{
  "markdown": "# SkillOS\n\nSkillOS is an enterprise-grade **Continuous Agentic Skills Framework**. It acts as the definitive \"operating system\" for your AI coding agents, built on top of a set of composable skills and highly authoritative instructions that make sure your agent uses them.\n\n## Quickstart\n\nGive your agent an Operating System: [Gemini CLI](#gemini-cli), [Claude Code](#claude-code), [Cursor](#cursor), [Copilot CLI](#github-copilot-cli).\n\n## How it works\n\nIt starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it *doesn't* just jump into trying to write code. Instead, it respects the **SkillOS Bootstrapper** and hooks into the **Methodology Engine**.\n\nSkillOS enforces a strict state machine. The agent is logically and cryptographically blocked from writing application code until the **Brainstorming** and **Planning** phases are signed off. \n\nIt heavily emphasizes **Andrej Karpathy's LLM Coding Guidelines**:\n- Think Before Coding\n- Simplicity First\n- Surgical Changes\n- Goal-Driven Execution\n\nOnce you say \"go\", it leverages the **JIT Context Kernel** to dynamically load only the skills it needs (Progressive Disclosure) preventing context window bloat. The system continuously runs an `@audit_logger` telemetry to document the agent's actions into a lightweight project memory file.\n\nIf your agent runs a terminal command that fails two times consecutively, the built-in **Anti-Looping Failsafe** will force it to halt and request human intervention. Your coding agent doesn't just write code; it operates with surgical discipline.\n\n## Installation\n\nInstallation differs by harness. The framework is designed as a portable, cross-platform extension.\n\n### Gemini CLI\n\nSkillOS can be installed directly as a Gemini extension:\n\n```bash\ngemini extensions install https://github.com/naravid19/skill-os\n```\n\n- Update later:\n  ```bash\n  gemini extensions update skill-os\n  ```\n\n### Claude Code\n\n1. Clone the repository into your global or local tools directory:\n   ```bash\n   git clone https://github.com/naravid19/skill-os\n   cd skill-os\n   ```\n2. The framework includes a native `.claude-plugin/` configuration folder. Claude Code will automatically wire up the instructions.\n\n### Cursor\n\n1. Clone the repository into your project directory:\n   ```bash\n   git clone https://github.com/naravid19/skill-os\n   cd skill-os\n   ```\n2. The framework includes a native `.cursor-plugin/` configuration folder. Open Cursor Agent chat and the rules will automatically apply.\n\n### GitHub Copilot CLI\n\nSkillOS hooks natively support Copilot CLI context injection. Ensure you have the `COPILOT_CLI` environment variable configured and run the `session-start` hook.\n\n---\n\n## 🛠 Initialization (Required for all platforms)\n\nAfter installing/cloning, you must initialize the **JIT Catalog**.\nRun the indexer to scan all local and external skills and generate the `SKILL_CATALOG.json` file. The AI agent needs this file to load skills efficiently.\n\n```bash\npython scripts/indexer.py\n# Or use `py scripts/indexer.py` on Windows\n```\n\n*(Optional) Configure External Skills:*\nIf you have a centralized folder for agent skills outside this project, set the environment variable so the indexer can find them:\n- **Windows (PowerShell):** `$env:SKILLOS_EXTERNAL_DIRS=\"C:\\path\\to\\your\\external\\skills\"`\n- **macOS/Linux:** `export SKILLOS_EXTERNAL_DIRS=\"/path/to/your/external/skills\"`\n\n## The Basic Workflow\n\n1. **1_Brainstorming** - Activates before writing code. Refines rough ideas through questions, explores alternatives, and presents design in sections for validation.\n2. **2_Planning** - Activates with approved design. Breaks work into bite-sized tasks. Every task has exact file paths, complete code, and verification steps.\n3. **3_TDD_Execution** - Enforces RED-GREEN-REFACTOR. The agent must write a failing test, watch it fail, write minimal code to pass it, and commit.\n4. **4_Review** - Activates when tasks complete. Verifies tests and cleans up the workspace.\n\n**The agent checks for relevant skills before any task.** Mandatory workflows, not suggestions.\n\n## What's Inside\n\n### Core Architecture\n- **Hooks (`hooks/`)** - Cross-platform polyglot wrappers (`run-hook.cmd`) that inject JSON context into Claude, Cursor, and Copilot on startup.\n- **Scripts (`scripts/`)** - Background daemons including the `state_manager`, `indexer` (JIT Context Kernel), and `memory_manager` (Audit Telemetry).\n- **Skills (`skills/`)** - The repository of authoritative commands, utilizing Progressive Disclosure.\n\n### Skills Library\n- **skill-creator** - Create new skills following the Agent Skills Framework best practices.\n- **planning** - Enforces TDD and the anti-looping rules.\n\n## Philosophy\n\n- **Test-Driven Development** - Write tests first, always.\n- **Systematic over ad-hoc** - Process over guessing.\n- **Complexity reduction** - Simplicity as primary goal.\n- **Evidence over claims** - Verify before declaring success.\n\n## Contributing\n\nThe general contribution process for SkillOS is below:\n\n1. Fork the repository\n2. Switch to the `dev` branch\n3. Create a branch for your work\n4. Follow the `skill-creator` skill for creating and testing new and modified skills\n5. Submit a PR.\n\n## License\n\nMIT License - see `package.json` for details.\n\n## Community\n\nBuilt and maintained by **Naravid**.\n\n- **GitHub Repository**: https://github.com/naravid19/skill-os",
  "bytes": 5397,
  "sha": "5f2df2d0c9f055ef35a147b725b69dd92cc73d804109ae6bd75c1ac449e798ce",
  "repo_slug": "naravid19/skill-os",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_naravid19_skill_os_a036271c/readme"
}