sources
  • Structure the answer logically:
    1. Direct answer to the user's question
    2. Supporting details from official documentation
    3. Related component interactions (if applicable)
    4. Links to source documentation for further reading
  • Use clear headings and formatting
  • Include code examples or configuration snippets when relevant
Show full SKILL.md (275 more words)Show less

Best Practices

  1. Always Cite Sources

    • Reference the specific documentation URLs you fetched
    • Help users find more detailed information
  2. Stay Current

    • Fetch documentation fresh each time (don't rely on cached knowledge)
    • Note version requirements (Python, Docker, PostgreSQL, etc.)
  3. Explain Component Interactions

    • Backend.AI is a distributed system - explain how components work together
    • Clarify the relationship between WebUI (this project) and Backend.AI backend
  4. Be Precise with Technical Details

    • Include version numbers, requirements, and configuration details
    • Distinguish between different API types (REST vs GraphQL)
  5. Limit Recursion Depth

    • Fetch main README + relevant component READMEs
    • Only follow 1-2 additional link levels unless user needs deep details
    • Balance thoroughness with response time

Example Question Types

Architecture Questions

  • "How does Backend.AI work?"
  • "What is the architecture of Backend.AI?"
  • "What are the main components of Backend.AI?"

Component Questions

  • "What does the Backend.AI Manager do?"
  • "How does the Agent component work?"
  • "What is the Storage Proxy?"

Integration Questions

  • "How does this WebUI connect to Backend.AI?"
  • "What APIs does Backend.AI expose?"
  • "How do I authenticate with Backend.AI?"

Setup Questions

  • "What are the requirements for Backend.AI?"
  • "How do I set up Backend.AI?"
  • "What infrastructure does Backend.AI need?"

Response Format

Structure answers as follows:

markdown
## [Direct Answer to Question]

[Concise, direct answer based on official documentation]

## Details

[Supporting information from fetched documentation]

### Component Interactions (if applicable)

[How different components work together]

## Technical Specifications (if applicable)

- Requirements: [versions, dependencies]
- Configuration: [relevant settings]
- APIs: [REST/GraphQL endpoints]

## Source Documentation

- Main: [URL to main README]
- Component: [URLs to component READMEs]
- Additional: [URLs to other relevant docs]

Notes

  • Backend.AI is the backend platform that this WebUI project connects to
  • This WebUI (backend.ai-webui) is a client application that uses Backend.AI's APIs
  • When users ask about "the backend" in this project context, they likely mean Backend.AI
  • Distinguish between WebUI code (this project) and Backend.AI platform code (separate repo)

Limitations

  • This skill only fetches publicly available GitHub documentation
  • For questions requiring internal documentation or specific deployment details, direct users to Backend.AI team
  • Cannot access private repositories or non-public documentation

© lablup, LGPL-3.0. 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 5 other files in .claude/skills/backend-ai-guide of lablup/backend.ai-webui.

  • SKILL.md
  • common-questions.md
  • component-overview.md
  • examples/architecture-example.md
  • examples/component-example.md
  • examples/webui-integration-example.md

Open the folder on GitHubat commit 10554dc

Used in 1 other repository

We found 7 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in lablup/backend.ai-webui, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Backend AI Guide 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.

Backend AI Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backend AI Guide this skilllablup/backend.ai-webui1331 repos~1.8kAutomated safety check: PassLGPL-3.0
Senior Backenddavila7/claude-code-templates32k1 repos~1.1kAutomated safety check: NotesMIT
Backend Developertheneoai/awesome-skills183—~2.1kAutomated safety check: PassMIT
Create Cuda Python Pull RequestNVIDIA/cuda-python3.4k—~1.1kAutomated safety check: PassApache-2.0
Unraiddinglebear-ai/unraid135—~5.4kAutomated safety check: NotesMIT
Unraiddinglebear-ai/unraid135—~2.8kAutomated safety check: PassMIT

Similar skills

  • Senior Backend

    davila7/claude-code-templates

    Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs.

    32k GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check: notes
  • Backend Developer

    theneoai/awesome-skills

    Elite Backend Developer skill with expertise in API design (REST, GraphQL, gRPC), microservices architecture, database optimization (PostgreSQL, MongoDB, Redis), and distributed systems.

    183 GitHub stars~2.1k tokensUpdated 4 mo ago
    Backend & APIsAuto-check passed
  • Official

    Create a CUDA Python pull request from an approved personal or organization-owned fork, including the GitHub CLI GraphQL fallback for renamed organization-owned forks.

