realZillionX/InspireSkill

启智平台的 Agent 驾驶舱：Skill + CLI，一条命令直达。Agent cockpit for the Inspire ML platform: one command, every operation, straight from chat.

What it solves

InspireSkill acts as a bridge between popular AI coding agents (like Cursor, Claude Code, and Codex) and the Inspire compute platform. It solves the friction of manually managing research resources—such as requesting compute, creating notebooks, submitting training jobs, and managing datasets—by converting the platform's web-based interface into a CLI and a set of agent-native skills.

How it works

It provides a three-part system: a inspire CLI for direct command-line control of resources; a set of SKILL.md files that teach AI agents how to interact with the platform's specific workflows; and a Python SDK for programmatic access. By installing these skills into your preferred AI agent's environment, the agent can autonomously handle tasks like checking resource availability, submitting GPU jobs, monitoring logs, and managing model deployments without requiring you to switch to a different platform-specific tool.

Who it’s for

Researchers and developers who use the Inspire compute platform and want to automate their infrastructure management using their existing AI coding assistants (e.g., Cursor, Claude Code, Kimi Code, etc.) rather than relying on manual web-based operations.

Highlights

  • Agent-Native Integration: Injects platform capabilities directly into your existing AI coding agent's workflow.
  • Full Lifecycle Management: Supports Notebooks, GPU jobs, HPC (Slurm), Ray clusters, model serving, and TensorBoard monitoring.
  • Resource Intelligence: Provides real-time visibility into quota, node availability, and job health, allowing agents to make informed scheduling decisions.
  • Multi-Account Support: Manages multiple platform accounts locally, allowing for easy switching between different research projects or workspaces.

Related

  • Project
    ray-r-ren/agent-apprenticeship

    Agent Apprenticeship is a CLI toolkit that runs AI code‑generation agents in iterative loops, lets a mentor model evaluate each step, and saves the whole execution as reusable "experience compilations" that can be shared or installed as training data.

  • Project
    MoizIbnYousaf/ai-agent-skills

    A genuine npm‑based CLI/TUI that ships a curated library of AI‑agent skills, lets you build and manage your own skill collections, and integrates with many LLM‑agents via the Agent Skills spec.

  • Project
    codeaholicguy/ai-devkit

    AI DevKit is a Node‑based, Apache‑2.0‑licensed tool that adds a shared configuration, console UI, SQLite‑backed memory, cross‑agent messaging, and composable engineering “skills” (requirements, design, TDD, verification, security review, etc.) to multiple AI coding assistants (Claude Code, Gemini‑CLI, Codex‑CLI, Cursor, Copilot, etc.). It lets developers run, supervise, and coordinate these agents from a single control plane, reducing scattered setups and enforcing disciplined development workflows.

  • Project
    luongnv89/asm

    A scriptable CLI for installing and managing AI agent skills across 21 different providers, featuring token cost tracking and security scanning.

  • Project
    HKUDS/CLI-Anything

    CLI‑Anything is an open‑source Python framework that automatically generates agent‑friendly command‑line wrappers for any software. It ships a package manager (`cli‑anything‑hub`) that indexes dozens of community‑built CLIs (GIMP, Blender, Zoom, GIS tools, etc.) and lets agents discover, install, and invoke them via structured JSON output. Developers can use a 7‑phase generator to create new CLIs for any application, and AI agents (Claude Code, Cursor, Pi, OpenClaw, …) can install the meta‑skill to browse the registry autonomously. The project is actively maintained, well‑tested (2 461 passing tests), and Apache‑2.0 licensed.