opensite-ai/opensite-skills / linux-ai-dev-stack
linux-ai-dev-stack
FlaggedInstall and wire the AI toolchain on a Linux dev machine: local LLM inference (Ollama, llama.cpp, vLLM, SGLang, TabbyAPI) with VRAM-based model selection, AI coding agents and CLIs (Claude Code, Codex, aider, OpenCode) with MCP servers, ML frameworks (PyTorch/JAX, Jupyter, HuggingFace) and GPU containers, and cloud/remote GPU workflows (RunPod, Vast.ai, Lambda, remote dev over SSH and Tailscale). Use when someone wants to run local models, set up or connect AI coding agents, configure MCP servers, route agents to local or cloud models, install an ML/GPU Python stack, or offload work to a rented GPU. It runs on the machine and assumes working GPU drivers.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.9 KB |
| agents/openai.yaml | config | 420 B |
| examples/24gb-nvidia-local-plus-cloud.md | markdown | 5.0 KB |
| references/activation.md | markdown | 2.9 KB |
| references/ai-coding-agents.md | markdown | 7.1 KB |
| references/local-llm-inference.md | markdown | 11.9 KB |
| references/mcp-servers.md | markdown | 4.5 KB |
| references/ml-frameworks.md | markdown | 5.0 KB |
| references/model-wiring.md | markdown | 4.6 KB |
| references/remote-gpu.md | markdown | 4.1 KB |
| templates/AGENTS.md | markdown | 1.8 KB |
| templates/gpu-compose.yaml | config | 1.4 KB |
| templates/litellm-config.yaml | config | 2.3 KB |
templates/AGENTS.md
View on GitHub<!--
AGENTS.md — cross-tool agent instructions (the emerging standard).
Read by Codex, Gemini CLI, aider, Goose, OpenCode, Zed, Warp, Cursor, VS Code, and more.
Claude Code reads CLAUDE.md natively. Keep ONE source of truth by symlinking:
ln -s AGENTS.md CLAUDE.md
Then edit only this file. Keep it concise and high-signal; nested per-subsystem
AGENTS.md files override/merge (closest file wins).
-->
# Agent Instructions
## Project overview
<!-- One or two sentences: what this project is and its primary language/framework. -->
TODO: describe the project.
## Build, test, and run commands
<!-- The exact commands an agent should use. Prefer the project's own gates. -->
- Install: `TODO`
- Build: `TODO`
- Test: `TODO`
- Lint / format: `TODO`
- Run locally: `TODO`
## Conventions
- Language/style: TODO (e.g. formatter + linter, import order, naming).
- Commit style: TODO (e.g. Conventional Commits).
- Branching: TODO (e.g. feature branches off `main`; never commit to `main`).
## Guardrails (safety)
- Never run destructive commands without explicit confirmation: `rm -rf`,
`git push --force`, `git reset --hard`, database drops, package publishes.
- Do not read or print secrets. Secrets live outside the repo and are injected at
runtime (e.g. `op run -- <cmd>`). Do not commit `.env` or tokens.
- Prefer plan mode / read-only exploration before large multi-file edits.
- Ask before opening firewall ports or binding a service to `0.0.0.0`.
## Model routing (optional)
- Cheap/read-only tasks (search, tests, classification): a small or local model.
- Everyday coding: mid-tier model. Architecture/review: top-tier model.
- Local model endpoint (if configured): `http://localhost:11434/v1` (Ollama).
## Notes for humans
- This file is the single source of truth for all agents. `CLAUDE.md` is a symlink to it.
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: 471k | Updated | Claude CodeCodex | Unverified | 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 |