    3.4k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Unraid

    dinglebear-ai/unraid

    This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check…

    135 GitHub stars~5.4k tokensUpdated 3 days ago
    DevOps & CloudAuto-check: notes
  • Unraid

    dinglebear-ai/unraid

    Query and monitor an Unraid NAS/homelab server — array health, disk temperatures, Docker containers, virtual machines, system metrics, notifications, alerts, shares, UPS status, log files, network…

    135 GitHub stars~2.8k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed
  • Docker

    avibebuilder/claude-prime

    ALWAYS activate when the user's query involves Docker in any way — even if it also matches other skills.

    120 GitHub stars~1k tokensUpdated 4 mo ago
    DevOps & CloudAuto-check: notes

More from lablup/backend.ai-webui

All 13 skills in this repo
  • Walkthrough

    lablup/backend.ai-webui

    Mint a walkthrough for the PR this session just implemented: a set of numbered stops a reviewer opens in the live dev server, each one marking an element on screen with what changed and what to check.

    133 GitHub stars~4.9k tokensUpdated today
    Auto-check: notes
  • Docs Lead

    lablup/backend.ai-webui

    A skill your agent uses whenever the user mentions docs, the manual, documentation, terminology, translations, or screenshots — including indirect mentions like "이 PR 문서 영향 봐줘", "문서 점검", "용어 통일"…

    133 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Dev Server

    lablup/backend.ai-webui

    Start the project's development server (pnpm dev for backend.ai-webui; discovered from README/package.json elsewhere), deriving the header color, app name, default backend endpoint and login…

    133 GitHub stars~6.9k tokensUpdated today
    Auto-check: notes
  • Record E2E Gif

    lablup/backend.ai-webui

    Record Playwright e2e tests as one GIF per test case (video → ffmpeg palette GIF) and return a markdown table for a PR description.

    133 GitHub stars~907 tokensUpdated today
    Auto-check: notes
  • Relay Mutation Store Updates

    lablup/backend.ai-webui

    A skill your agent uses when writing if (success) updateFetchKey(), an onRequestClose handler, or any refetch after a mutation; when a setting modal handles both create and update behind one…

    133 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Release Train Prep

    lablup/backend.ai-webui

    Post a Korean release risk digest to a Microsoft Teams thread, grouped by risk category.

    133 GitHub stars~5k tokensUpdated today
    Auto-check passed

Categories

Questions about Backend AI Guide

What does Backend AI Guide do?

Expert guide for Backend.AI distributed computing platform. An agent skill from lablup/backend.ai-webui. ai-webui.AI distributed computing platform.

When should I use Backend AI Guide?

Backend AI Guide fits situations like: S ask about: - Backend.AI architecture; components (Manager; app Proxy) - Features (session scheduling; sokovan orchestrator.

How do I install Backend AI Guide in Claude Code?

Run `npx skills add lablup/backend.ai-webui --skill backend-ai-guide -a claude-code`. Or copy the skill folder (.claude/skills/backend-ai-guide in lablup/backend.ai-webui) into .claude/skills/backend-ai-guide in your project. Claude Code loads it when a task matches its description.

How do I install Backend AI Guide in Codex?

Run `npx skills add lablup/backend.ai-webui --skill backend-ai-guide -a codex`. Or copy the skill folder (.claude/skills/backend-ai-guide in lablup/backend.ai-webui) into .agents/skills/backend-ai-guide in your project. Codex loads it when a task matches its description.

Can I use Backend AI Guide 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 lablup/backend.ai-webui --skill backend-ai-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backend-ai-guide, .gemini/skills/backend-ai-guide, .github/skills/backend-ai-guide and .opencode/skills/backend-ai-guide in your project.

What does Backend AI Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: Backend AI Guide is instructions for the agent only. Our summary lists: Python 3; Docker. Its frontmatter pre-approves these tools: WebFetch, Read.

Does Backend AI Guide access the network?

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

Is Backend AI Guide 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 Backend AI Guide use?

Backend AI Guide is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Backend AI Guide use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Backend AI Guide?

Skills that share tags, products or a category with Backend AI Guide: Senior Backend (davila7/claude-code-templates, 32k stars), Backend Developer (theneoai/awesome-skills, 183 stars), Create Cuda Python Pull Request (NVIDIA/cuda-python, 3.4k stars) and Unraid (dinglebear-ai/unraid, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backend AI Guide?

lablup (a GitHub organization) maintains it in lablup/backend.ai-webui, which has 133 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.

Source: lablup/backend.ai-webui on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.