internet-court/internet-court-skill / vendored/0g/0g-compute
0g-compute
Verified0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integration (0g-serving-broker), processResponse API, broker.inference methods, CLI commands (0g-compute-cli), and account management. Use this skill for any 0G compute, 0G AI, or decentralized GPU question.
| File | Kind | Size |
|---|---|---|
| .github/workflows/claude-code-review.yml | config | 4.5 KB |
| LICENSE | other | 345 B |
| README.md | markdown | 2.5 KB |
| SKILL.md | skill md | 7.3 KB |
| references/account-management.md | markdown | 20.3 KB |
| references/examples/README.md | markdown | 4.9 KB |
| references/examples/speech-to-text.md | markdown | 17.5 KB |
| references/examples/streaming-chat.md | markdown | 17.1 KB |
| references/examples/text-to-image.md | markdown | 14.9 KB |
| references/fine-tuning.md | markdown | 18.1 KB |
| references/inference.md | markdown | 12.8 KB |
README.md
View on GitHub# 0G Compute Skills
> **Note**: This repository has been superseded by [0g-agent-skills](https://github.com/0gfoundation/0g-agent-skills) as the unified entry point for all 0G skills.
An [Agent Skills](https://agentskills.io) compatible skill for working with 0G Compute Network — a decentralized GPU marketplace for AI inference and model fine-tuning.
## Supported Platforms
This skill follows the [Agent Skills open standard](https://agentskills.io) and works with:
- **Claude Code** — `~/.claude/skills/0g-compute/`
- **OpenAI Codex** — `~/.agents/skills/0g-compute/`
- **OpenClaw** — `~/.openclaw/skills/0g-compute/`
- **Cursor, Gemini CLI, VS Code, Roo Code** — standard SKILL.md discovery
## Installation
```bash
# Claude Code
git clone https://github.com/0gfoundation/0g-compute-skills ~/.claude/skills/0g-compute
# OpenAI Codex
git clone https://github.com/0gfoundation/0g-compute-skills ~/.agents/skills/0g-compute
# OpenClaw
git clone https://github.com/0gfoundation/0g-compute-skills ~/.openclaw/skills/0g-compute
```
For project-scoped installation, clone into your project's `.claude/skills/` (or equivalent) directory instead.
## Structure
```
0g-compute-skills/
├── SKILL.md # Core skill (always loaded by LLM)
├── references/
│ ├── inference.md # SDK patterns for all service types
│ ├── fine-tuning.md # Complete fine-tuning workflow
│ ├── account-management.md # Fund management guide
│ └── examples/
│ ├── README.md # Examples index
│ ├── streaming-chat.md # Complete streaming chat project
│ ├── text-to-image.md # Complete image generation project
│ └── speech-to-text.md # Complete transcription project
└── README.md # This file (GitHub-facing)
```
**Progressive disclosure**: `SKILL.md` (~2,500 tokens) is always loaded. Reference files (~2,200-3,100 tokens each) are loaded on demand when the user's question requires detailed guidance.
## Verification
1. Open your AI coding agent
2. Ask: "What skills are available?" or type `/0g-compute`
3. You should see `0g-compute` in the available skills
## Resources
- [0G Compute Documentation](https://docs.0g.ai)
- [SDK GitHub](https://github.com/0gfoundation/0g-serving-broker)
- [Starter Kit](https://github.com/0gfoundation/0g-compute-ts-starter-kit)
- [Discord Community](https://discord.gg/0glabs)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |